To Örebro University

OBJECTIVE: We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury.

STUDY DESIGN AND SETTING: We performed logistic (LR), lasso, and ridge regression with key baseline predictors in the IMPACT-II database (15 studies, n=11,022). ML algorithms included support vector machines, random forests, gradient boosting machines, and artificial neural networks, and were trained using the same predictors. To assess generalizability of predictions, we performed internal, internal-external, and external validation on the recent CENTER-TBI study (patients with GCS<13, n = 1,554). Both calibration (calibration slope/intercept) and discrimination (AUC) was quantified.

RESULTS: In the IMPACT-II database, 3,332/11,022(30%) died and 5,233(48%) had unfavorable outcome (Glasgow Outcome Scale below 4). In the CENTER-TBI study, 348/1,554(29%) died and 651(54%) had unfavorable outcome. Discrimination and calibration varied widely between the studies, and less so between the studied algorithms. The mean AUC was 0.82 for mortality and 0.77 for unfavorable outcome in CENTER-TBI.

CONCLUSION: ML algorithms may not outperform traditional regression approaches in a low-dimensional setting for outcome prediction after moderate or severe TBI. Similar to regression-based prediction models, ML algorithms should be rigorously validated to ensure applicability to new populations.