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

Led by Simon Vandekar, PhD, a group of biostatisticians earned the honor for tools that help brain researchers tell strong, trustworthy findings from weak ones. Vanderbilt Health teams took two of 15 total NIH prizes.

The FROSTBITE-2 trial used the 1.1-millimeter cryoprobe which, unlike the larger probes, is small enough to remove the biopsy specimen through the working channel without having to remove the scope, which increases safety.

A new platform allows visualization of drug-tumor interactions in human solid tumors, providing a tool for measuring drug delivery and signaling.

The artificial intelligence model Enformer was retrained with tissue-specific datasets; this "transfer learning" approach outperformed the base model in identifying disease-associated genes.

DNA biobanks had lacked systematic ways to evaluate whether the medical record data being analyzed accurately reflected the diseases under study.

The new artificial intelligence tool aims to spare Vanderbilt Health patients and clinicians the back-and-forth that can delay answers to patients' electronic health care questions.