Machine learning in suicide science: Applications and ethics

Abstract

For decades, our ability to predict suicide has remained at near‐chance levels. Machine learning has recently emerged as a promising tool for advancing suicide science, particularly in the domain of suicide prediction. The present review provides an introduction to machine learning and its potential application to open questions in suicide research. Although only a few studies have implemented machine learning for suicide prediction, results to date indicate considerable improvement in accuracy and positive predictive value. Potential barriers to algorithm integration into clinical practice are discussed, as well as attendant ethical issues. Overall, machine learning approaches hold promise for accurate, scalable, and effective suicide risk detection; however, many critical questions and issues remain unexplored.

An investigation of clinical decisionmaking: identifying important factors in treatment planning for suicidal patients in the emergency department

“…42,53 Future work in the ED setting should focus on incorporating valid and reliable predictive algorithms as an aid to existing clinical decisionmaking practices, while also aligning suicide risk decisions with appropriate and evidence-based clinical interventions to reduce patient suicide risk. [25][26][27]52,54 Overall, results from this study provide important implications for improving ED care and treatment planning for patients reporting active suicidal ideation.…”

Ethical dilemmas posed by mobile health and machine learning in psychiatry research

“…43 Consider a machine learning model trained using the electronic health records of medical visits; 44 this model might not be able to accurately predict psychiatric conditions in immigrant populations that avoid interacting with the health-care system. 45 Additionally, clinician bias in the International Classification of Disease's codes or clinical notes can introduce variations in the inputs to a machine learning model that, in turn, bias the model's predictions for minority groups. 46 Further, with less interpretable models, it can be more challenging to detect, track and rectify these different sources of bias.…”

Reaching Those at Highest Risk for Suicide: Development of a Model Using Machine Learning Methods for use With Native American Communities

“…However, there are challenges with risk identification. Most risk identification strategies are assessment‐based—often requiring intensive training, expertise, and/or time (Linthicum, Schafer & Ribeiro, ). Moreover, these assessments are based on rather simple combinations of risk factors known from suicide research (Linthicum, Schafer & Ribeiro, ).…”

“…Most risk identification strategies are assessment‐based—often requiring intensive training, expertise, and/or time (Linthicum, Schafer & Ribeiro, ). Moreover, these assessments are based on rather simple combinations of risk factors known from suicide research (Linthicum, Schafer & Ribeiro, ). A recent meta‐analysis has shown that despite over 50 years of suicide research, we have seen little improvement in our predictive accuracy for suicide‐related behaviors (Franklin et al, ).…”

“…Machine learning approaches examine the probabilistic relationships between a large set of dependent variables and then test the reliability of the results through cross‐validation procedures. Given the complexity of suicide risk and machine learning’s ability to model this complexity, ML methods seem to have potential to improve accuracy and scale (Linthicum, Schafer & Ribeiro, ). One recent study suggests that ML methods may be better at identifying suicide risk than clinician evaluation (Tran et al, ).…”