AI model predicts in-hospital mortality for elderly surgical patients

An AI-driven Geriatric Emergency Perioperative Risk Index (GEPR) effectively predicts postoperative in-hospital mortality for elderly patients undergoing emergency general surgery. Utilizing data from 1,500 patients, the Random Forest Classifier algorithm excelled in accuracy, achieving a c-statistic of 0.872. The probability of in-hospital mortality varied significantly, increasing from 0% to 100% as GEPR scores ranged from 0 to 15, emphasizing the model’s robustness. Ongoing clinical trials aim to further validate GEPR’s reliability across diverse patient populations.