ScAN: Suicide Attempt and Ideation Events Dataset

TL;DR

This paper introduces the ScAN dataset with annotated suicidal behavior events from EHR notes and presents ScANER, a model that effectively detects and classifies suicidal behaviors to aid in prevention efforts.

Contribution

The paper creates a large, annotated dataset for suicidal behaviors and develops a multi-task RoBERTa-based model for evidence retrieval and classification, advancing automated suicide risk detection.

Findings

ScAN dataset contains over 12,000 EHR notes with 19,000+ annotated events.

ScANER achieved 0.83 macro F1-score in evidence retrieval.

ScANER classified SA and SI with F1-scores of 0.78 and 0.60, respectively.

Abstract

Suicide is an important public health concern and one of the leading causes of death worldwide. Suicidal behaviors, including suicide attempts (SA) and suicide ideations (SI), are leading risk factors for death by suicide. Information related to patients' previous and current SA and SI are frequently documented in the electronic health record (EHR) notes. Accurate detection of such documentation may help improve surveillance and predictions of patients' suicidal behaviors and alert medical professionals for suicide prevention efforts. In this study, we first built Suicide Attempt and Ideation Events (ScAN) dataset, a subset of the publicly available MIMIC III dataset spanning over 12k+ EHR notes with 19k+ annotated SA and SI events information. The annotations also contain attributes such as method of suicide attempt. We also provide a strong baseline model ScANER (Suicide Attempt and Ideation Events Retriever), a multi-task RoBERTa-based model with a retrieval module to extract all the relevant suicidal behavioral evidences from EHR notes of an hospital-stay and, and a prediction module to identify the type of suicidal behavior (SA and SI) concluded during the patient's stay at the hospital. ScANER achieved a macro-weighted F1-score of 0.83 for identifying suicidal behavioral evidences and a macro F1-score of 0.78 and 0.60 for classification of SA and SI for the patient's hospital-stay, respectively. ScAN and ScANER are publicly available.