The former Vanderbilt University School of Medicine student and Vanderbilt Health resident spent 15 years on the faculty of the University of Louisville.

Large language models have been functionally opaque. Seeking some transparency, a team undertook a comparison with traditional machine learning for predicting which patients would discontinue their home cancer medications.

Due to nations’ conflicting privacy regulations, de-identified clinical data needed for science doesn’t always travel so well internationally. A team turned to AI to generate a better class of fake people living with HIV.

As trustworthiness takes center stage in medical AI, a new paper in Nature Biomedical Engineering describes a solution for trustworthy AI cancer subtyping.

Three Department of Biostatistics faculty have won new leadership roles and honors in the American Statistical Association and the International Statistical Institute

The machine learning-derived model was 88% accurate in ranking preoperative patients according to risk for postoperative acute kidney injury.