Researchers at Vanderbilt University Medical Center and the University of Cambridge have developed a method of or predicting gene expression in hard-to-access tissues like the brain from more accessible tissues, including whole blood.

A new project, funded by the National Institutes of Health (NIH), National Institute on Deafness and Other Communication Disorders (NIDCD) and led by Aaron Moberly, MD, and Metin Gurcan, PhD, professor and director of the Center for Biomedical Informatics and the Clinical Image Analysis Lab at Wake Forest University School of Medicine, aims to develop machine learning applications to analyze eardrum videos collected with a digital otoscope.

A machine learning method based on neural networks outperformed a mutational scanning model at identifying disease-causing mutations in an Alzheimer’s disease protein, suggesting the method could be useful for facilitating therapeutic design.

Using machine learning based on electronic health records of ICU patients predicted new-onset delirium with 82% sensitivity, Vanderbilt researchers found.

Vanderbilt researchers will lead and comprise the greater part of an artificial intelligence research ethics core for a National Institutes of Health (NIH) program called Bridge to Artificial Intelligence, or Bridge2AI.