Predicting the Individual Treatment Effect of Neurosurgery for TBI Patients in the Low Resource Setting: A Machine Learning Approach in Uganda.

Traumatic brain injury (TBI) disproportionately affects low- and middle-income countries (LMICs). In these low-resource settings, effective triage of TBI patients-including the decision regarding whether or not to perform neurosurgery-is critical in optimizing patient outcomes and healthcare resource utilization. Machine learning may allow for effective predictions of patient outcomes both with and without surgery. Data from TBI patients was prospectively collected at Mulago National Referral Hospital in Kampala, Uganda, from 2016 to 2019. One linear and 6 non-linear machine learning models were designed to predict good vs poor outcome near hospital discharge and internally-validated using nested 5-fold cross-validation. The 13 predictors included clinical variables easily acquired on admission and whether or not the patient received surgery. Using the elastic-net regularized logistic regression model (GLMnet), with predictions calibrated using Platt scaling, the probability of poor outcome was calculated for each patient both with and without surgery (quantifying the "individual treatment effect", ITE). Relative ITE equals this ITE divided by the probability of bad outcome with no surgery. Ultimately, 1766 patients were included. Areas under the receiver operating characteristic curve (AUCs) ranged from 83.1% (single C5.0 ruleset) to 88.5% (random forest), with the GLMnet at 87.5%. The two variables promoting good outcomes in the GLMnet model were high GCS and receiving surgery. For the subgroup not receiving surgery, the median relative ITE was 42.9% (IQR, 32.7% to 53.5%); similarly, in those receiving surgery, it was 43.2% (IQR, 32.9% to 54.3%). We provide the first machine learning-based model to predict TBI outcomes with and without surgery in LMICs, thus enabling more effective surgical decision making in the resource-limited setting. Predicted ITE similarity between surgical and non-surgical groups suggests that, currently, patients are not being optimally chosen for neurosurgical intervention. A clinical decision aid as presented here may help improve outcomes.