Changes in body composition over time can be identified on total-body dual-energy x-ray absorptiometry (DEXA) exam by artificial intelligence (AI) algorithms and help to predict mortality risk, according to research presented at RSNA 2021 in Chicago.
After developing deep-learning algorithms on data from over 3,000 subjects, researchers from the University of Hawaii found that DEXA image data-enhanced mortality predictions.
“Including longitudinal and total-body DEXA information [in deep-learning models] does improve mortality prediction,” said presenter Yannik Glaser, PhD.
AI can predict mortality from DEXA body composition data by Erik L. Ridley, AuntMinnie.com staff writer
Read more about our work using AI and DEXA under The TBDXAI Project.