In ever more pressured health-care systems, technological solutions offering scalability of care and better resource targeting are appealing. Research on machine learning as a technique for identifying individuals at risk of suicidal ideation, suicide attempts, and death has grown rapidly. This research often places great emphasis on the promise of machine learning for preventing suicide, but overlooks the practical, clinical implementation issues that might preclude delivering on such a promise. In this Review, we synthesise the broad empirical and review literature on electronic health record-based machine learning in suicide research, and focus on matters of crucial importance for implementation of machine learning in clinical practice. The challenge of preventing statistically rare outcomes is well known; progress requires tackling data quality, transparency, and ethical issues. In the future, machine learning models might be explored as methods to enable targeting of interventions to specific individuals depending upon their level of need—ie, for precision medicine. Primarily, however, the promise of machine learning for suicide prevention is limited by the scarcity of high-quality scalable interventions available to individuals identified by machine learning as being at risk of suicide.
Bibliographical noteFunding Information:
OJK reports grants from UCB Community Health Fund, outside the submitted work. NK reports grants and personal fees from the UK Department of Health and Social Care, the UK National Institute of Health Research, the UK National Institute of Health and Care Excellence (NICE), and Healthcare Quality and Improvement Partnership, outside the submitted work; and has worked with the National Health Service England on national quality improvement initiatives for suicide and self-harm. NK sits on the Department of Health and Social Care's (England) National Suicide Prevention Strategy Advisory Group. NK has chaired and been the Topic Advisor for NICE guideline committees for self-harm and depression.
© 2022 Elsevier Ltd