Engineering System Safety: Liability Informed Healthcare System Safety Design

Preventable patient safety incidents remain a leading cause of harm globally and in Canada, yet systemic factors influencing these events remain poorly understood. In Canada, fragmented incident data and the absence of standardized mechanisms for aggregated learning limit system-wide safety improvement and prediction of future harm. Medico-legal claims data offers a potentially rich but underused source of insight into systemic contributors to preventable patient harm. This work explores the application of active machine learning to Canadian medico-legal claims data to identify systemic risk factors and inform risk prediction. More specifically, this research highlights how medico-legal data and predictive analytics can support human factors practitioners, healthcare leaders, and researchers in advancing safer system design in healthcare.