Early Prediction of Standing at Discharge in Moderate-to-Severe Traumatic Brain Injury: A Clinical Machine Learning Model Integrating Modifiable and Nonmodifiable Factors
Archives of Physical Medicine and Rehabilitation · 2026-06 · 107 (6) · 1177-1185
DOI: 10.1016/j.apmr.2026.02.487 ↗Kurz gefasst
Fachartikel in der Zeitschrift Archives of Physical Medicine and Rehabilitation, 2026-06. Verfasst von Hsiao-Ching Yen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Physical Therapy, Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan. Hauptthemen laut MEDLINE: Brain Injuries, Traumatic, Machine Learning, Patient Discharge, Postural Balance. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Taiwan University Hospital.
Abstract (Originalsprache)
OBJECTIVE To develop and internally validate a machine learning model to predict favorable standing ability at hospital discharge in patients with moderate-to-severe traumatic brain injury (TBI), incorporating both modifiable and nonmodifiable clinical factors. DESIGN Retrospective cohort study. SETTING A tertiary academic medical center in Taiwan. PARTICIPANTS A total of 248 adults with moderate-to-severe TBIs admitted between 2019 and 2024 who received standard acute care and had complete discharge functional outcome data. INTERVENTIONS Not applicable. MAIN OUTCOME MEASURES Favorable standing ability at discharge, defined as a score ≥6 on the Modified ICU Mobility Scale. Predictor variables included age, Glasgow Coma Scale score, Injury Severity Score, Charlson Comorbidity Index, alanine aminotransferase level, standardized education scale (nonmodifiable), intubation duration, early mobilization, trauma activation, and selected micronutrient supplementation (modifiable). Four ML models-logistic regression, extreme gradient boosting (XGBoost), random forest, and support vector machine-were trained using an 80/20 data split. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis (DCA). RESULTS The XGBoost model achieved the greatest discrimination (AUC = 0.85), good calibration (Brier score = 0.16), and an accuracy of 78%, followed by the logistic regression model (AUC = 0.82; Brier score = 0.16; accuracy = 80%). The most influential predictors were age, intubation duration, and early mobilization. In the DCA, both the XGBoost and logistic regression models provided the greatest net benefit across clinically relevant probability thresholds (0.2-0.6). CONCLUSIONS This ML-based model enables early, individualized prediction of standing ability at discharge among patients with moderate-to-severe TBIs. The inclusion of modifiable variables enhances its clinical utility for rehabilitation planning in the intensive care unit and supports data-driven quality improvement initiatives. External validation is recommended to assess its generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Physical Therapy, Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan.
- Doctoral Program in Big Data Analytics for Industrial Applications, National Chung Hsing University, Taichung, Taiwan.
- Department of Applied Mathematics and Institute of Statistics, National Chung Hsing University, Taichung, Taiwan.
- Department of Traumatology, National Taiwan University Hospital, Taipei, Taiwan; Department of Surgery, Cardiovascular Division, National Taiwan University Hospital, Taipei, Taiwan; Graduate Institute of Clinical Medici…
- Department of Traumatology, National Taiwan University Hospital, Taipei, Taiwan; Department of Anesthesiology, National Taiwan University Hospital, Taipei, Taiwan. Electronic address: noviahan@gmail.com.
Förderung
- National Taiwan University Hospital
Zitieren
APA
Yen, H. C., Huang, T. H., Hsu, Y. L., Wu, I. H., & Han, Y. Y. (2026). Early Prediction of Standing at Discharge in Moderate-to-Severe Traumatic Brain Injury: A Clinical Machine Learning Model Integrating Modifiable and Nonmodifiable Factors. Archives of Physical Medicine and Rehabilitation, 107(6), 1177-1185. https://doi.org/10.1016/j.apmr.2026.02.487
Vancouver
Yen HC, Huang TH, Hsu YL, Wu IH, Han YY. Early Prediction of Standing at Discharge in Moderate-to-Severe Traumatic Brain Injury: A Clinical Machine Learning Model Integrating Modifiable and Nonmodifiable Factors. Archives of Physical Medicine and Rehabilitation. 2026;107(6):1177-1185. doi:10.1016/j.apmr.2026.02.487
BibTeX
@article{Yen2026,
author = {Yen, Hsiao-Ching and Huang, Tzu-Hsuan and Hsu, Ying-Lin and Wu, I-Hui and Han, Yin-Yi},
title = {Early Prediction of Standing at Discharge in Moderate-to-Severe Traumatic Brain Injury: A Clinical Machine Learning Model Integrating Modifiable and Nonmodifiable Factors},
journal = {Archives of Physical Medicine and Rehabilitation},
year = {2026},
volume = {107},
number = {6},
pages = {1177--1185},
doi = {10.1016/j.apmr.2026.02.487}
}
EUVIMED