AI Model Predicts Risk of Acute Kidney Injury in ICU Patients

Among 16,785 adults admitted to the ICU in 2015–2020 in Taichung Veterans General Hospital (Taiwan), 30% developed AKI. An AI–based AKI prediction model based on these patients’ data (21 features including urine trend and serum creatine) was validated in patients from four other medical centers (2,874, 10,758, 12,299, and 12,483 patients, respectively, with a wide range of AKI incidence of 24.9–67.2%). The model was accurate at predicting AKI 24 hours ahead of time.

“Early prediction of AKI ahead of 24 hours may help clinicians initiate timely interventions to prevent AKI from happening or alleviate its severity,” said corresponding author Chun-Te Huang, MD, of Taichung Veterans General Hospital. “Our model could be easily shared and integrated to different hospitals to provide a real-time risk prediction in electronic health information systems.”

Related Links:
Taichung Veterans General Hospital