New York, NY—Researchers at the Icahn School of Medicine at Mount Sinai have developed a machine learning tool that can help doctors manage blood sugar levels in patients recovering from heart surgery, a critical but often difficult task in the intensive care unit (ICU).
The research team created a reinforcement learning model, named GLUCOSE, that recommends insulin doses tailored to each patient’s needs. In tests using data from real-world ICU cases, GLUCOSE matched or even outperformed experienced clinicians in keeping blood sugar levels within a safe range. The model could eventually be integrated into electronic health record systems to provide real-time insulin dosing guidance in the ICU, helping reduce complications and improve outcomes.