HHS · no agency ID · record R0685

Detecting, evaluating, and redacting PII in NAMCS HC Component

Department of Health and Human Services · HHS/CDC

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Health and Medical
Operational functions: FOIA and records management Derived by keyword rules; see methodology

Problem the AI is intended to solve

How effective are open-source PII detection models in identifying and redacting PII? The National Center for Health Statistics’ (NCHS) Division of Health Care Statistics has collected millions of health records with laboratory results from encounters at health centers via the National Ambulatory Medical Care Survey (NAMCS), Health Center (HC) Component. Due to inadvertent errors during data entry and processing, some records contain identifiers (e.g. names, locations, etc.) in non-PII fields. Due to the PII, certain fields cannot be made available for restricted or public use, but reviewing millions of records for PII is not practical.

Expected benefits

If the process is feasible, it will significantly increase the healthcare lab data available to researchers for analysis. Additionally, the process could be applied to additional tables and years of data, increasing overall data availability.

System outputs

A semi-automated process to conduct a quality control review of health data records, including potential PII records flagged for manual review.

Technology

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

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
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: Not reported
Privacy Impact Assessment: Not reported
Authorization to Operate: Not reported
Demographic features: Not reported
Training and evaluation data: Not reported
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