Clinical Decision Support for Suicide Risk Assessment: Exploring the Opportunity of Predictive Analytics and the Need to Build Different Approaches

Suicide is a large public health concern accounting for 4000 deaths per year in Canada. Previous research has focused on identifying patient risk factors and developing risk assessment tools to better recognize high risk patients, but there has been limited supporting evidence for the use of these tools. Through five interrelated studies, this dissertation is focused on how electronic health records (EHRs) and Computerized Decision Support Systems can aid healthcare professionals in suicide risk assessment (SRA). First, the feasibility of incorporating EHR-based algorithms for SRA is explored. A systematic mapping review on EHR data used in suicide prediction found promising predictive performance of such algorithms, however a majority remained in the realm of research and were not validated or implemented within clinical care. Next, a retrospective validation of such a predictive algorithm (developed externally) was performed within a mental health hospital. Low sensitivity ceased implementation and clinical adoption, with data availability and quality acting as the main barriers. Following that, other targets of clinical decision-support were explored, focusing on understanding healthcare professional-level behaviour instead of relying on patient-specific algorithms. Personal and contextual factors that affect a healthcare professional’s ability to assess suicide risk were catalogued, finding a range of system-level (e.g. an ill-equipped system), organizational-level (e.g. documentation requirements, team dynamics) and individual-level (e.g. ability to connect with a patient, cultural issues) factors through means of a scoping review. Then, through a concurrent mixed methods study (79 healthcare professionals surveyed and 21 interviewed), the decision-making processes, current barriers and facilitators were explored. It was identified that a health professional’s clinical designation and mental health experience were significantly associated with their decision and confidence in SRA. Most SRAs were conducted conversationally, without the use of a structured tool. Barriers within this process included gathering appropriate collateral or past history of a patient and effectively detecting changes from baseline for patients who are chronically suicidal, among many other barriers identified. Based on this needs assessment, customized clinical decision support systems are recommended– one that moves beyond patient algorithms. This work also has implications for SRA training and education.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.