OS-PCORTF Product Library

The projects in the OS-PCORTF portfolio support the development of a wide and diverse array of products and services intended to expand or strengthen federal data capacity for patient-centered outcomes research. The OS-PCORTF Product Library, complemented by the product descriptions in the completed projects in the OS-PCORTF Project Portfolio, presents the most comprehensive view of the products produced by OS-PCORTF projects.

Please bookmark this page -- new products will be added as projects are completed.

The products are open for public and governmental uses, although attribution may be required for some resources; certain data holders may charge user fees for access. Products may be at different stages of maturity upon completion of project support from the OS-PCORTF.

Product Types:

Project Outputs by Product Category	Project and Portfolio Reports, Profiles, and Evaluations
Datasets and Databases (including linked data)	Project Reports and Briefs
Data Elements & Information Models	Vignettes, Project Spotlights, and Portfolio Reports
HIT Standards	Annual Reports
Tools and Guides	Evaluation Reports
Software and Analytic Services
Data Governance Products
Publications

Datasets and Databases

Child and Caregiver Outcomes Using Linked Data (CCOULD) Dataset and User Guide

These linked, state datasets contain information from both child welfare and Medicaid information systems on case demographics, medical diagnoses, services, outcomes, and other relevant information. The dataset is accompanied by a user guide that explains the background, purpose, and design of the study; the data de-identification procedures; the data limitations; and analytical considerations. A codebook for the dataset is available on request.

Product Type: Linked dataset
Year Released: 2023
Project: Project Description
Agency: Assistant Secretary for Planning and Evaluation (ASPE) and Administration for Children and Families (ACF)
Link: Read more about the dataset and user guide

Social Determinants of Health Database

These files contain the Agency for Healthcare Research and Quality’s (AHRQ) database on Social Determinants of Health (SDOH). These files are curated from existing Federal datasets and other publicly available data sources. The purpose of the files is to make it easier to find a range of well documented, readily linkable SDOH variables across domains without having to access multiple source files, facilitating SDOH research and analysis. The July 2022 updated SDOH Database includes data through 2020 at the county, ZIP Code, and tract levels.

Product Type: Database
Year Released: 2022
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Link: Read more about the SDOH database

Training Data for the Tuberculosis Drug Resistance Use Case

These training data on tuberculosis (TB) drug resistance can be used by others to develop research models using machine learning. These are available for download on the National Institutes of Health (NIH) National Institute of Allergy and Infectious Disease's (NIAID) TB portals.

Product Type: Dataset
Year Released: 2022
Project: Project Description
Agency: National Institutes of Health (NIH) and Office of the National Coordinator for Health Information Technology (ONC)
Link: Dataset information and access requirements

Training Datasets and Validated Machine Learning Algorithms from the United States Renal Data System

These training datasets and validated machine learning algorithms use data from the United States Renal Data System (USRDS) for their kidney disease use case: predicting mortality in the first 90 days following initiation of chronic dialysis in end-stage kidney disease patients. The training dataset includes 188 elements, including demographics, prior care, clinical variables, comorbidities, and patient education and contains over 1 million individual patients. The Office of the National Coordinator for Health Information Technology (ONC) team prepared two versions of the dataset using imputed and non-imputed values.

The 2016 National Hospital Care Survey (NHCS)/National Death Index (NDI)/Drug-Involved Mortality (DIM) Enhanced Dataset

This dataset includes linked data on hospitalizations, mortality, and drugs and includes data from the National Hospital Care Survey (NHCS) 2016, National Death Index (NDI) 2016-2017, and the Drug-Involved Mortality (DIM) 2016-2017. The dataset is available through the National Center for Health Statistics Research Data Center by request.

Product Type: Linked dataset
Year Released: 2021
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Link: Dataset information and access requirements

Linked Dataset: 2016 National Hospital Care Survey (NHCS) to 2015/2017 U.S. Department of Housing and Urban Development (HUD) Data

This file contains the linkages of the 2016 National Hospital Care Survey (NHCS) to the 2015/2017 U.S. Department of Housing and Urban Development (HUD) data. Data are accessible only through the National Center for Health Statistics (NCHS) Research Data Center (RDC).

Linked NHCS and CMS Medicare MBSF Claims/Encounters and Assessment Data

The 2016 NHCS has been linked to the 2016-2017 CMS Medicare MBSF, Claims/Encounters, and Assessment data. The linked dataset provides the opportunity to conduct a vast array of studies on health care utilization and expenditures among the elderly U.S. population and persons receiving Medicare disability benefits.

Product Type: Linked dataset
Year Released: 2020
Project: Project Description
Agency: Centers for Disease Control and Prevention, Food and Drug Administration, Centers for Medicare and Medicaid Services
Link: Dataset information and access requirements

NHCS and NDI linked with the National Vital Statistics System mortality files on drug overdose deaths (NVSS-M-DO) file

The dataset includes the following: 1) Merged 2014 NHCS/NDI/NVSS-M-DO, and 2) Merged 2016 NHCS/NDI/NVSS-M-DO. Analysis of this data set will result in a report exploring characteristics of individuals who have opioid-related events, patterns of hospital use in months prior to death, and comparison of patients and services.

Product Type: Linked dataset
Year Released: 2020
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: Read more about the linkage

AHRQ Social Determinants of Health Database (Beta Version)

The purpose of this project is to create easy to use, easily linkable SDOH-focused data to use in PCOR research, inform approaches to address emerging health issues, and ultimately contribute to improved health outcomes. These SDOH beta data files are curated from existing Federal datasets and other publicly available data sources. The purpose of the files is to make it easier to find a range of well documented, readily linkable SDOH variables across domains without having to access multiple source files, facilitating SDOH research and analysis.

Product Type: Database
Year Released: 2020
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: Read more about the linkable database

Linked National Hospital Care Survey (NHCS) and National Death Index (NDI) Mortality Data

The linked NHCS data with the NDI mortality data provides the opportunity to conduct a vast array of outcome studies designed to investigate the association of a wide variety of health factors with mortality. The linked datasets include 2014 NHCS linked to 2014-2015 NDI Mortality Data and the 2016 NHCS linked to 2016-2017 NDI Mortality Data.

Product Type: Linked dataset
Year Released: 2018 & 2019
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: Dataset information and access requirements

Linked Dataset

2016 National Hospital Care Survey (NHCS) Inpatient and Emergency Department Claims and Electronic Health Records (EHRs) to the 2016/2017 National Death Index (NDI) This file contains the linkages of the 2016 National Hospital Care Survey (NHCS) inpatient and emergency department claims and electronic health records (EHRs) with the 2016/2017 National Death Index (NDI). Linkage of NHCS data with the NDI mortality data provides the opportunity to conduct a vast array of outcome studies designed to investigate the association of a wide variety of health factors with mortality.

Product Type: Linked dataset
Year Released: 2019
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Link: Dataset information and access requirements

Linked NHCS and CMS Medicare Master Beneficiary Summary File (MBSF) Data

The 2014 NHCS has been linked to the 2014-2015 CMS Medicare Master Beneficiary Summary File (MBSF). The linked data allows for new analyses, such as examining comorbidities and utilization of non-inpatient-related health care services.

Product Type: Linked dataset
Year Released: 2019
Project: Project Description
Agency: Centers for Disease Control and Prevention, Food and Drug Administration, Centers for Medicare and Medicaid Services
Link: Dataset information and access requirements

Data Elements & Information Models

Multiple Chronic Care Conditions Value Sets

This value set library defines value sets relevant to research and care for people with multiple chronic conditions, including chronic kidney disease, cardiovascular disease, diabetes, chronic pain, and opioid use disorder that can be used along with FHIR® profiles as part of the Multiple Chronic Care (MCC) Conditions eCare Plan. These value sets, included in the MCC eCare Plan Implementation Guide, were developed by the National Health Institute (NIH)/ National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) team, in collaboration with AHRQ, are housed on National Library of Medicine (NLM) Value Set Authority Center.

Product Type: Data/Technical Product
Year Released/Updated: 2023
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ) | National Institutes of Health/National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
Product Link: Access Value Set Library

Training Data for Machine Learning to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure Data Dictionary

This data dictionary provides detailed information on the variables in the training dataset, such as dataset of origin, category, variable name, feature description, and variable type.

Product Type: Data/Technical Product
Year Released/Updated: 2021
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC) | National Institutes of Health/National Library of Medicine (NLM)
Product Link: View Data Dictionary

FHIR® Library for Depression Outcome Measures

This library includes the harmonized depression outcome measures, including Clinical Quality Language (CQL) and links to appropriate value sets. This library can be used by others to reproduce code for condition outcome definitions and criteria for use cases beyond those studied by the Agency for Health Research and Quality (AHRQ) team.

Product Type: Data/Technical Product
Year Released/Updated: 2020
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Product Link: View Implementation Guide

Libraries of Clinical Definitions for Outcome Measures

AHRQ publicly posted clinical definitions (“Standardized Library”) of outcome measures in five clinical areas, including (1) Atrial fibrillation, (2) Asthma, (3) Depression, (4) Lung cancer, and (5) Lumbar spondylolisthesis on its Effective Healthcare Program website.

Product Type: Data/Technical Product
Year Released: 2018-2021
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Link: View Definitions

GitHub Annotations for 1,000 Vaccine Adverse Event Reporting System (VAERS) Reports

The FDA project team initiated and completed the generation of an annotated corpus to support training and development efforts of language models. The complete clinical and temporal annotations for the 1,000 Vaccine Adverse Event Reporting System (VAERS) reports are publicly available to the research community on GitHub.

Product Type: Data/Technical Product
Year Released: 2018
Project: Project Description
Agency: Food and Drug Administration
Link: GitHub Code

NIH Common Data Elements Repository

The NIH Common Data Elements (CDE) Repository provides access to structured human and machine-readable definitions of data elements that have been recommended or required by NIH Institutes and Centers and other organizations for use in research and for other purposes.

Product Type: Data/Technical Product
Year Released: 2015
Project: Project Description
Agency: National Institutes of Health (NIH)
Link: View Resource

HIT Standards

Making Electronic Data More Available for Research and Public Health (MedMorph) Reference Architecture HL7® FHIR Implementation Guide

This content implementation guide establishes the MedMorph Reference Architecture that provides a standardized yet flexible template infrastructure for automated data exchange from a data source to a data receiver, with or without an intermediary. This resource is for programs interested in leveraging a streamlined approach for automated data exchange to support their use case(s).

Product Type: HL7 Implementation Guide
Year Published/Updated: 2023
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: View Content Implementation Guide

Making Electronic Data More Available for Research and Public Health (MedMorph) Healthcare Surveys Content HL7® FHIR Implementation Guide

This content implementation guide based on the MedMorph Reference Architecture that supports the health care surveys use case. This resource is for external organizations interested in adopting the reference architecture.

The Multiple Chronic Conditions (MCC) eCare Plan HL7® FHIR® Implementation Guide (Continuous Build Version)

The HL7® Multiple Chronic Condition (MCC) Care Plan Implementation Guide (IG) defines FHIR R4 profiles, structures, extensions, transactions, and value sets needed to represent, query for, and exchange Care Plan information. This initial version focuses on Chronic Kidney Disease Type 2 diabetes mellitus, common cardiovascular disease (hypertension, ischemic heart disease and heart failure), chronic pain and Long COVID. The implementation guide is currently being balloted through HL7 in the September 2023 ballot cycle.

Product Type: HL7 Implementation Guide
Year Released/Updated: 2020, updated through 2023
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ) | National Institutes of Health/National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
Product Link: View Implementation Guide

Making Electronic Data More Available for Research and Public Health (MedMorph) Central Cancer Registry HL7® FHIR Implementation Guide

This content implementation guide is based on the MedMorph Reference Architecture that supports the cancer reporting use case. This resource is for external organizations interested in adopting the reference architecture.

Product Type: HL7 Implementation Guide
Year Released/Updated: 2021
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: View Content Implementation Guide

Making Electronic Data More Available for Research and Public Health (MedMorph) Research Data Exchange HL7® FHIR Implementation Guide

This content implementation guide is based on the MedMorph Reference Architecture that supports research use cases. This resource is for external organizations interested in adopting the reference architecture.

Logical Observation Identifiers Names and Codes (LOINC) Equivalence Class Artifact Releases

The project team created three releases of a LOINC Equivalence Class artifact. The first version, LOINC Group File Alpha 1, was released June 2017 (LOINC release 2.61), containing 12 Parent Groups and 2,178 Groups that aggregate a total 6,438 unique LOINC terms. LOINC Group File Alpha 2 was released December 2017 (LOINC release 2.63). It contained 21 Parent Groups, 4,100+ equivalence groups that aggregate more than 17,500 unique LOINC terms. The final version was released June 2018 as LOINC Group File Beta 1 (LOINC release 2.64) and contains 36 parent groups, containing 5,650 groups that organize 24,075 unique LOINC terms. Releases are available in the LOINC release archive.

Product Type: Terminology standard guide
Year Released: 2017
Project: Project Description
Agency: National Institutes of Health
Link: View Product

HL7 Version 2.6 Implementation Guide: Vital Records Death Reporting, Release 1 STU 2 - US Realm

This document provides a technical messaging specification for transmitting death related information using the HL7 Version 2.6 ADT Update Patient Information. The project aims to enable interoperable electronic data exchanges among electronic health record systems, U.S. vital records systems and the national statistical agency, National Center for Health Statistics (NCHS). The use cases represented within this implementation guide (IG) describe the technical requirements for reporting death from a clinical setting to the jurisdictional vital records office that sends vital records information to NCHS. Additionally, the document provides support for NCHS to report information back to the jurisdictional vital records office.

Product Type: HL7 Implementation guide
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Product

Common Data Models Harmonization FHIR Implementation Guide (Release 0.1.0)

This FHIR Implementation Guide will focus on mapping and translating observational data extracted from different research networks for PCOR purposes into FHIR format.

Product Type: HL7 Implementation guide
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Women’s Health Technology CRN FHIR Implementation Guide

The Women’s Health Technologies (WHT) Coordinated Registry Network (CRN) FHIR Implementation Guide (IG) will focus on capturing and exchanging data related to women’s health.

Product Type: HL7 Implementation guide
Year Released:
Project: Project Description
Agency: Food and Drug Administration | National Institutes of Health | Office of the National Coordinator for Health Information Technology
Link: View Product

Patient Reported Outcomes FHIR Implementation Guide

The Patient Reported Outcomes (PRO) FHIR Implementation Guide (IG) will focus on capturing and exchanging patient reported outcome data electronically using the FHIR standard (Release 0.2.0).

Product Type: HL7 Implementation guide
Year Released:
Project: Project Description
Agency: Agency for Health Research and Quality | Office of the National Coordinator for Health Information Technology
Link: View Product

The HAPI Open-Source FHIR® library

This is the homepage for the HAPI-FHIR library, which is developing an open-source implementation of the FHIR (Fast Healthcare Interoperability Resources) specification in Java in order to support the exchange of healthcare data in a modern and developer friendly way.

Product Type: Other documentations related to HIT standards
Year Released:
Project: Project Description
Agency: National Institutes of Health
Link: View Product

Tools and Guides

Training Data for Machine Learning to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure — A Case Study in Tuberculosis Drug Resistance

This document provides details on the datasets, methodology, and snippets of the code used for building the training datasets and machine learning models for a tuberculosis drug resistance use case.

Product Type: Implementation Guide
Year Released/Updated: 2023
Project: Project Description
Agency: National Institutes of Health National Library of Medicine (NLM) | National Institutes of Health National Institute of Allergy and Infectious Diseases (NIAD)
Product Link: View Implementation Guide

Toolkit: Data Sharing for Child Welfare Agencies and Medicaid

This technical assistance document provides guidance to Medicaid and child welfare agencies to assist and support the creation of automated, bi-directional (two-way) data exchanges between their respective information systems. This document describes the population served by both agencies, provides the legal framework for sharing information, summarizes the opportunities and benefits of sharing data, provides tips for overcoming challenges, provides guidance for establishing partnerships and developing a strategic design for bi-directional data exchanges, highlights examples of successfully operating state and locally administered data exchanges and finally, provides cost-allocation guidance.

Product Type: Toolkit
Year Released/Updated: 2022
Project: Project Description
Agency: ASPE’s) Office of Human Services Policy and Administration for Children and Families - Office of Planning Research and Evaluation (ACF/OPRE)
Product Link: View Toolkit

Coordinated Registry Network (CRN) Maturity Framework

The CRN Maturity Framework, which serves as a guide for researchers and clinicians to develop and advance high-quality CRNs by describing proven approaches in seven core technical areas that contribute to CRN success, was published in BMJ Surgery, Interventions, & Health Technologies.

Product Type: Journal Article
Year Released/Updated: 2022
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: Read publication

LOINC Mapping Guide – Chemistry

This is a chemistry domain-specific Logical Observation Identifiers Names and Codes (LOINC) Mapping guide that contains mapping principles, examples, and exercises aimed at helping laboratories map their individual tests or catalogs to appropriate LOINC terms according to current and best practices.

Product Type: Mapping Guide
Year Released/Updated: 2022
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: View Guide

LOINC Mapping Guide – Drug and Toxicology

This is a drug and toxicology domain-specific Logical Observation Identifiers Names and Codes (LOINC) Mapping guide that contains mapping principles, examples, and exercises aimed at helping laboratories map their individual tests or catalogs to appropriate LOINC terms according to current and best practices.

Product Type: Mapping Guide
Year Released/Updated: 2022
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: View Guide

LOINC Mapping Guide – Hematology and Serology

This is a hematology and serology domain-specific Logical Observation Identifiers Names and Codes (LOINC) Mapping guide that contains mapping principles, examples, and exercises aimed at helping laboratories map their individual tests or catalogs to appropriate LOINC terms according to current and best practices.

Product Type: Mapping Guide
Year Released/Updated: 2022
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: View Guide

LOINC Mapping Guide – Molecular Pathology

This is a molecular pathology domain-specific Logical Observation Identifiers Names and Codes (LOINC) Mapping guide that contains mapping principles, examples, and exercises aimed at helping laboratories map their individual tests or catalogs to appropriate LOINC terms according to current and best practices.

Product Type: Mapping Guide
Year Released/Updated: 2022
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: View Guide

The Linkage of the 2014 and 2016 National Hospital Care Survey to U.S. Department of Housing and Urban Development Administrative Data: Matching Methodology and Analytic Considerations

This documentation includes a brief overview of the data sources used for the linkage of the 2014 National Hospital Care Survey (NHCS) to the 2013/2015 U.S. Department of Housing and Urban Development (HUD) data files and the 2016 NHCS to the 2015/2017 HUD data files, a description of the methods, and analytic guidance to assist researchers while using the files. Detailed information on the linkage methodology is provided in the report’s Appendix.

Product Type: Report
Year Released/Updated: 2021
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: View Document

Outcome Measure Harmonization and Data Infrastructure for Patient-Centered Outcomes Research in Depression: Data Use and Governance Toolkit

This white paper summarizes current best practices in sharing registry data and provides additional information to assist registries in sharing data including regulatory and privacy precautions, data governance structure and procedures, and procedures for reviewing and responding to data requests.

Product Type: Toolkit
Year Released/Updated: 2021
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Product Link: View Toolkit

Training Data for Machine Learning to Enhance Patient Centered Outcomes Research (PCOR) Data Infrastructure Implementation Guide for Chronic Kidney Disease Use Case

This document provides details on the methodology and snippets of the code used for building the training datasets and machine learning models for a chronic kidney disease use case, as well as points to consider for other researchers as they undertake similar work.

Product Type: Implementation Guide
Year Released/Updated: 2021
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC) | National Institutes of Health National Library of Medicine (NLM)
Product Link: View Implementation Guide

Natural Language Processing Clinical Language Engineering Workbench (CLEW) User Guidance Document

This document explains how to install and use the Clinical Language Engineering Workbench (CLEW) and products developed in the Centers for Disease Control and Prevention (CDC) and the Food and Drug Administration (FDA) pilots.

Product Type: Manual/user guide
Year Released: 2019
Project: Project Description
Agency: Centers for Medicare & Medicaid Services | Food and Drug Administration
Link: View Report

Data Quality Metrics (DQM) Tool

The Data Quality Metrics (DQM) tool provides a harmonized approach to data characterization across multiple data sources to enable researchers to better assess data source comparability and fitness-for-use. The system operationalizes existing data quality (DQ) parameters and methodologies in a way that is compatible across Common Data Models (CDMs) and data sources. This data model and data source agnostic approach enables the DQM application to facilitate research planning and compare data characteristics across any data source.

Product Type: Toolkit
Year Released: 2019
Project: Project Description
Agency: Food and Drug Administration
Link: View Product

Guide for Using LOINC Microbiology Terms

This resource helps laboratories map their individual tests or catalogs to appropriate Logical Observation Identifiers Names and Codes (LOINC) terms according to current and best practices.

Product Type: Mapping Guide
Year Released/Updated: 2018
Project: Project Description
Agency: Food and Drug Administration (FDA)
Product Link: View Guide

Conceptualizing a Data Infrastructure for the Capture, Use, and Sharing of Patient-Generated Health Data in Care Delivery and Research through 2024 Practical Guide

This document is a practical guide that offers suggested practices and questions to consider for the implementation of the capture, use, and sharing of patient-generated health data in clinical and research settings. Depending on the size of the clinical or research organization (e.g., large health system, solo practitioner), considerations or requirements that influence how the guide is applied at that organization may differ.

Product Type: Implementation/roll-out guide
Year Released: 2018
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Cross-Network Directory Service (CNDS) Project Design and Technical Documentation

The CNDS Project Design and Technical Documentation provides background, architectural overview, and requirements and testing.

Product Type: System documentation
Year Released: 2018
Project: Project Description
Agency: Food and Drug Administration
Link: View Product

Electronic Death Reporting System (EDRS) Online Reference Manual

This document is a resource guide for jurisdictions to support development and sustainability of EDRS.

Product Type: Implementation/roll-out guide
Year Released: 2016
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Product

Utilizing Data from Various Partners in a Distributed Manner

The purpose of this project, Utilizing Data from Various Partners in a Distributed Manner was to develop and test the capability to conduct rapid and secure distributed regression analysis utilizing data for different people that are held at different institutions (horizontally partitioned). In addition, it explored the feasibility of creating a virtual linkage capability to utilize data about a single person that is held at different institutions (vertically partitioned). The goal of the project was to enable research sites within a distributed research network to maintain control of patient-level data while generating valid regression estimates across the network without the need to transfer sensitive information.

Product Type: Methods documentation
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Source Data Capture From EHRS: Using Standardized Clinical Research Data

This report describes the methods and tools to automate the flow of structured electronic health record data into external systems and thereby reduce operating costs, save time, and improve data quality for clinical trials. It is based on a collaboration between investigators at the University of California San Francisco (UCSF) and FDA.

Product Type: Tools and Guides
Year Released:
Project: Project Description
Agency: Centers for Medicare & Medicaid Services
Link: View Report

NLP CLEW Workbench Web Service Technical Report

This report presents a detailed technical description of the core NLP approach of the prototype version of the Workbench and two pilot applications developed using the Workbench. In doing so, the core motivating use cases for NLP across a range of clinical domains were explored. The tools and constituent components that are available as part of the prototype are described.

Product Type: Technical documentation
Year Released:
Project: Project Description
Agency: Food and Drug Administration | Centers for Disease Control and Prevention
Link: View Report

Software and Analytic Services

Published Opioid Natural Language Processing (NLP) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

This natural language processing (NLP) code is an open-source tool used to analyze the clinical notes from the 2016 National Hospital Care Survey (NHCS) data for the fiscal year (FY) 2018. The goal of this code is to flag opioid involvement and overdoses in free text clinical notes.

Product Type: Analytic codes
Year Released/Updated: 2022
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: GitHub Code

Published Medical Code-based (translation from SAS) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

This is a Python version of the original SAS code used to analyze the 2016 National Hospital Care Survey (NHCS) data for the fiscal year (FY) 2018 and 2019. The first algorithm identifies patients with opioid-involved hospitalizations and emergency department (ED) visits (FY18) by utilizing the structured coded medical data and analyzing free text in the EHR clinical notes. The second algorithm then identifies patients with opioid-involved hospitalizations or ED visits that have a co-occurring substance use disorder or a mental health issue (FY19).

Product Type: Analytic codes
Year Released/Updated: 2022
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: GitHub Code

Frailty Algorithms in SAS and R

SAS and R code used in the 2021-2022 ASPE-supported frailty validation using EHR is available on GitHub titled: "Developing and Assessing the Validity of Claims-based Indicators of Frailty & Functional Disabilities and Testing their Use in Other Data (EHRs and linked EHR-claims)". This code is related to the completion of Task 2 (Link and Compare Claims Data with EHR) and Task 3 (Evaluate the Accuracy and Concordance of Claims vs. EHR-based Measures of Frailty) of the project.

Product Type: Algorithmic codes
Year Released/Updated: 2022
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ) | Office of the Assistant Secretary for Planning and Evaluation (ASPE) | Centers for Disease Control and Prevention (CDC) | Centers for Medicare and Medicaid Services (CMS)
Product Link: GitHub Code

Published Substance Abuse Disorder (SUD) and Mental Health Issues (MHI) Natural Language Processing (NLP) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

This is the first release of the code used to analyze the clinical notes from the 2016 National Hospital Care Survey (NHCS) data for the fiscal year (FY) 2019.This repository contains only the substance abuse disorder (SUD) and mental health issues (MHI) search. The goal of this code is to flag MHI and SUD mentions in clinical text, primarily those that rise to diagnosis-level phrasing.

Product Type: Analytic codes
Year Released/Updated: 2021
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Product Link: GitHub Code

Training Dataset Code for Chronic Kidney Disease Use Case

This code used to develop the machine learning algorithm is available on GitHub for use by others for the Chronic Kidney Disease Use Case.

Product Type: Analytic codes
Year Released/Updated: 2021
Project: Project Description
Agency: National Institutes of Health National Library of Medicine (NLM) | Office of the National Coordinator for Health Information Technology (ONC)
Product Link: GitHub Code

National Library of Medicine Training Data GitHub Repository

This repository provides machine learning models for five binary tuberculosis classification problems, including performance evaluation.

Major Depression Outcomes Application

This application is a SMART-on-FHIR® App that uses scores from the Patient Health Questionnaire 9 (PHQ-9) and clinical data to calculate and display standardized depression outcome measures. The purpose of this app is to provide a “snapshot” view of a patient’s depression symptoms and outcomes.

Product Type: Application
Year Released/Updated: 2020
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Product Link: View Application

Synthea™ Disease-specific Modules: Cerebral Palsy

This module models the treatment of sialorrhea (excessive drooling) in cerebral palsy in patients aged 18 and under. It is based on the American Academy for Cerebral Palsy and Developmental Medicine (AACPDM) clinical care pathway for sialorrhea. Synthea™ uses these modules to generate individual synthetic patient records, simulating the progression and treatment of disease from birth to death.

Product Type: Analytic software
Year Released/Updated: 2020
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC)
Product Link: Access the treatment of sialorrhea in cerebral palsy module. For additional information about this module, review the accompanying companion guide. A guidance document for using Synthea™ is also available.

Synthea™ Disease-specific Modules: Prescribing Opioids for Chronic Pain and Treatment of Opioid Use Disorder

This module models the prescribing of opioids for chronic pain and treatment of opioid use disorder (OUD) for patients aged 18 and over. It is based on the Centers for Disease Control (CDC) Guideline for Prescribing Opioids for Chronic Pain. Synthea™ uses these modules to generate individual synthetic patient records, simulating the progression and treatment of disease from birth to death.

Product Type: Analytic software
Year Released/Updated: 2020
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC)
Product Link: Access the prescribing of opioids module. For additional information about this module, review the accompanying companion guide. A guidance document for using Synthea™ is also available.

Synthea™ Disease-specific Modules: Sepsis

This module models the treatment of sepsis in patients age 18+. Synthea™ uses these modules to generate individual synthetic patient records, simulating the progression and treatment of disease from birth to death.

Product Type: Analytic software
Year Released/Updated: 2020
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC)
Product Link: Access the treatment of sepsis module. For additional information about this module, review the accompanying companion guide. A guidance document for using Synthea™ is also available.

Synthea™ Disease-specific Modules: Spina Bifida

This module models myelomeningocele, the most severe form of spina bifida, for patients under the age of 18. Synthea™ uses these modules to generate individual synthetic patient records, simulating the progression and treatment of disease from birth to death.

Product Type: Analytic software
Year Released/Updated: 2020
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology (ONC)
Product Link: Access the spina bifida module. For additional information about this module, review the accompanying companion guide. A guidance document for using Synthea™ is also available.

Blue Button 2.0 Application Programming Interface (API) Developer Sandbox

The Blue Button Sandbox is a place where users can build, and test applications using synthetic sample beneficiary data and get up and running with the Blue Button 2.0 API.

Product Type: Development environment
Year Released: 2016
Project: Project Description
Agency: Centers for Medicare & Medicaid Services
Link: View Product

CMS Blue Button Webpage and API Developer Environment

This webpage houses the CMS Blue Button Application Programming Interface (API) developer environment. Blue Button 2.0 is a standards-based API that delivers Medicare Part A, B, and D data for over 60 million Medicare beneficiaries.

Product Type: Development environment
Year Released:
Project: Project Description
Agency: Centers for Medicare & Medicaid Services
Link: View Product

Patient Matching, Aggregation, and Linking (PMAL) Provider Data Validation Tool

This repository contains a number of command-line utilities and related code libraries for parsing, creating, and validating US-based health provider data. Tools include: parsing, indexing, pulling/loading, and utility scripts. These resources can be used to validate FHIR documents prior to, or at the point of, submission.

Product Type: Data management platform
Year Released: 2017
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

FDA MyStudies App

The FDA MyStudies app lets patients provide data that can be linked to traditional clinical trials, real-world trials, observational studies, and registries. This repository contains the code and documentation for running the FDA MyStudies mobile application, web configuration portal, and storage environment.

Product Type: Mobile Application (source code)
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Product

Clinical Language Engineering Workbench (CLEW) Platform

The CLEW allows the clinical natural language processing community to collaborate and share their work in a central repository. This could enable development of NLP and machine-learning solutions to provide high-quality structured data for clinical, academic, government, and public health organizations. It could also minimize duplication in the development of solutions and expand the availability of tools and services to additional clinical domains.

Product Type: Development environment
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention | Food and Drug Administration
Link: Contact cancerinformatics@cdc.gov

Distributed Regression Analysis (DRA) source code and documentation for the algorithms, and test data and samples reports for each regression model type

The DRA was fully integrated into the 2017 PopMedNet™ release and the new version of the software is available on www.popmednet.org and on Sentinel’s website. In addition to source code and documentation for the algorithms, the Sentinel website also provides test data and sample reports for each regression model type.

Product Type: Analytic codes
Year Released: 2018
Project: Project Description
Agency: Food and Drug Administration
Link: View Product

National Plan & Provider Enumeration System (NPPES) Open Application Programming Interface (API)

This API is an alternative to the downloadable NPPES data files. It allows systems to access NPPES public data in real-time, rather than through batched uploads. The API retrieves data from NPPES daily.

Product Type: Application programming interface (API)
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Identity Matching Adjudicator Collector (IMAC) Tool

The IMAC is a matching algorithm that was modified and used in a pilot as part of this project. Open-source code for the tool is available in GitHub.

Product Type: Algorithmic codes
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Data Governance Products

Legal and Ethical Framework to Use Centers for Disease Control and Prevention Data for Patient-Centered Outcomes Research

This paper offers a legal and ethical framework to navigate the legal and ethical challenges of allowing CDC’s data to be used for PCOR. It outlines the legal restrictions on CDC to answer the question “what can CDC do to support PCOR?” It also offers the ethical guardrails for CDC to consider the question “what should CDC do to support PCOR?” Both legal and ethical considerations are essential to CDC in this process.

Product Type: Legal and ethical framework
Year Released: 2018
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Product

Legal and Ethical Architecture for Patient-Centered Outcomes Research (PCOR) Data (“Architecture”)

This Architecture is a collection of tools and resources that help researchers and others navigate an overview of the legal requirements related to data use, sharing, and disclosure for PCOR. Specifically, the Architecture: a) provides a common structure and model for the analysis of legal requirements and ethical consideration and responsibilities in research, particularly PCOR; b) supports PCOR by illustrating pathways to collect and share data for research that is in compliance with relevant federal laws and regulations and in consideration of state law; and c) supports a culture of trust among stakeholders by applying meaningful and appropriate privacy and security parameters.

Product Type: Legal and ethical framework
Year Released: 2020
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Pilot of a Data Quality Framework to Support Patient Matching

This report is based on a pilot performed to test the Data Quality Framework for Patient Matching Framework. The implementation considerations in this paper are intended to assist organizations in implementing the PDDQ Framework (or the Ambulatory Guide) and to encourage their contributions to developing additional resources to improve the quality of demographic data and patient matching. The PDDQ Framework provides guidance for the standardization of policies, processes, procedures, and practices both locally at the clinic level and across an entire health care system. The framework includes standards and processes to help health care organizations improve the quality of patient demographic data by preventing the creation of duplicate patient records and helping them better manage existing duplicate records.

Product Type: Data quality guide/framework
Year Released: 2019
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Product

Publications

Medical Care Special Issue: Building Data Capacity to Study Economic Outcomes for Patient-Centered Outcomes Research

Product Type: Journal Article
Year Released: 2023
Link: Read the articles

PLOS Digital Health Publication: Synthetic Data in Health Care: Narrative Review

Product Type: Journal Article
Year Released: 2022
Link: Read the article

Medical Care Journal Publication: Federal Data for Conducting Patient-Centered Outcomes Research on Economic Outcomes

Product Type: Journal Article
Year Released: 2022
Link: Read the article

Considerations for Building Federal Data Capacity for Patient-Centered Outcomes Research Related to Intellectual and Developmental Disabilities

Product Type: Report
Year Released: 2021
Link: Read the report

Federal Data for Conducting Patient-Centered Outcomes Research on Economic Outcomes

Brown D, Srinivasan M, Arbulu L, Dullabh P, Curtis K, Zott C, and Smith SR.

Product Type: Report
Year Released: 2021
Link: Read the report

Harmonized outcome measures for use in depression patient registries and clinical practice

Richard E Gliklich, Michelle B Leavy, Lisa Cosgrove, Gregory E Simon, Bradley N Gaynes, Lars E Peterson, Bryan Olin, Collette Cole, J Raymond DePaulo Jr, Philip Wang, Chris M Crowe, Cristina Cusin, Mary Nix, Elise Berliner, Madhukar H Trivedi

Product Type: Journal article
Year Released: 2020
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: Read the article

Harmonized outcome measures for use in asthma patient registries and clinical practice

Richard E Gliklich, Mario Castro, Michelle B Leavy, Valerie G Press, Amisha Barochia, Christopher L Carroll, Julie Harris, Sarah S Rittner, Robert Freishtat, Reynold A Panettieri Jr, Giselle S Mosnaim

Product Type: Journal article
Year Released: 2019
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: Read the article

Harmonized outcome measures for use in atrial fibrillation patient registries and clinical practice: endorsed by the Heart Rhythm Society Board of Trustees

Hugh Calkins, Richard E Gliklich, Michelle B Leavy, Jonathan P Piccini, Jonathan C Hsu, Sanghamitra Mohanty, William Lewis, Saman Nazarian, Mintu P Turakhia

Product Type: Journal Article
Year Released: 2019
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: Read the article

Generation of an annotated reference standard for vaccine adverse event reports

Matthew Foster, Abhishek Pandey, Kory Kreimeyer, Taxiarchis Botsis

Product Type: Journal Article
Year Released: 2018
Project: Project Description
Agency: Centers for Disease Control and Prevention | Food and Drug Administration
Link: Read the article

Inappropriate Utilization in Fee-for-Service Medicare and Medicare Advantage Plans

Shriram Parashuram, Seung Kim, Bryan Dowd

Product Type: Journal Article
Year Released: 2018
Project: Project Description
Agency: Assistant Secretary for Planning and Evaluation
Link: Read the article

Twelve-month health care use and mortality in commercially insured young people with incident psychosis in the United States

Michael Schoenbaum, Jason M Sutherland, Andre Chappel, Susan Azrin, Amy B Goldstein, Agnes Rupp, Robert K Heinssen

Product Type: Journal Article
Year Released: 2017
Project: Project Description
Agency: Assistant Secretary for Planning and Evaluation
Link: Read the article

Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review

Kory Kreimeyer, Matthew Foster, Abhishek Pandey, Nina Arya, Gwendolyn Halford, Sandra F Jones, Richard Forshee, Mark Walderhaug, Taxiarchis Botsis

Product Type: Journal Article
Year Released: 2017
Project: Project Description
Agency: Centers for Disease Control and Prevention | Food and Drug Administration
Link: Read the article

Improving the value of clinical research through the use of common data elements

Jerry Sheehan, Steven Hirschfeld, Erin Foster, Udi Ghitza, Kerry Goetz, Joanna Karpinski, Lisa Lang, Richard P Moser, Joanne Odenkirchen, Dianne Reeves, Yaffa Rubinstein, Ellen Werner, Michael Huerta

Product Type: Journal Article
Year Released: 2016
Project: Project Description
Agency: National Institutes of Health
Link: Read the article

Project Reports and Briefs

Shield (Systemic Harmonization and Interoperability Enhancement for Laboratory Data) - Standardization of Lab Data to Enhance Patient-Centered Outcomes Research and Value-Based Care: Final Report

This report summarizes the accomplishments of the FDA project SHIELD. The project sought to improve the quality, interoperability and portability of laboratory data within and between institutions so that diagnostic information can be pulled from different sources or shared between institutions to help illuminate clinical management and understand health outcomes. The project developed LOINC code mapping manuals for Chemistry, Drug/Toxicology, Allergy, Serology/Hematology, Cell Markers and Molecular Pathology. The also conducted pilot implementation and testing of an interoperability upgrade to existing laboratory information systems (LIS) and registries by incorporating SHIELD-approved, high-quality, industry-defined and supported format to facilitate the publication and exchange of LOINC codes for vendor IVD test results.

Product Type: Final Report
Year Released: August 2023
Project: Project Description
Agency: Food and Drug Administration (FDA)
Link: View Report

Assessing Outcomes Relevant for Patient-Centered Outcomes Research Among Adults Aged 18–64 with Disabilities and Federal Data Infrastructure Opportunities

This report and dataset inventory identifies individual-level measures for conducting patient-centered outcomes research (PCOR) relevant to adults with disabilities, aged 18–64 years. The work identifies six broad outcome domains relevant to PCOR for this population from prior research, including: (1) social and community engagement; (2) choice and control; (3) employment and self-sufficiency; (4) privacy, rights, and human security; (5) health-related social needs; and (6) health and wellbeing. Additionally, it identifies 32 sources of measures across the domains that include standardized tools/instruments, routinely fielded surveys, and administrative datasets.

Product Type: Final Report
Year Released: August 2023
Agency: The Office of the Assistant Secretary for Planning and Evaluation (ASPE)
Link: View Report

Strengthening the Data Infrastructure for Outcomes Research on Mortality Associated with Opioid Poisonings: Final Report

This is a final OS PCORTF report for a CDC project. The purpose of the project was to strengthen the mortality data produced by the National Center for Health Statistics’ (NCHS) National Vital Statistics System (NVSS) infrastructure for outcomes-based research on deaths associated with opioid poisoning.

Product Type: Final Report
Year Released: 2023
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Link: View Report

Bridging the Patient-Center Outcome Research Infrastructure and Technology

This final report summarizes the project to strengthen the Coordinated Registry Networks as a real-world data source for high quality, relevant, reliable, timely and actionable evidence to improve patient outcomes of medical devices, specifically for technologies affecting women’s health. Examples of accomplishments include advancing their ability to capture standardized data, including patient generated data, and linking their registry data to additional data sources.

Product Type: Final Report
Year Released: 2023
Project: Project Description
Agency: Food and Drug Administration (FDA)
Link: View Report

Final Report: Training Data for Machine Learning (ML) to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure (ONC)

This report describes the project led by the Office of the National Coordinator for Health Information Technology (ONC) wherein foundational work was conducted to support future applications of artificial intelligence (AI), specifically focused on machine learning (ML) to further health, health care, and patient-centered outcomes research (PCOR), and in turn enhance the adoption and implementation of a PCOR data infrastructure.

Product Type: Final Report
Year Released: 2023
Agency: Office of the National Coordinator for Health Information Technology
Link: View Report

Training Data for Machine Learning to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure — A Case Study in Tuberculosis Drug Resistance

This report describes the project led by the National Library of Medicine – National Institutes of Health that developed data infrastructure to advance the use of artificial intelligence (AI) for Patient-Centered Outcomes Research (PCOR) and clinical practice, using existing and to be acquired TB Portals data from the National Institute of Allergy and Infectious Diseases (NIAID).

Product Type: Final Report
Year Released: 2023
Agency: National Library of Medicine – National Institutes of Health
Link: View Report

Implementation of an Electronic Care Plan for People with Multiple Chronic Conditions (HP-19-012)

The purpose of this project was to develop and test a suite of electronic Care Plan (eCP) tools for adults with multiple chronic conditions (MCC), including an eCP implementation guide specifying data standards and value sets for key use case conditions and two open-source eCP apps (one for patients and one for clinicians). This joint initiative supported the work to develop and test these apps, which are intended to facilitate aggregation and sharing of critical patient-centered data across home-, community-, clinic-, and research-based settings by extracting data from point-of-care health systems and allowing transfer of those data across settings.

Product Type: Final Report
Year Released: November 2022
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Link: View Report

Validating and Expanding Claims-Based Algorithms of Frailty and Functional Disability for Value-Based Care and Payment (HP-19-009)

This project focused on validating an established claims-based frailty indexes (CFI) using linked claims-EHR databases of multiple large health systems. Additionally, the project assessed and compared the EHR and claims data of these data sources to ensure sufficient data quality for frailty analysis. Lastly, this project compared the EHR based frailty indexes (EFI) and CFI using EHR and claims data of each data source.

Product Type: Final Report
Year Released: September 2022
Project: Project Description
Agency: Agency for Healthcare Research and Quality (AHRQ)
Link: View Report

Surveillance Network: Maternal, Infant, and Child Health Outcomes Following Medication for Opioid Use Disorder during Pregnancy (MAT-LINK) – Phase I

This final report summarizes the Office of the Secretary Patient-Centered Outcomes Research (OS-PCORTF) project by CDC that established MAT-LINK, a network to examine practice patterns and outcomes associated with MOUD during pregnancy. This surveillance network created a data platform and standard data elements to collect linked maternal and child data among people taking MOUD during pregnancy at four clinical sites across the United States (Phase I): Boston Medical Center, Kaiser Foundation Research Institute Northwest in Oregon and Washington, The Ohio State University, and University of Utah. In 2020, CDC received additional funding from ASPE to expand MAT-LINK by including three more clinical sites (University of New Mexico, University of Rochester, and University of South Florida) and extending child follow-up through 6 years of age (Phase II). This final report shares information and deliverables related to Phase I of MAT-LINK.

Product Type: Final Report
Year Released: 2022
Project: Project Description
Agency: Centers for Disease Control and Prevention (CDC)
Link: View Report

Outcome Measures Harmonization Final Report (18-009)

This final report summarizes the OS PCORTF project by AHRQ that produced tools and resources to support future implementations of harmonized outcome measures for depression and other clinical areas. The data infrastructure tools include a prioritized research agenda and data use and governance toolkit.

Product Type: Final Report
Year Released: 2022
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: View Report

Identifying Co-Occurring Disorders among Opioid Users Final Report (19-005)

This final report summarizes the CDC project that developed a Co-occurring Disorders Algorithm to identify opioid-involved hospital visits with co-occurring substance use disorders (SUDs) and mental health issues (MHIs). With the collection of Electronic Health Record data, NCHS/CDC developed the Enhanced Opioid Identification Algorithm to identify opioid-involved hospital visits. To identify these hospital visits the algorithm analyzed medical codes (e.g., diagnoses, procedures) and used data science techniques such as regular expression operations and natural language processing (NLP) to determine the occurrence of an event by analyzing all available structured and unstructured data. Additionally, this project involved the fielding of a validation study that involved manual abstraction of medical records from a sample of 2016 NHCS inpatient and ED encounters to assess, evaluate, and verify the performance of the Enhanced Opioid Identification Algorithm and Co-occurring Disorder Algorithm.

Product Type: Final Report
Year Released: 2021
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Report

Enhancing Data Resources for Studying Patterns and Correlates of Mortality in Patient-Centered Outcomes Research: Pilot Linkage of National Death Index to Commercially and Publicly Insured Populations

This report summarizes standardized and reusable methods developed for attaining death and cause of death information from the Centers for Disease Control and Prevention's National Death Index (NDI) in multi-site studies. The developed linkage process avoids sharing identifiable patient information among study sites or with a central coordinating center. This approach promotes data sharing by protecting patient privacy, data security, as well as any other confidential information. This report provides a guide with step-by-step recommendations for multi-site studies that require linkage with NDI data, along with lessons learned.

Product Type: Final Report
Year Released: 2022
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Medicare Beneficiary Data Donation-National Institutes of Health (NIH) and Centers for Medicare & Medicaid Services (CMS) Inter-Agency Agreement-CMS Blue Button – Sync for Science (S4S)Final Project Summary

This final project report summarizes the work and resulting tools that CMS and NIH collaborated on to leverage the Sync for Science (S4S) and Blue Button API (BB API) programs to enable Medicare beneficiaries to donate their medical claims data for scientific research studies using S4S data donation workflow.

Product Type: Final Report
Year Released: 2022
Project: Project Description
Agency: National Institutes of Health (NIH) and Centers for Medicare & Medicaid Services (CMS)
Link: View Report

FY 19 CDC - Augmenting the National Hospital Care Survey (NHCS) Data through Linkages with Administrative Records

This final project report summarizes the work and resulting datasets that the Centers for Disease Control and Prevention conducted to link inpatient and Emergency Department claims and Electronic Health Record data from the National Center for Health Statistics (NCHS) National Hospital Care Survey (NHCS) to administrative data from the Centers for Medicare and Medicaid and housing data from Housing and Urban Development.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Report

Enhancing Data Resources for Studying Patterns and Correlates of Mortality in Patient-Centered Outcomes Research: Project 1 - Adding Cause-Specific Mortality to NCHS’s National Hospital Care Survey by Linking to the National Death Index

This final report summarizes the FY 17 OS-PCORTF project from the Centers of Disease Control and Prevention (CDC), that linked National Hospital Care Survey to the National Death Index to obtain cause-specific mortality. Cause-specific mortality is a key patient-centered outcome because it allows deaths unrelated to care to be excluded.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Report

Emergency Medicine Opioid Data Infrastructure: Key Venue to Address Opioid Morbidity and Mortality (Capturing Opioid Use Disorder Electronically and Patient-Reported Outcomes)

This report summarizes the FY 18 OS-PCORTF Project managed by the National Institutes of Health/National Institute of Drug Abuse to enhance capacity to use electronic health record (EHR) data and patient-reported outcomes measures (PROs) to conduct opioid-related research in emergency departments (EDs).

Product Type: Final Report
Year Released:
Project: Project Description
Agency: National Institutes of Health
Link: View Report

Common Data Model Harmonization Final Report

This project was a collaboration between FDA, several NIH Institutes (NCATS, NCI and NLM), and ONC. The goal of the project was to reuse data, methods, and other resources from existing research networks and to take advantage of available open, consensus-based standards, and to build reusable data mappings and transformation services. The project resulted in a Health Level Seven (HL7) Fast Healthcare Interoperability Resources (FHIR) CDMH Implementation Guide, a data governance framework, methods and standard process for ongoing curation, validated mappings between the Common data models, a portal and clinical query software, and public access to data specifications and visualizations of the mappings.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration | National Institutes of Health | Office of the National Coordinator for Health Information Technology
Link: View Report

Office of the National Coordinator’s Privacy and Security Framework Final Report

This project was a collaboration between ONC and CDC. The goal of this project was to develop resources to support the protection of privacy and security of electronic health data as it is used for PCOR. The resources resulting from this project consider the legal and regulatory requirements relative to patient consent, privacy, and autonomy in examining the factors of collection, access, use, and disclosure of electronic health data that were current at the time of the project. The project resulted in a framework and testing of technology that support the use of health data from a wide variety of sources for PCOR.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Report

Women’s Health Coordinated Registry Network Final Report

The project was a collaboration between FDA, NIH/NLM, and ONC. The project produced several publicly available products including the Stress Urinary Incontinence (SUI) Surgery Module aimed at collecting quality data on all types of SUI surgeries, WHT-CRN Common Core Dataset; and an HL7 WHT-CRN FHIR Implementation Guide, which is a “recipe book” that provides general guidelines for how the implementation of the FHIR standard can be applied to support the capture and exchange of data among the registries.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Developing a Strategically Coordinated Registry Network for Women’s Health Technologies: Office of the National Coordinator

This report summarizes the results of ONC’s work on an interagency project to develop and test a standards-based approach to establishing a new Coordinated Registry Network for women’s health technologies and to develop tools that facilitate data collection to populate registries. The ONC portion of the project resulted in the development and testing of a Health Level Seven International (HL7®) Fast Healthcare Interoperability Resource (FHIR) Implementation Guide that provides guidance regarding the capture and exchange of women’s health data by registries.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Report

Enhancing Data Resources for Studying Patterns and Correlates of Mortality in Patient-Centered Outcomes Research: Project 4 - NDI Workshop and Strategy Paper

This report summarizes the barriers to the national death index (NDI) from the Federal and State perspective, as well as the long-term strategy for NDI - on how access and use of NDI data may be improved for research. The strategy examined altering the economic model used to support NDI; de-identifying and minimizing the non-economic barriers to accessing and using NDI; re-using cause of death data (e.g., sharing the data with other research proposals; multiple use of approved data for other research studies); improving the efficiency of the administrative aspects of linkages; improving the timeliness and quality of the NDI data; and improving the timeliness of the NDI approval process.

Product Type: Other Report (strategy paper)
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Report

Data Quality Metrics System Final Report

This Final Report is for the Food and Drug Administration’s Data Quality Metrics Project. This project designed, tested, and released for open-source use a web-based data quality toolkit for exploring and describing the quality, completeness, and stability of data sources and visualization of data quality metrics from any data source.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Advancing the Collection and Use of Patient-Reported Outcomes through Health Information Technology: Final Report

This report describes the project led by the Office of the National Coordinator for Health Information Technology (ONC) and the Agency for Healthcare Research and Quality (AHRQ) focused on standardizing the collection, exchange, and integration of patient-reported outcome (PRO) data in electronic health record (EHR) systems and other health information technology (IT) solutions to support the electronic sharing of this information.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Report

Natural Language Processing Clinical Language Engineering Workbench (CLEW) Project - Final Report

This report summarized the goals, methodologies, accomplishments and deliverables of the project.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration | Centers for Disease Control and Prevention
Link: View Report

Natural Language Processing Clinical Language Engineering Workbench (CLEW) Project - Lessons Learned

This report compiles lessons that were realized and captured while developing a natural language process (NLP) workbench. The lessons have been separated into three categories that represent overall general observations; tools, systems development, and testing; and NLP and machine learning pipeline and model development.

Product Type: Other Report (lessons learned)
Year Released:
Project: Project Description
Agency: Food and Drug Administration | Centers for Disease Control and Prevention
Link: View Report

NLP CLEW Workbench Web Service Technical Report

Patient Matching, Aggregation, and Linking (PMAL) Project Final Report

This report explains the project, deliverables, and lessons learned in the areas of improving patient matching, improving data quality, expanding data sharing, and data standardization.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View Report

Improving the Timeliness and Quality of State Electronic Death Registration Systems

The CDC/National Center for Health Statistics (NCHS) worked with jurisdictions in 19 states to address three objectives. The project worked to strengthen both the states’ mortality data infrastructures and the NCHS infrastructure for more timely delivery of state records the National Death Index (ND) database; conducted intersystem exchanges between EHRs and electronic death registration system using national standards; and linked the National Hospital Care Survey inpatient and emergency department data with the NDI data to pilot test capturing within- and post-hospital mortality.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Centers for Disease Control and Prevention
Link: View Report

Conceptualizing a Data Infrastructure for the Capture and Use of Patient-Generated Health Data

ONC defines patient-generated health data (PGHD) as health-related data created and recorded by or from patients outside of the clinical setting to help address a health concern. The rise of innovative digital health technologies has increased the ease of capturing, using, and sharing PGHD. Although patients are creating an abundance of PGHD, several technical and cultural barriers have slowed the adoption of PGHD in care delivery and research. This report envisions a health IT ecosystem that optimizes PGHD use for care delivery and research settings and developed a Practical Guide that offers suggested practices and questions to consider for the implementation of the capture, use, and sharing of PGHD in clinical and research settings.

Product Type: White paper & infographic
Year Released:
Project: Project Description
Agency: Office of the National Coordinator for Health Information Technology
Link: View white paper and infographic

Creation of LOINC Equivalence Classes

LOINC provides standardized codes and names for a wide range of clinical observations and provides codes for the observations recorded in a spectrum of settings for diverse applications. This project’s purpose was to create a flexible, extensible, and computable mechanism for rolling up LOINC codes into clinically relevant equivalence groups that enable more efficient processing and aggregation of laboratory and other data from diverse health IT systems.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: National Institutes of Health
Link: View Report

Development of Harmonized Outcome Measures for Use in Patient Registries and Clinical Practice: Methods and Lessons Learned

Variation in types and definitions of outcome measures used in patient registries make it difficult to compare, link, and aggregate data across a range of registries even in the same clinical area. This project report describes the use of the Outcome Measures Framework to develop minimum sets of standardized outcome measures in five clinical areas (atrial fibrillation, asthma, depression, lung cancer, and lumbar spondylolisthesis) for use in patient registries and in clinical practice.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Agency for Healthcare Research and Quality
Link: View Report

Enhanced Data Resources for Studying Patterns and Correlates of Mortality in Patient-Centered Outcomes Research

This CMS project links CDC/NCHS National Death Index (NDI) data for known Medicare and Medicaid deaths with Medicare and Medicaid data in the CMS Chronic Conditions Warehouse (CCW). The CCW Medicare and Medicaid data includes claim and enrollment information. Linkage of NDI and CCW selected data were updated into the Master Beneficiary Summary file, the Medicaid Enrollee Supplemental file, and included in the CCW data dictionary.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Centers for Medicare & Medicaid Services
Link: View Report

Collection of Patient‐Provided Information through a Mobile Device Application for Use in Comparative Effectiveness and Drug Safety Research

This FDA project developed a mobile device application for use in clinical trials and other research. The pilot test was conducted with pregnant women although the app is applicable to a range of topics and research methodologies. The project is now known as “FDA MyStudies App”. For additional information, please refer to the Appendix. The output of the project is found on the FDA website.

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Cross-Network Directory Service Project

This project creates an open-source interoperable service that allows: 1) data partners to easily participate in multiple data research networks, 2) queries to seamlessly move across such networks, and 3) users to share analytic capabilities and knowledge across networks. This project pilot tested the Cross-Network Directory Service (CNDS) across two existing networks: FDA’s Sentinel and PCORI’s National Patient-Centered Clinical Research Network (PCORnet).

Product Type: Final Report
Year Released:
Project: Project Description
Agency: Food and Drug Administration
Link: View Report

Vignettes, Project Spotlights, and Portfolio Reports

Addressing the Opioid Overdose Crisis Through Better Data: Opioids Vignette

This updated 2022 vignette provides examples of how a range of Office of the Secretary Patient-Centered Outcomes Research Trust Fund (OS-PCORTF) cross-agency projects are working to address the opioid overdose crisis by 1) Improving Timeliness and Quality of Outcomes Data 2) Building Capacity for Collection of Patient-Reported Outcomes3) Building Linkages to Address Co-Morbidities

Product Type: Vignette
Link: View Product

2022 Enhancing the Data Infrastructure for Women’s Health Research to Improve Women’s and Maternal Health Outcomes

This 2022 vignette provides examples of how a range of OS-PCORTF cross-agency projects are working to improve maternal health by 1) Enhancing Women’s Health Data for Research 2) Adding Electronic Health Records to the Suite of Maternal Health Data for Research 3) Linking Maternal Survey Data with Other Health Data.

Product Type: Vignette
Link: View Product

Research Data Networks and Patient-Centered Outcomes Research Trends and Opportunities: Scan and Interviews with Key Informants

This report focuses on research networks that engage in or support research on patient-centered outcomes. The report was produced as as part of the strategic planning process for the Office of the Secretary Patient-Centered Outcomes Research Trust Fund portfolio.

Product Type: Portfolio Report
Link: View Product

Addressing the Opioid Crisis through Better Data and Data Infrastructure

This vignette provides examples of how a range of OS-PCORTF cross-agency projects are working to address the opioid crisis by 1) improving the quality and timeliness of outcomes data, 2) increasing collection of patient-reported information, and 3) building linkages to address co-morbid conditions that affect patient outcomes.

Product Type: Vignette
Link: View Product

Generating Real-World Evidence by Strengthening Real-World Data Sources

This vignette provides examples of how a range of OS-PCORTF cross-agency projects are working to strengthen the availability of Real World Evidence by standardizing Real World Data sources so they are fit for use and by building linkages across sources so data are easier to share and analyze.

Product Type: Vignette
Link: View Product

Building the Data Capacity for Patient-Centered Outcomes Research: 2019 Vignettes

This report presents brief vignettes that describe highlights of projects that are funded through the OS-PCOR trust fund. The report gives illustrative examples of the value of the work that has been done in partnership with HHS agencies to build data capacity for patient-centered outcomes research. The vignette document showcases accomplishments of the portfolio and explains the usefulness of the products that project teams are producing.

Product Type: Vignette
Link: View Product

Standardizing Narrative Text for Public Health Research

This spotlight highlights a CDC project - Development of a Natural Language Processing (NLP) Web Service for Public Health. This project developed an NLP Web Service or workbench, called the Clinical Language Engineering Workbench (CLEW). CLEW is a cloud-based web service that hosts NLP and machine learning tools that researchers can use to convert unstructured clinical data into standardized coded data. Once converted, data can be analyzed for public health and clinical research and surveillance.

Product Type: Project Spotlight
Link: View Product

Data Linkage Helps Researchers Find Patterns in Opioid Use and Treatment Response among Patient’s Hospital Encounters

This spotlight highlights the National Center for Health Statistics (NCHS) within the Centers for Disease Control and Prevention (CDC) three projects to address these data infrastructure needs. Since 2017, NCHS has integrated multiple data sources to build innovative data resources that will improve researchers’ ability to analyze data on hospital care, co-occurring mental health and substance use issues, post-acute care delivery, and deaths related to opioid-involved overdose. Through utilization of these integrated data resources, researchers can gain insight on patient characteristics, patterns of care, and other risk factors that affect health outcomes in cases of opioid misuse or abuse.

Product Type: Project Spotlight
Link: View Product

Social Determinants of Health Data Sharing at the Community Level

This report represents a landscape review of community-level efforts to address SDOH, followed by interviews with participants in three community-level initiatives that have built networks to coordinate clinical and social services. This report presents a cross-site analysis of the three initiatives, highlighting factors they identified as facilitating their efforts, the challenges they have faced thus far, their plans for continued expansion, and opportunities for federal and state entities, among other actors, to contribute to their efforts.

Product Type: Portfolio Report
Link: View Product

State Data for Conducting Patient-Centered Outcomes Research to Improve Maternal Health: Stakeholder Discussions Summary Report

This report presents a summary of discussions with stakeholders conducted to identify key components of successful state-based maternal health data linkage initiatives, to recognize the gaps in implementing such initiatives including data use for research and finally to understand the current status of existing linkages of state-level data with other data sources and with electronic health records.

Product Type: Portfolio Report
Link: View Product

Challenges and Improvements for PCOR Data Infrastructure: Results from a Stakeholder Prioritization Activity

In support of the development of the OS-PCORTF Strategic Planning, ASPE sought to gather perspectives on challenges and improvements for PCOR data infrastructure from a diverse group of stakeholders—with a wide range of occupational backgrounds including policy, health care delivery, research and informatics—through an online prioritization activity. Participants first generated challenges and improvements for the five functionalities. Participants then voted on challenges and improvements within each functionality, generating a ranked list of the participant-generated ideas.

Product Type: Portfolio Report
Link: View Product

Addressing the Opioid Epidemic with Better Data: An Overview of HHS Priorities and Projects to Expand Data Capacity for Patient-Centered Outcomes Research on Opioids

This report builds on a workshop sponsored by ASPE, titled Addressing the Opioid Epidemic: Harnessing the Power of Data for Patient-Centered Research in December 2018, which showcased projects working to build the data infrastructure for patient-centered outcomes research around opioids.

Product Type: Portfolio Report
Link: View Product

Incorporating Social Determinants of Health in Electronic Health Records: A Qualitative Study of Perspectives on Current Practices Among Top Vendors

To investigate the development of software products that allow health care providers to identify and address patients SDH in health care settings, this report conducted interviews with six electronic health records (EHRs) vendors with large market shares in both ambulatory and inpatient settings. This report conducted thematic analysis of the interviews to a) identify their motivations to develop such software products, b) describe their products and uses, and c) identify facilitators and challenges to collection and use of SDH data—through their products or otherwise—either at the point of care or in population health interventions.

Product Type: Portfolio Report
Link: View Product

Building Data Capacity for Patient-Centered Outcomes Research (PCOR) for COVID-19: Highlights of Seven OS-PCORTF Funded Multiagency Data Initiatives

This report describes seven new multiagency projects to strengthen the data infrastructure for conducting patient-centered outcomes research on COVID-19, during and after the pandemic. In general, these projects either expand the use of existing data or link datasets across Federal and State sources. Some projects advance modeling using artificial intelligence (AI) and machine learning (ML) to identify subpopulations at risk for poorer outcomes, sequelae, and the impacts of care settings and community characteristics. Other projects gather critical data on the effectiveness of repurposed treatments and vaccines for COVID-19.

Product Type: Report
Link: View Report

Enhancing the Data Infrastructure for Women's Health Research to Improve Women's and Maternal Health Outcomes

This Vignette highlights OS-PCORTF projects that are developing tools to collect, standardize, link, share, and analyze women’s and maternal health data.

Product Type: Vignette
Link: View Product

Supporting Value-Based Care Transformation through Interoperability and Care Coordination

This Vignette highlights OS-PCORTF projects that help support care coordination and quality by 1) aggregating data across sources to better reflect patient voices among vulnerable populations; 2) building greater interoperability across electronic health record (EHR) systems to improve coordination across the continuum of care, and 3) linking and standardizing metrics for the collection of social determinants of health data to improve care and reduce health disparities.

Product Type: Vignette
Link: View Product

Improving Patient-Centered Outcomes Research through Better Collection and Use of Participant-Provided Information

This Participant-Provided Information (PPI) Vignette highlights OS-PCORTF projects that are working to expand data capacity or data infrastructure for the collection and use of PPI.

Product Type: Vignette
Link: View Product

Annual Reports

Building the Data Capacity for Patient-Centered Outcomes Research: The 2022 Annual Report Report and Infographic

The OS-PCORTF FY2022 Annual Portfolio Report provides an overview of its 32 active projects as well as the major programmatic accomplishments and initiatives that support its new strategic plan goals.

Product Type: Annual Report
Link: Full Annual Report | Infographic

Building the Data Capacity for Patient-Centered Outcomes Research: The 2021 Annual Report Executive Summary and Full Report

The OS PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 34 projects that were active in calendar year 2021, as well as the major accomplishments.

Product Type: Annual Report
Link: Full Annual Report | Executive Summary

Building the Data Capacity for Patient-Centered Outcomes Research: The 2020 Annual Report

The OS PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 27 projects that were active in calendar year 2020, as well as the major accomplishments.

Product Type: Annual Report
Link: Full Annual Report | Executive Summary | Infographic

Building the Data Capacity for Patient-Centered Outcomes Research: The 2019 Annual Report

The OS-PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 27 projects that were active in calendar year 2019, as well as the major accomplishments.

Product Type: Annual Report
Link: Full Annual Report | Executive Summary | Infographic

Building the Data Capacity for Patient-Centered Outcomes Research: The 2018 Annual Report

The OS-PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 25 projects that were active in calendar 2018.

Product Type: Annual Report
Link: Full Annual Report

2017 Annual Report of HHS Projects to Build Data Capacity for Patient-Centered Outcomes Research

The OS-PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 21 projects that were active in calendar year 2017.

Product Type: Annual Report
Link: Full Annual Report

2016 Annual Report of HHS Projects to Build Data Capacity for Patient-Centered Outcomes Research

The OS-PCORTF Annual Report provides project descriptions for each of the OS-PCORTF portfolio’s 18 projects that were active in calendar year 2016.

Product Type: Annual Report
Link: Full Annual Report

HHS Projects to Build Data Capacity for Patient-Centered Outcomes Research: Completed Projects FY 2010 through FY 2015

The purpose of this document is to provide a summary of projects that were funded through the Office of the Secretary Patient-Centered Outcomes Research Trust Fund (OS-PCORTF) and completed between fiscal years (FY) 2010 and 2015.

Product Type: Annual Report
Link: Full Annual Report

Evaluation Reports

United States Government Accountability Office, Report to Congressional Committees, November 2020 Comparative Effectiveness Research

In this report, GAO reviewed the CER activities that PCORI and HHS have carried out to meet legislative requirements, described how PCORI and HHS allocated funding to CER activities, and described PCORI and HHS efforts to evaluate the effectiveness of their CER dissemination and implementation activities. The report can also be viewed by visiting: https://www.gao.gov/products/GAO-21-61.

Product Type: Evaluation Report
Link: View Report

United States Government Accountability Office, Report to Congressional Committees, March 2018 Comparative Effectiveness Research: Activities Funded by the Patient-Centered Outcomes Research Trust Fund

Product Type: Evaluation Report
Link: View Report

Understanding the Impacts of OS-PCORTF Projects on Data Capacity: An Interim Qualitative Assessment

This report presents findings from an interim qualitative assessment that examined the ways in which OS-PCORTF projects collectively advanced the ability of researchers to conduct patient-centered outcomes research (PCOR) by (1) improving the quality of data; (2) providing more relevant, comprehensive data; (3) enhancing analytical resources; and (4) reducing barriers to data access and use.

Product Type: Report
Link: View Report

Building Data Capacity for Patient-Centered Outcome Research: Portfolio Highlights (2016-2019): Impact, Opportunities and Case Studies

This report summarizes the impact of the OS-PCORTF portfolio in terms of products, tools and lessons learned for future work. The report is based on an assessment of portfolio awards funded from Fiscal Year (FY) 2016 through FY 2019.

Product Type: Evaluation Report
Link: Full Report | Executive Summary

Building Data Capacity for Patient-Centered Outcomes Research in HHS: A Formative Evaluation of 2012-2016 Projects

This report is a formative evaluation of the OS-PCORTF portfolio of projects from 2012 to 2016. It summarizes achievements as well as considerations for future work to build data capacity for clinical comparative effectiveness research and patient-centered outcome research.

Product Type: Evaluation Report
Link: View Report

OS-PCORTF Product Library

Datasets and Databases

Child and Caregiver Outcomes Using Linked Data (CCOULD) Dataset and User Guide

Social Determinants of Health Database

Training Data for the Tuberculosis Drug Resistance Use Case

Training Datasets and Validated Machine Learning Algorithms from the United States Renal Data System

The 2016 National Hospital Care Survey (NHCS)/National Death Index (NDI)/Drug-Involved Mortality (DIM) Enhanced Dataset

Linked Dataset: 2016 National Hospital Care Survey (NHCS) to 2015/2017 U.S. Department of Housing and Urban Development (HUD) Data

Linked NHCS and CMS Medicare MBSF Claims/Encounters and Assessment Data

NHCS and NDI linked with the National Vital Statistics System mortality files on drug overdose deaths (NVSS-M-DO) file

AHRQ Social Determinants of Health Database (Beta Version)

Linked National Hospital Care Survey (NHCS) and National Death Index (NDI) Mortality Data

Linked Dataset

Linked NHCS and CMS Medicare Master Beneficiary Summary File (MBSF) Data

Data Elements & Information Models

Multiple Chronic Care Conditions Value Sets

Training Data for Machine Learning to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure Data Dictionary

FHIR® Library for Depression Outcome Measures

Libraries of Clinical Definitions for Outcome Measures

GitHub Annotations for 1,000 Vaccine Adverse Event Reporting System (VAERS) Reports

NIH Common Data Elements Repository

HIT Standards

Making Electronic Data More Available for Research and Public Health (MedMorph) Reference Architecture HL7® FHIR Implementation Guide

Making Electronic Data More Available for Research and Public Health (MedMorph) Healthcare Surveys Content HL7® FHIR Implementation Guide

The Multiple Chronic Conditions (MCC) eCare Plan HL7® FHIR® Implementation Guide (Continuous Build Version)

Making Electronic Data More Available for Research and Public Health (MedMorph) Central Cancer Registry HL7® FHIR Implementation Guide

Making Electronic Data More Available for Research and Public Health (MedMorph) Research Data Exchange HL7® FHIR Implementation Guide

Logical Observation Identifiers Names and Codes (LOINC) Equivalence Class Artifact Releases

HL7 Version 2.6 Implementation Guide: Vital Records Death Reporting, Release 1 STU 2 - US Realm

Common Data Models Harmonization FHIR Implementation Guide (Release 0.1.0)

Women’s Health Technology CRN FHIR Implementation Guide

Patient Reported Outcomes FHIR Implementation Guide

The HAPI Open-Source FHIR® library

Tools and Guides

Training Data for Machine Learning to Enhance Patient-Centered Outcomes Research (PCOR) Data Infrastructure — A Case Study in Tuberculosis Drug Resistance

Toolkit: Data Sharing for Child Welfare Agencies and Medicaid

Coordinated Registry Network (CRN) Maturity Framework

LOINC Mapping Guide – Chemistry

LOINC Mapping Guide – Drug and Toxicology

LOINC Mapping Guide – Hematology and Serology

LOINC Mapping Guide – Molecular Pathology

The Linkage of the 2014 and 2016 National Hospital Care Survey to U.S. Department of Housing and Urban Development Administrative Data: Matching Methodology and Analytic Considerations

Outcome Measure Harmonization and Data Infrastructure for Patient-Centered Outcomes Research in Depression: Data Use and Governance Toolkit

Training Data for Machine Learning to Enhance Patient Centered Outcomes Research (PCOR) Data Infrastructure Implementation Guide for Chronic Kidney Disease Use Case

Natural Language Processing Clinical Language Engineering Workbench (CLEW) User Guidance Document

Data Quality Metrics (DQM) Tool

Guide for Using LOINC Microbiology Terms

Conceptualizing a Data Infrastructure for the Capture, Use, and Sharing of Patient-Generated Health Data in Care Delivery and Research through 2024 Practical Guide

Cross-Network Directory Service (CNDS) Project Design and Technical Documentation

Electronic Death Reporting System (EDRS) Online Reference Manual

Utilizing Data from Various Partners in a Distributed Manner

Source Data Capture From EHRS: Using Standardized Clinical Research Data

NLP CLEW Workbench Web Service Technical Report

Software and Analytic Services

Published Opioid Natural Language Processing (NLP) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

Published Medical Code-based (translation from SAS) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

Frailty Algorithms in SAS and R

Published Substance Abuse Disorder (SUD) and Mental Health Issues (MHI) Natural Language Processing (NLP) algorithms for the 2018-2019 National Hospital Care Survey Data Linkage projects

Training Dataset Code for Chronic Kidney Disease Use Case

National Library of Medicine Training Data GitHub Repository

Major Depression Outcomes Application

Synthea™ Disease-specific Modules: Cerebral Palsy

Synthea™ Disease-specific Modules: Prescribing Opioids for Chronic Pain and Treatment of Opioid Use Disorder

Synthea™ Disease-specific Modules: Sepsis

Synthea™ Disease-specific Modules: Spina Bifida

Blue Button 2.0 Application Programming Interface (API) Developer Sandbox

CMS Blue Button Webpage and API Developer Environment

Patient Matching, Aggregation, and Linking (PMAL) Provider Data Validation Tool

FDA MyStudies App

Clinical Language Engineering Workbench (CLEW) Platform

Distributed Regression Analysis (DRA) source code and documentation for the algorithms, and test data and samples reports for each regression model type

National Plan & Provider Enumeration System (NPPES) Open Application Programming Interface (API)

​​​​Identity Matching Adjudicator Collector (IMAC) Tool

Data Governance Products

Legal and Ethical Framework to Use Centers for Disease Control and Prevention Data for Patient-Centered Outcomes Research

Legal and Ethical Architecture for Patient-Centered Outcomes Research (PCOR) Data (“Architecture”)

Pilot of a Data Quality Framework to Support Patient Matching

Publications

Medical Care Special Issue: Building Data Capacity to Study Economic Outcomes for Patient-Centered Outcomes Research

PLOS Digital Health Publication: Synthetic Data in Health Care: Narrative Review

Identity Matching Adjudicator Collector (IMAC) Tool