Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis.

Background: Traumatic brain injury (TBI) is a leading cause of death and disability worldwide. The use of machine learning (ML) has emerged as a key advancement in TBI management. This study aimed to identify ML models with demonstrated effectiveness in predicting TBI outcomes. Methods: We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. In total, 15 articles were identified using the search strategy. Patient demographics, clinical status, ML outcome variables, and predictive characteristics were extracted. A small meta-analysis of mortality prediction was performed, and a meta-analysis of diagnostic accuracy was conducted for ML algorithms used across multiple studies. Results: ML algorithms including support vector machine (SVM), artificial neural networks (ANN), random forest, and Naïve Bayes were compared to logistic regression (LR). Thirteen studies found significant improvement in prognostic capability using ML versus LR. The accuracy of the above algorithms was consistently over 80% when predicting mortality and unfavorable outcome measured by Glasgow Outcome Scale. Receiver operating characteristic curves analyzing the sensitivity of ANN, SVM, decision tree, and LR demonstrated consistent findings across studies. Lower admission Glasgow Coma Scale (GCS), older age, elevated serum acid, and abnormal glucose were associated with increased adverse outcomes and had the most significant impact on ML algorithms. Conclusion: ML algorithms were stronger than traditional regression models in predicting adverse outcomes. Admission GCS, age, and serum metabolites all have strong predictive power when used with ML and should be considered important components of TBI risk stratification.

Frailty as a Superior Predictor of Dysphagia and Surgically Placed Feeding Tube Requirement After Anterior Cervical Discectomy and Fusion Relative to Age.

Frailty is a measure of physiological reserve that has been demonstrated to be a discriminative predictor of worse outcomes across multiple surgical subspecialties. Anterior cervical discectomy and fusion (ACDF) is one of the most common neurosurgical procedures in the United States and has a high incidence of postoperative dysphagia. To determine the association between frailty and dysphagia after ACDF and compare the predictive value of frailty and age. 155,300 patients with cervical stenosis (CS) who received ACDF were selected from the 2016-2019 National Inpatient Sample (NIS) utilizing International Classification of Disease, tenth edition (ICD-10) codes. The 11-point modified frailty index (mFI-11) was used to stratify patients based on frailty: mFI-11 = 0 was robust, mFI-11 = 1 was prefrail, mFI-11 = 2 was frail, and mFI-11 = 3 + was characterized as severely frail. Demographics, complications, and outcomes were compared between frailty groups. A total of 155,300 patients undergoing ACDF for CS were identified, 33,475 (21.6%) of whom were frail. Dysphagia occurred in 11,065 (7.1%) of all patients, and its incidence was significantly higher for frail patients (OR 1.569, p < 0.001). Frailty was a risk factor for postoperative complications (OR 1.681, p < 0.001). Increasing frailty and undergoing multilevel ACDF were significant independent predictors of negative postoperative outcomes, including dysphagia, surgically placed feeding tube (SPFT), prolonged LOS, non-home discharge, inpatient death, and increased total charges (p < 0.001 for all). Increasing mFI-11 score has better prognostic value than patient age in predicting postoperative dysphagia and SPFT after ACDF.