In 2019, Google AI subsidiary DeepMind used a large dataset of patient records from the Veterans Health Administration to develop a predictive model for acute kidney injury. The DeepMind model purported to predict AKI 48 hours in advance, allowing ample lead time for clinicians to intervene and administer treatment. However, a U-M team, including researchers in the ML4LHS Lab, run by Karandeep Singh, M.D., MMSc., assistant professor in the Department of Learning Health Sciences and the Biomedical & Clinical Informatics Lab run by Kayvan Najarian, Ph.D., professor in the Department of Computational Medicine and Bioinformatics found that the model performed worse for female patients and concerns were raised about its generalizability. They updated the model with data from a more sex-balanced population, which improved performance in the U-M cohort both overall and between sexes.
Read the full story in M Health Lab.