Analysis of Risk Factor Domains in Psychosis Patient Health Records

TL;DR

This paper develops a topic extraction pipeline from psychiatric EHRs to improve readmission risk prediction, addressing the challenge of diverse clinical narratives and vocabulary.

Contribution

It introduces a novel document vector similarity-based topic extraction method tailored for psychiatric EHRs, supporting future readmission risk modeling.

Findings

Initial results demonstrate effective topic extraction from psychiatric notes

Identified additional features for improving readmission prediction

Established a data pipeline for future model development

Abstract

Readmission after discharge from a hospital is disruptive and costly, regardless of the reason. However, it can be particularly problematic for psychiatric patients, so predicting which patients may be readmitted is critically important but also very difficult. Clinical narratives in psychiatric electronic health records (EHRs) span a wide range of topics and vocabulary; therefore, a psychiatric readmission prediction model must begin with a robust and interpretable topic extraction component. We created a data pipeline for using document vector similarity metrics to perform topic extraction on psychiatric EHR data in service of our long-term goal of creating a readmission risk classifier. We show initial results for our topic extraction model and identify additional features we will be incorporating in the future.