Mortality Prediction in Severe Traumatic Brain Injury Using Traditional and Machine Learning Algorithms.

Abstract Prognostic prediction of traumatic brain injury (TBI) in patients is crucial in clinical decision and health care policy making. This study aimed to develop and validate prediction models for in-hospital mortality after severe traumatic brain injury (sTBI). We developed and validated logistic regression (LR), LASSO regression, and machine learning (ML) algorithms including support vector machines (SVM) and XGBoost models. Fifty-four candidate predictors were included. Model performance was expressed in terms of discrimination (C-statistic) and calibration (intercept and slope). For model development, 2804 patients with sTBI in the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) China Registry study were included. External validation was performed in 1113 patients with sTBI in the CENTER-TBI European Registry study. XGBoost achieved high discrimination in mortality prediction, and it outperformed logistic and LASSO regression. The XGBoost model established in this study also outperformed prediction models currently available, including the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) core and International Mission for Prognosis and Analysis of Clinical Trials (CRASH) basic models. When including 54 variables, XGBoost and SVM reached C-statistics of 0.87 (95% confidence interval [CI]: 0.81-0.92) and 0.85 (95% CI: 0.79-0.90) at internal validation, and 0.88 (95% CI: 0.87-0.88) and 0.86 (95% CI: 0.85-0.87) at external validation, respectively. A simplified version of XGBoost and SVM using 26 variables selected by recursive feature elimination (RFE) reached C-statistics of 0.87 (95% CI: 0.82-0.92) and 0.86 (95% CI: 0.80-0.91) at internal validation, and 0.87 (95% CI: 0.87-0.88) and 0.87 (95% CI: 0.86-0.87) at external validation, respectively. However, when the number of variables included decreased, the difference between ML and LR diminished. All the prediction models can be accessed via a web-based calculator. Glasgow Coma Scale (GCS) score, age, pupillary light reflex, Injury Severity Score (ISS) for brain region, and the presence of acute subdural hematoma were the five strongest predictors for mortality prediction. The study showed that ML techniques such as XGBoost may capture information hidden in demographic and clinical predictors of patients with sTBI and yield more precise predictions compared with LR approaches.

Right median nerve electrical stimulation for acute traumatic coma (the Asia Coma Electrical Stimulation trial): study protocol for a randomised controlled trial.

BACKGROUND: Traumatic brain injury (TBI) has become the most common cause of death and disability in persons between 15 and 30 years of age, and about 10-15% of patients affected by TBI will end up in a coma. Coma caused by TBI presents a significant challenge to neuroscientists. Right median nerve electrical stimulation has been reported as a simple, inexpensive, non-invasive technique to speed recovery and improve outcomes for traumatic comatose patients. METHODS/DESIGN: This multicentre, prospective, randomised (1:1) controlled trial aims to demonstrate the efficacy and safety of electrical right median nerve stimulation (RMNS) in both accelerating emergence from coma and promoting long-term outcomes. This trial aims to enrol 380 TBI comatose patients to partake in either an electrical stimulation group or a non-stimulation group. Patients assigned to the stimulation group will receive RMNS in addition to standard treatment at an amplitude of 15-20 mA with a pulse width of 300 µs at 40 Hz ON for 20 s and OFF for 40 s. The electrical treatment will last for 8 h per day for 2 weeks. The primary endpoint will be the percentage of patients regaining consciousness 6 months after injury. The secondary endpoints will be Extended Glasgow Outcome Scale, Coma Recovery Scale-Revised and Disability Rating Scale scores at 28 days, 3 months and 6 months after injury; Glasgow Coma Scale, Glasgow Coma Scale Motor Part and Full Outline of Unresponsiveness scale scores on day 1 and day 7 after enrolment and 28 days, 3 months and 6 months after injury; duration of unconsciousness and mechanical ventilation; length of intensive care unit and hospital stays; and incidence of adverse events. DISCUSSION: Right median nerve electrical stimulation has been used as a safe, inexpensive, non-invasive therapy for neuroresuscitation of coma patients for more than two decades, yet no trial has robustly proven the efficacy and safety of this treatment. The Asia Coma Electrical Stimulation (ACES) trial has the following novel features compared with other major RMNS trials: (1) the ACES trial is an Asian multicentre randomised controlled trial; (2) RMNS therapy starts at an early stage 7-14 days after the injury; and (3) various assessment scales are used to evaluate the condition of patients. We hope the ACES trial will lead to optimal use of right median nerve electrical treatment. TRIAL REGISTRATION: ClinicalTrials.gov, NCT02645578 . Registered on 23 December 2015.