Using Machine Learning to Predict Unplanned Return to the Operating Room for Early-Onset Scoliosis Patients

Surgical treatment of early-onset scoliosis allows the spine to grow and preserves pulmonary function, but it often involves a high rate of complications that may require an unplanned return to the operating room. Researchers have created and validated a machine learning model that predicts which early-onset scoliosis patients will end up requiring an unplanned return to the operating room and gives surgeons a better understanding of the factors that lead to this. Their study is published in Spine Deformity. 

“It is helpful to know which patient factors contribute to unplanned returns to the operating room because we can control some of them pre-operatively,” says Brett Lullo, MD, an attending physician in the Division of Orthopaedic Surgery and Sports Medicine at Ann & Robert H. Lurie Children’s Hospital of Chicago and lead author of the study. “Though we cannot change a patient's underlying disease, we can delay surgery and allow them to gain weight and grow taller. We can also choose a more appropriate surgical construct for the patient.”