HHS · no agency ID · record R0847

FE5: Incorporate a range of frequently used engineering features from EHRs into the Sentinel common data model in the Sentinel EHR and claims linked Data Partner network

Department of Health and Human Services · HHS/FDA/CDER

Overview

Development stage: DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2023-09 (month precision)Source: Sep-23
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Health and Medical
Operational functions: Clinical and medical Derived by keyword rules; see methodology

Problem the AI is intended to solve

This AI project is designed to solve the problem of extracting valuable clinical information trapped in unstructured free-text fields within electronic health records. It aims to create a systematic feature engineering approach that can convert narrative clinical notes and text data into structured, analyzable formats for pharmacoepidemiologic research and drug safety surveillance.

Expected benefits

Supports the use of Natural Language Processing (NLP) to extract information on five specific medical concepts from Electronic Health Record (EHR) data and make available in the Sentinel Common Data Model for future drug safety studies, enhancing FDA's surveillance capabilities.

System outputs

NLP for EHR unstructured data extraction

Technology

AI classification: Natural language processingSource: Natural Language Processing: AI that processes, interprets, and shares information in human language.
System name(s): Sentinel
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): Contractor teams
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: Yes
Demographic features: k) None of the above
Training and evaluation data: Free-text data from the commercial and development network EHR-claims
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported