Researchers evaluate the potential of automated artificial intelligence (AI)-based body composition algorithms to predict future fall risks in patients. Their study used automated abdominal CT-based measures of muscle, fat, and bone to provide a novel method for future fall risk stratification, particularly in identifying patients with osteosarcopenic obesity.
The retrospective case-control study involved 9,029 patients who underwent abdominal CT scans over 20 years at a single institution. The study utilized validated and automated quantitative algorithms to assess skeletal muscle, adipose tissue, and trabecular bone attenuation at the L1 vertebral level. The results indicated lower muscle and bone Hounsfield units and higher total adipose area were associated with increased fall risks.
Ref: Liu D, Binkley N, Pérez A, et al. CT image-based biomarkers acquired by AI-based algorithms for the opportunistic prediction of falls. BJR|open. 2023;5(1). doi: https://doi.org/10.1259/bjro.20230014
2 responses to “AI-Powered Abdominal CT Analysis Predicts Fall Risk”
Yes
Great article! It’s fascinating to see how AI-based body composition algorithms can help predict future fall risks in patients. My question for the author is, did the study also take into account other factors that could contribute to fall risks, such as age or previous fall history? Great article! It’s fascinating to see how AI-based body composition algorithms can help predict future fall risks in patients. My question for the author is, did the study also take into account other factors that could contribute to fall risks, such as age or previous fall history?
Johnie
AiRiches.Online
This study is a retrospective age- and sex-matched case–control study. So the researchers did take age in to study design. There is no mention about other variables like previous fall history.