JMIR Publications

ABSTRACT

Suicide attempts are one of the most challenging psychiatric outcomes and have great importance in clinical practice. However, they remain difficult to detect in a standardised way to assist prevention because assessment is mostly qualitative and often subjective. As digital documentation is increasingly used in the medical field, Electronic Health Records (EHRs) have become a source of information that can be used for prevention purposes, containing codified data, structured data, and unstructured free text. This study aims to provide a quantitative approach to detection of suicide risk using EHRs, employing natural language processing techniques in combination with deep learning artificial intelligence methods to create an algorithm intended for use with clinical documentation in German. Using psychiatric medical files from inpatient psychiatric hospitalisations between 2013 and 2021, free text reports were transformed into structured embeddings using a German-trained adaptation of Word2Vec, followed by a Long-Short Term Memory (LSTM) – Convolutional Neural Network (CNN), BERT models (gbert-large and bert-base-german-cased), and GPT-2 approaches on sentences of interest to label suicide related content. The present study resulted in an average overall accuracy of >70% for all models, sensitivity, and F1 scores for the positive related sentences >60%. This study offers promising ways for automated early prediction of suicide attempts and therefore holds opportunities for mental health care.