Sign in Subscribe
Gerontology

AI-Based Frailty Index Predicts Postoperative Outcomes in Older Adults

Strategic Insights

— 2 min read

A new study published in The Journals of Gerontology, Series A has found that an artificial intelligence (AI)-based frailty index effectively predicts postoperative outcomes in older adults. The study, conducted by a team of researchers at the University of Florida, used electronic health records (EHR) to develop and validate an AI-based frailty index that can be used to stratify surgical risk in older adults.

The researchers examined the association between the predicted frailty and three postoperative outcomes: 30-day mortality, length of hospital stay, and discharge disposition. They found that patients in the highest frailty level (top 20%) had significantly higher odds of 30-day mortality, longer hospital stays, and a higher likelihood of unfavorable discharge dispositions compared to the lowest frailty level. The general frailty index performed comparably to or slightly better than service-specific indices across surgical specialties.

This research has significant implications for improving surgical care and outcomes in older adults. By providing a more efficient and accurate way to predict postoperative risks, healthcare providers can make more informed decisions and provide better care for their patients. The AI-based frailty index developed by the researchers can potentially improve surgical care and outcomes by identifying which patients are at higher risk for adverse postoperative outcomes.

Key Takeaways:

  • An AI-based frailty index developed using electronic health records (EHR) can effectively predict postoperative outcomes in older adults.
  • Patients in the highest frailty level (top 20%) had significantly higher odds of 30-day mortality, longer hospital stays, and a higher likelihood of unfavorable discharge dispositions compared to the lowest frailty level.
  • The general frailty index performed comparably to or slightly better than service-specific indices across surgical specialties.
  • The AI-based frailty index can potentially improve surgical care and outcomes by identifying which patients are at higher risk for adverse postoperative outcomes.
  • The study used a large and diverse external cohort of 152,364 surgical patients aged 65+ years from the OneFlorida+ Clinical Research Consortium.
  • The researchers examined the association between the predicted frailty and three postoperative outcomes: 30-day mortality, length of hospital stay, and discharge disposition.
  • The study found a strong and stepwise association between the predicted frailty and adverse postoperative outcomes.

Statistics:

  • The study used a cohort of 152,364 surgical patients aged 65+ years from the OneFlorida+ Clinical Research Consortium.
  • The general frailty index performed comparably to or slightly better than service-specific indices across surgical specialties.
  • Patients in the highest frailty level (top 20%) had significantly higher odds of 30-day mortality (OR 4.33, 95% CI 3.91-4.80).
  • Patients in the highest frailty level (top 20%) had significantly longer hospital stays (2.53 times longer, 95% CI 2.47-2.60).
  • Patients in the highest frailty level (top 20%) had a higher likelihood of unfavorable discharge dispositions compared to the lowest frailty level.

Sources:

  • External validation of an AI-based preoperative frailty index using real-world data. The Journals of Gerontology, Series A, 2025;80(11).
  • NewsRx. Findings on Geriatrics and Gerontology Detailed by Researchers at University of Florida (External validation of an AI-based preoperative frailty index using real-world data). Medical Devices & Surgical Technology Week. October 26, 2025; p 651.

Read more