Assessing the Efficacy of Clinical Sentiment Analysis and Topic Extraction in Psychiatric Readmission Risk Prediction
This work addresses the problem of high readmission rates in psychiatry for clinicians, but it appears incremental as it builds on existing methods by adding new features.
The paper tackled the challenge of predicting 30-day hospital readmission risk for psychiatry patients by incorporating NLP-based features like topic extraction and clinical sentiment analysis from Electronic Health Records, aiming to improve classifier performance beyond traditional structured data.
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.