Predicting Outcome of Traumatic Brain Injury: Is Machine Learning the Best Way?

• Published in: Biomedicines Vol. 10; no. 3; p. 686
• Main Authors: Bruschetta, Roberta, Tartarisco, Gennaro, Lucca, Lucia Francesca, Leto, Elio, Ursino, Maria, Tonin, Paolo, Pioggia, Giovanni, Cerasa, Antonio
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 16.03.2022; MDPI
• Subjects: Algorithms; Artificial intelligence; Bayesian analysis; Classification; Coma; Decision trees; ensemble of classifiers; Feature selection; Learning algorithms; linear regression; Machine learning; Ostomy; outcome predictors; Patients; Regression analysis; Support vector machines; Traumatic brain injury; linear regression; traumatic brain injury; outcome predictors; machine learning; ensemble of classifiers
• ISSN: 2227-9059; 2227-9059
• DOI: 10.3390/biomedicines10030686

One of the main challenges in traumatic brain injury (TBI) patients is to achieve an early and definite prognosis. Despite the recent development of algorithms based on artificial intelligence for the identification of these prognostic factors relevant for clinical practice, the literature lacks a rigorous comparison among classical regression and machine learning (ML) models. This study aims at providing this comparison on a sample of TBI patients evaluated at baseline (T0), after 3 months from the event (T1), and at discharge (T2). A Classical Linear Regression Model (LM) was compared with independent performances of Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Naïve Bayes (NB) and Decision Tree (DT) algorithms, together with an ensemble ML approach. The accuracy was similar among LM and ML algorithms on the analyzed sample when two classes of outcome (Positive vs. Negative) approach was used, whereas the NB algorithm showed the worst performance. This study highlights the utility of comparing traditional regression modeling to ML, particularly when using a small number of reliable predictor variables after TBI. The dataset of clinical data used to train ML algorithms will be publicly available to other researchers for future comparisons.