Suicide is a public health crisis and ranks among the leading causes of death in the U.S. for most age groups. Emerging digital behavioral health (dBH) technologies show potential to detect, stratify, and intervene — regardless of when or where SI occurs. This session presents two studies assessing a dBH platform's effectiveness in detecting hidden suicide risks in patients from various healthcare systems, payor networks, and organizations who used the platform as an adjunct to their traditional care. The first study explored the use of natural language processing (NLP) to detect SI and enable intervention. The second study used dBH-administered ecological momentary assessment (EMA) of affective and physiological states to predict the 30-day risk of SI based on responses to self-harm questions.