Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models

TL;DR

This study evaluates BERT-based models for identifying suicidal behaviors from clinical notes, demonstrating that optimized pretraining and multi-label strategies significantly improve detection accuracy in psychiatric settings.

Contribution

It introduces an effective multi-label classification approach using pre-trained language models tailored for suicide phenotyping from clinical narratives.

Findings

RoBERTa achieved 86% accuracy and 78% F1 score with single-label classification.

Multi-label fine-tuning of RoBERTa further improved accuracy to 88% and F1 to 81%.

Pretraining with domain-specific data enhances model performance for suicide detection.

Abstract

Accurate identification and categorization of suicidal events can yield better suicide precautions, reducing operational burden, and improving care quality in high-acuity psychiatric settings. Pre-trained language models offer promise for identifying suicidality from unstructured clinical narratives. We evaluated the performance of four BERT-based models using two fine-tuning strategies (multiple single-label and single multi-label) for detecting coexisting suicidal events from 500 annotated psychiatric evaluation notes. The notes were labeled for suicidal ideation (SI), suicide attempts (SA), exposure to suicide (ES), and non-suicidal self-injury (NSSI). RoBERTa outperformed other models using multiple single-label classification strategy (acc=0.86, F1=0.78). MentalBERT (acc=0.83, F1=0.74) also exceeded BioClinicalBERT (acc=0.82, F1=0.72) which outperformed BERT (acc=0.80, F1=0.70). RoBERTa fine-tuned with single multi-label classification further improved the model performance (acc=0.88, F1=0.81). The findings highlight that the model optimization, pretraining with domain-relevant data, and the single multi-label classification strategy enhance the model performance of suicide phenotyping. Keywords: EHR-based Phenotyping; Natural Language Processing; Secondary Use of EHR Data; Suicide Classification; BERT-based Model; Psychiatry; Mental Health