Evaluating a Human Detection Model in a Behaviour Analysis Pipeline for Suicide Prevention.

Suicides in public places, such as railways, can have a significant impact on bystanders, railway staff, first responders and the surrounding communities. Behaviours prior to a suicide attempt have been identified, that could potentially be detected automatically. As a first step, the algorithm is required to accurately identify individuals exhibiting these behaviours in different settings. Our study analyses a human detection model focussing on pedestrian detection at railway stations as one component of a broader project to detect pre-suicidal behaviours. Closed-circuit television footage from two stations collected for the same 24-hour period were manually analysed to obtain parameters (true positives, false positives, and false negatives) which were then used to compute performance measures (sensitivity, precision, and F1 score). The model performed differently in both stations with a sensitivity of 0.73 and F1 score of 0.84 in Station A and a sensitivity of 0.48 and F1 score of 0.65 in Station B. Root causes of false negatives identified include differing body postures and occlusion. Although the model was adequate, its performance is dependent on the view captured by the cameras in stations. Collectively, these findings can be used to improve the model's performance.Clinical Relevance-Detecting behaviours prior to a suicide attempt offers a critical period for intervention by bystanders or first responders, potentially interrupting the attempt. This offers the potential to directly reduce suicide attempts, as well as reduce third-party exposure to these traumatic events.

The Role of Bystanders in the Prevention of Railway Suicides in New South Wales, Australia.

Background: Bystanders can play a key role in preventing railway suicides by taking direct action or by raising an alarm. Aims: The study investigated in this context: (1) the prevalence of preventative actions by bystanders; (2) the relationship, if any, between first-hand preventions by bystanders and the degree of ambiguity around the imminence of danger; and (3) the nature of first-hand preventions by bystanders. Method: Data were obtained from a security reporting database at Sydney Trains for 2011-2019 for accident and suicide-related incidents (N = 1,278). Results: In 635 cases of suicide prevention, bystanders were identified as first responders in 11% of cases and as raising the alarm in 11% of cases. Bystanders as first responders intervened proportionally more where the ambiguity of danger is low (jumping) compared with high (sitting, standing, wandering). Of the 69 cases of bystander preventions, 77% involved physical interaction (e.g., holding back) and 49% involved more than one bystander. Limitations: The data source could be biased because of incompleteness or nonstandard reporting. Conclusion: Rail policy-makers should consider education and support for bystanders and staff: for example, by making known the prevalence of helping, the importance of intervening, and what types of intervention are most helpful.

Patterns of pre-crash behaviour in railway suicides and the effect of corridor fencing: a natural experiment in New South Wales.

Suicides on railway systems remain a significant concern world-wide. Understanding patterns of pre-crash behaviour, whether jumping, lying or wandering on tracks, is important for the design of preventative measures, yet prior studies have reported divergent patterns of behaviour. This study tested the hypothesis that higher standards of corridor fencing reduce the proportion of train suicides in the non-jumping category. Data was analyzed as a natural experiment for 171 cases of apparent railway suicides in New South Wales (NSW) for the period 2011-2018. Results were congruent with the hypothesis. A higher level of corridor fencing in metropolitan Sydney was associated with a lower proportion in the non-jumping category (33%) compared with regional areas (74%). The article contributes by showing that: (i) fencing appears to lead to a reduction in some types of rail suicides and thus; (ii) contributes to a lower overall rate of suicide by train; and (iii) even with fencing, the non-jumping incidents warrant attention for appropriate countermeasures.