Abstract Details

Title Machine Learning Models to Predict Withdrawal of Life-sustaining Therapy in Patients With Severe Traumatic Brain Injury

Topic Neuro Trauma and Critical Care

Presentation(s) S21 - Neurocritical Care (1:24 PM-1:36 PM)

Poster/Presentation
Number 003

Objective We aimed to create a machine learning (ML) model that could accurately predict the decision to withdrawal life-sustaining therapy (WLST) and hypothesized that facility WLST rate would emerge as a highly impactful WLST determinant.

Background Despite recent improvements in traumatic brain injury (TBI) mortality, rates of WLST have remained unchanged, potentially reflecting outdated prognostic misconceptions. Determinants of the decision to WLST are multifaceted and complex, which is reflected in the significant variability in WLST rates between centers.

Design/Methods This observational study analyzed data from the American College of Surgeons Trauma Quality Improvement Project National Trauma Databank (2017–2021). Patients with severe TBI, defined by a maximum Abbreviated Injury Scale-Head ≥1 and presenting Glasgow Coma Scale (GCS) <9, were included. ML models were developed to predict WLST using variables available at different time points. The performance of each model in predicting WLST was optimized for area under the receiver operating curve (AUROC). The most impactful determinants of WLST were assessed using Shapley additive explanation scores.

Results Of 5,481,046 patients, 155,639 met inclusion criteria, with 32,385 (20.8%) undergoing WLST. The mean age was 43 ± 22 years, 26.5% of patients were female, and the median time to WLST was 46.4 hours. The AUROC of 0.875 (95% CI 0.871–0.879) in the admission model improved to 0.896 (95% CI 0.892–0.900) in the total length-of-stay model. Age, highest emergency department GCS, and facility WLST rate were the most important factors in prediction of WLST.

Conclusions Our models reliably predict the decision to WLST. We found that institutional withdrawal culture is a strong independent determinant of WLST, irrespective of clinical condition. As TBI care improves, our findings underscore the importance of refining prognosticating tools to prevent premature WLST decisions which may be influenced by biases associated with self-fulfilling prophecies and institutional practice patterns.

Authors/Disclosures
Michael D. Cobler-Lichter, MD PRESENTER	Dr. Cobler-Lichter has nothing to disclose.
Jessica Delamater, MD	Dr. Delamater has nothing to disclose.
Fernanda Jacinto Pereira Teixeira, MD	Dr. Jacinto Pereira Teixeira has nothing to disclose.
Ana Reyes, MD	Dr. Reyes has nothing to disclose.
Talia Arcieri	Ms. Arcieri has nothing to disclose.
Brian Manolovitz, PhD	Dr. Manolovitz has nothing to disclose.
John McKeown, PhD	Dr. McKeown has received personal compensation for serving as an employee of University of Miami Miller School of Medicine.
Tulay Koru-Sengul, PhD	Dr. Koru-Sengul has nothing to disclose.
Jonathan Jagid	Jonathan Jagid has received personal compensation in the range of $10,000-$49,999 for serving as an Expert Witness for Miami Dade County State Attorneys office. The institution of Jonathan Jagid has received research support from Boston Scientific.
JOACIR G. Cordeiro, MD, PhD	Dr. Cordeiro has nothing to disclose.
Nina M. Massad, MD (University of Miami)	Dr. Massad has nothing to disclose.
Mohan Kottapally, MD (University of Miami Miller School of Medicine)	Dr. Kottapally has nothing to disclose.
Amedeo Merenda, MD (Univeristy of Miami Miller School of Medicine)	Dr. Merenda has nothing to disclose.
Kristine H. O'Phelan, MD (University of Miami)	Dr. O'Phelan has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Bard Medical. Dr. O'Phelan has a non-compensated relationship as a DSMB member SIREN network with NIH/NINDS that is relevant to AAN interests or activities.
Nicholas Namias, MD	Dr. Namias has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Molnycke.
Ayham M. Alkhachroum, MD (Columbia University Medical Center)	The institution of Dr. Alkhachroum has received research support from Miami CTSI.

��ɫ��

��ɫ��