Development Of Machine Learning Models For Predicting Unfavorable Functional Outcomes From Preoperative Data In Patients With Chronic Subdural Hematomas

This study aimed to predict the functional prognosis of patients with chronic subdural hematoma (CSDH) before undergoing burr hole surgery by employing various machine learning algorithms and utilizing preoperative blood test results and clinical findings as inputs. The practicality and applicability of these predictive models in real-world clinical settings were assessed by performing internal and external validations. Data was collected from two institutions, and patients who met the criteria were included in the study. All patients underwent hematoma evacuation via single burr hole craniostomy under local anesthesia, and postoperative neurological status was assessed. Clinical findings, such as age, sex, medical history, and neurological symptoms, were also taken into account.