Extracting Housing and Food Insecurity Information From Clinical Notes Using cTAKES

Abstract

Objective

To assess the utility and challenges of using natural language processing (NLP) in electronic health records (EHRs) to ascertain health-related social needs (HRSNs) among older adults.

Study Setting and Design

We extracted HRSN information using the NLP system Clinical Text Analysis and Knowledge Extraction System (cTAKES), combined with Concept Unique Identifiers and Systematized Nomenclature for Medicine codes. We validated cTAKES performance, via manual chart review, on two HRSNs: food insecurity, which was included in the healthcare system's HRSN screening tool, and housing insecurity, which was not.

Data Sources and Analytic Sample

De-identified EHRs in a large California healthcare system (January 2013 through October 2022) from 119,127 patients aged 55+ in primary and emergency care settings (n = 1,385,259 clinical notes).

Principal Findings

Although cTAKES had a moderate positive predictive value (77.5%) for housing insecurity, housing challenges among older adults frequently did not align with the concepts the algorithm recognized. cTAKES performed poorly for food insecurity (positive predictive value: 18.5%) because this NLP system incorrectly flagged structured fields from the screening tool.

Conclusion

Unstandardized terminology and poor integration of HRSN screeners in EHR remain important barriers to identifying older adults' food and housing insecurity using cTAKES.