Predictive Models of Long‑Term Outcome in Patients with Moderate to Severe Traumatic Brain Injury are Biased Toward Mortality Prediction
Florian Pierre Martin(1,2), Thomas Goronflot(3), Jean Denis Moyer(4), Olivier Huet(5), Karim Asehnoune(1,2), Raphaël Cinotti(2,6), Pierre Antoine Gourraud(1,3) and Antoine Roquilly(1,2)
1 Nantes Université, Institut National de la Santé et de la Recherche Médicale (INSERM), UMR 1064, Center for Research in Transplantation and Translational Immunology (CR2TI), 22 Boulevard Bénoni Goullin, 44200 Nantes, France
2 Department of Anesthesiology and Surgical Intensive Care Unit, Centre Hospitalier Universitaire (CHU) Nantes, Nantes, France
3 CHU Nantes, Pôle Hospitalo‑Universitaire 11: Santé Publique, Clinique Des Données, INSERM, Nantes Université, Nantes, France
4 Department of Anesthesia and Critical Care, Départements Médico‑Universitaires Parabol, Assistance Publique–Hôpitaux de Paris Nord, Beaujon Hospital, Paris, France
5 Anesthesia and Intensive Care Unit, CHU Brest, Brest, France
6 Methods in Patient‑Centered Outcomes and Healthy Research (SPHERE), INSERM, UMR 1246, Nantes Université, Université de Tours, Nantes, France
Corresponding author. Florian Pierre Martin. Institut de Recherche en Santé 2 Nantes Biotech, Nantes University, 44000 Nantes, France. e-mail: florianpierremartin@gmail.com
Background. The prognostication of long-term functional outcomes remains challenging in patients with traumatic brain injury (TBI). Our aim was to demonstrate that intensive care unit (ICU) variables are not efficient to predict 6-month functional outcome in survivors with moderate to severe TBI (msTBI) but are mostly associated with mortality, which leads to a mortality bias for models predicting a composite outcome of mortality and severe disability.
Methods. We analyzed the data from the multicenter randomized controlled Continuous Hyperosmolar Therapy in Traumatic Brain-Injured Patients trial and developed predictive models using machine learning methods and baseline characteristics and predictors collected during ICU stay. We compared our models’ predictions of 6-month binary Glasgow Outcome Scale extended (GOS-E) score in all patients with msTBI (unfavorable GOS-E 1–4 vs. favorable GOS-E 5–8) with mortality (GOS-E 1 vs. GOS-E 2–8) and binary functional outcome in survivors with msTBI (severe disability GOS-E 2–4 vs. moderate to no disability GOS-E 5–8). We investigated the link between ICU variables and long-term functional outcomes in survivors with msTBI using predictive modeling and factor analysis of mixed data and validated our hypotheses on the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) model.
Results. Based on data from 370 patients with msTBI and classically used ICU variables, the prediction of the 6-month outcome in survivors was inefficient (mean area under the receiver operating characteristic 0.52). Using factor analysis of mixed data graph, we demonstrated that high-variance ICU variables were not associated with outcome in survivors with msTBI (p = 0.15 for dimension 1, p = 0.53 for dimension 2) but mostly with mortality (p < 0.001 for dimension 1), leading to a mortality bias for models predicting a composite outcome of mortality and severe disability. We finally identified this mortality bias in the IMPACT model.
Conclusions. We demonstrated using machine learning–based predictive models that classically used ICU variables are strongly associated with mortality but not with 6-month outcome in survivors with msTBI, leading to a mortality bias when predicting a composite outcome of mortality and severe disability.
KEYWORDS Traumatic brain injury, GOS-E, Predictive modeling, Intensive care, Machine learning