Assessing the Efficacy of Clinical Sentiment Analysis and Topic Extraction in Psychiatric Readmission Risk Prediction

TL;DR

This paper evaluates the use of clinical sentiment analysis and topic extraction from EHRs to improve prediction of 30-day psychiatric readmission risk, aiming to enhance clinical decision-making.

Contribution

It introduces NLP-based features like sentiment and topic analysis into readmission prediction models, which were previously dominated by structured data.

Findings

NLP features improve prediction accuracy.

Sentiment analysis correlates with readmission likelihood.

Topic extraction provides clinically relevant insights.

Abstract

Predicting which patients are more likely to be readmitted to a hospital within 30 days after discharge is a valuable piece of information in clinical decision-making. Building a successful readmission risk classifier based on the content of Electronic Health Records (EHRs) has proved, however, to be a challenging task. Previously explored features include mainly structured information, such as sociodemographic data, comorbidity codes and physiological variables. In this paper we assess incorporating additional clinically interpretable NLP-based features such as topic extraction and clinical sentiment analysis to predict early readmission risk in psychiatry patients.