Emily E. Haroz, PhD
By Yulin Hswen and Jennifer Abbasi, Journal of the American Medical Association (JAMA), Image: screenshot from article, January 10, 2025
This conversation is part of a series of interviews in which JAMA Network editors and expert guests explore issues surrounding the rapidly evolving intersection of artificial intelligence (AI) and medicine.
In a recent study using electronic health record data from nearly 17 000 patients, researchers found that an existing suicide risk machine learning model was better than a non-AI screening method at distinguishing who would or wouldn’t have a suicide attempt or death within 3 months of their last Indian Health Service visit. The findings, published this fall in JAMA Network Open, are important because although American Indian and Alaska Native communities have higher rates of suicide than any other racial or ethnic group in the US, no AI-based suicide screening or risk assessment tool has previously been studied in these communities.
The study’s lead author, Emily E. Haroz, PhD, an associate professor at the Johns Hopkins Bloomberg School of Public Health’s Center for Indigenous Health, spoke with Yulin Hswen, ScD, MPH, an associate editor at JAMA and the newly launched JAMA+ AI and an assistant professor of epidemiology and biostatistics at the University of California, San Francisco, about culturally sensitive development and testing of AI tools and how the machine learning model—if further validated in a clinical trial—could be applied in practice.
This interview has been edited for clarity and length.
Dr Hswen: This is obviously a very sensitive topic and especially dealing with populations like those from Indigenous communities. Can you tell me a little bit about how you started this work?
Comments (0)