GR.7 Artificial intelligence-based decision support predicts requirement for neurosurgical intervention in acute traumatic brain injury

Abstract

Background: We aimed to develop an efficient and reliable artificial intelligence solution to automate prediction of neurosurgical intervention using acute traumatic brain injury computed tomography (CT) scans. Methods: TBI patients were identified from 2005 - 2022 at a Level 1 Canadian trauma center. Model training, validation, and testing was performed using head CT scans with patient-level labels corresponding to whether the patient received neurosurgical intervention. The finalized model was then deployed in a simulated prospective fashion on all TBI patients presenting to our center over an 18-month epoch. Results: 2,806 TBI scans were utilized for development of the Automated Surgical Intervention Support Tool (ASIST-TBI). 612 additional consecutive scans were used for simulated prospective model deployment. Prediction of neurosurgical intervention exhibited an area under receiver operating curve (AUC) of 0.92, accuracy of 0.87, sensitivity of 0.87, and specificity of 0.88 on the test dataset. On simulated prospective data, the results were: AUC 0.89, sensitivity 0.85, specificity 0.84 and accuracy of 0.84. Conclusions: We demonstrate the development and validation of ASIST-TBI, a machine learning model that accurately predicts whether TBI patients will need neurosurgical intervention. This model has potential application to optimize decision support and province-wide efficiency of inter-facility TBI triage to tertiary care centers.