Across the Health Care System

The goal of the CEPI Evidence Discovery and Retrieval (CEDAR) project is to make patient-centered outcomes research findings within AHRQ repositories more FAIR— findable, accessible, interoperable, and reusable—through technologies used by clinicians, researchers, implementers, patients, and others.

This research developed DDInteract, a patient-facing shared decision making (SDM) tool that uses interactive decision dashboards to graphically communicate risks and decision options, supporting SDM for patients and providers regarding drug-drug interactions.

This research developed, refined, and assessed the validity of methods for handling missing data in distributed data networks, without sharing individual-level data, to improve data quality and research validity.

This research developed algorithms for eight key drug-drug interactions (DDI) to inform the building of contextualized DDI alerts; developed and tested three DDI-clinical decision support (CDS) apps; and disseminated the information and algorithms via the DDI-CDS.org website, webinars, and publications.

This research implemented and evaluated strategies to improve patient matching of health data from disparate sources improving accuracy of matching.

This study showed the feasibility and value of creating a methodology and process for a health information technology black box to inform electronic health record design and usability.

The Electronic Data Methods Forum is charged with advancing the national dialogue on the infrastructure and methods of health research and quality improvement using electronic clinical data, with the goal of improving patient care and outcomes.

The Electronic Data Methods (EDM) Forum facilitated learning and collaboration among researchers and other key stakeholders who are generating the data, methods, and knowledge needed to build learning health systems that will improve patient care and outcomes.

This research studied errors in medical documents created with speech recognition software and developed natural language processing methods to detect such errors.