This new study out in Scientific Reports, led by Dr. Adi Bejan, uses Natural Language Processing (NLP) to improve how well we identify suicidal thoughts and behaviors in healthcare data. Methods relying on diagnostic codes to identify suicidal ideation and suicide attempt in Electronic Health Records (EHRs) at scale are suboptimal because suicide-related outcomes are…
Category: Suicide Risk Prediction Using Machine Learning/AI
New Video – NIH/NCATS Machine Intelligence Workshop, 7/12/2019
The Video of the NIH/NCATS Machine Intelligence Workshop is now online. It was a fantastic day with rich discussion. Panels from experts like Ken Mandl, Nigam Shah, Dina Katabi, and more. Dr. Walsh participated in the second panel on Explainability. His talk focused on "The Importance of Algorithmic Explainability in Behavioral Health". https://videocast.nih.gov/summary.asp?Live=33220&bhcp=1
NIMH Suicide Risk Algorithm Applications in Healthcare Settings, June 5-6, 2019
Dr. Walsh participated in this workshop at the National Institutes of Mental Health with thought leaders and researchers in suicide prevention from around the country. The topics covered ranged from: Biostatistical challenges Provider and patient understanding of risk algorithms Ethical considerations Needs for clinical decision tools to guide risk algorithm application Policy-relevant research It…
Walsh Science 