Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study.

OBJECTIVE: Prior research suggests there are observable behaviours preceding suicide attempts in public places. However, there are currently no ways to continually monitor such sites, limiting the potential to intervene. In this mixed-methods study, we examined the acceptability and feasibility of using an automated computer system to identify crisis behaviours. METHODS: First, we conducted a large-scale acceptability survey to assess public perceptions on research using closed-circuit television and artificial intelligence for suicide prevention. Second, we identified crisis behaviours at a frequently used cliff location by manual structured analysis of closed-circuit television footage. Third, we configured a computer vision algorithm to identify crisis behaviours and evaluated its sensitivity and specificity using test footage. RESULTS: Overall, attitudes were positive towards research using closed-circuit television and artificial intelligence for suicide prevention, including among those with lived experience. The second study revealed that there are identifiable behaviours, including repetitive pacing and an extended stay. Finally, the automated behaviour recognition algorithm was able to correctly identify 80% of acted crisis clips and correctly reject 90% of acted non-crisis clips. CONCLUSION: The results suggest that using computer vision to detect behaviours preceding suicide is feasible and well accepted by the community and may be a feasible method of initiating human contact during a crisis.

Case reports of new-onset eating disorders in older adult cancer survivors.

BACKGROUND: It is unusual for a de novo eating disorder to emerge in late adulthood. Across a number of years, a number of patients were identified who experienced severe and unexpected weight loss post curative management of an upper abdominal cancer (i.e., cancer survivors). Each of the patients was readmitted to the tertiary surgical hospital due to complications of severe malnutrition. Each presentation was initially considered to have a major physical health problem (such as cancer recurrence). Each required extensive investigations and multidisciplinary team involvement and were later conceptualised as a new-onset (in later adulthood) eating disorder that emerged post curative cancer treatment. The team wished to better understand this group and/or characterise and/or inform the scientific community of this phenomena if not already well described. LITERATURE REVIEW: The review identified that the re-emergence of pre-existing eating disorders at the time of cancer treatment was described; however, there was no identification of similar new-onset in later adulthood cases of eating disorders in cancer survivors in the medical literature. REVIEW OF THE CASES: Once ethics and consent was obtained, then the clinical course of four complex individuals were reviewed, including the use of a multidisciplinary Delphi review process, to understand commonalities and then plot a common care pathway with potential intervention points. CASE PRESENTATIONS: Common factors identified among the four patients included the lack of a physical health (organic) cause to the weight loss and ongoing weight loss despite intense multidisciplinary care. All had abnormal attitudes and behaviours relating to food, nutritional rehabilitation and/or recovery. None returned to a healthy weight and/or healthy eating despite extensive team input. The presentations were ultimately conceptualised as having severe disordered eating behaviours and in at least three cases met criteria for a formal eating disorder. The cohort had similar psychosocial characteristics including low socioeconomic status and complex family dynamics. None had prior formal psychiatric care. The outcomes were poor; one patient died, another required admission to a specialist eating disorder admission with a subsequent relapsing remitting course, and the remaining two had complicated chronic courses. CONCLUSION: Similar cases may be underreported. If identified earlier, there may be a role for intervention to prevent high morbidity and mortality and to support clinical teams managing similar complex patients.