Skip to main content

ORIGINAL RESEARCH article

Front. Neurol.
Sec. Neurotrauma
Volume 15 - 2024 | doi: 10.3389/fneur.2024.1502153
This article is part of the Research Topic Differentiating and understanding the multifaceted nature of Traumatic Brain Injury using clinical and pre-clinical systems View all 5 articles

A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults

Provisionally accepted
Daisu Abe Daisu Abe 1Motoki Inaji Motoki Inaji 1*Takeshi Hase Takeshi Hase 1Eiichi Suehiro Eiichi Suehiro 2Naoto Shiomi Naoto Shiomi 3Hiroshi Yatsushige Hiroshi Yatsushige 4Shin Hirota Shin Hirota 5Shu Hasegawa Shu Hasegawa 6Hiroshi Karibe Hiroshi Karibe 7Akihiro Miyata Akihiro Miyata 8Kenya Kawakita Kenya Kawakita 9Haji Kohei Haji Kohei 10Hideo Aihara Hideo Aihara 11Shoji Yokobori Shoji Yokobori 12Takeshi Maeda Takeshi Maeda 13Takahiro Onuki Takahiro Onuki 14Kotaro Oshio Kotaro Oshio 15Nobukazu Komoribayashi Nobukazu Komoribayashi 16Michiyasu Suzuki Michiyasu Suzuki 10Taketoshi Maehara Taketoshi Maehara 1
  • 1 Tokyo Medical and Dental University, Tokyo, Japan
  • 2 International University of Health and Welfare, Narita, Narita, Japan
  • 3 Saiseikai Shigaken Hospital, Ritto, Japan
  • 4 National Disaster Medical Center (NHO), Tokyo, Japan
  • 5 Tsuchiura Kyodo General Hospital, Tsuchiura, Ibaraki, Japan
  • 6 Japanese Red Cross Kumamoto Hospital, Kumamoto, Kumamoto, Japan
  • 7 Sendai City Hospital, Sendai, Miyagi, Japan
  • 8 Chiba Emergency Medical Center, Chiba, Japan
  • 9 Kagawa University Hospital, Kita-gun, Japan
  • 10 Yamaguchi University, Yamaguchi, Yamaguchi, Japan
  • 11 Hyogo Prefectural Kakogawa Medical Center, Hyogo, Hyōgo, Japan
  • 12 Nippon Medical School, Bunkyō, Tōkyō, Japan
  • 13 Nihon University, Tokyo, Tōkyō, Japan
  • 14 Teikyo University, Itabashi, Tōkyō, Japan
  • 15 St. Marianna University School of Medicine, Kawasaki, Kanagawa, Japan
  • 16 Iwate Medical University, Morioka, Iwate, Japan

The final, formatted version of the article will be published soon.

    Objective: Neurological deterioration after mild traumatic brain injury (TBI) has been recognized as a poor prognostic factor. Early detection of neurological deterioration would allow appropriate monitoring and timely therapeutic interventions to improve patient outcomes. In this study, we developed a machine learning model to predict the occurrence of neurological deterioration after mild TBI using information obtained on admission.Methods: This was a retrospective cohort study of data from the Think FAST registry, a multicenter prospective observational study of elderly TBI patients in Japan. Patients with an admission Glasgow Coma Scale (GCS) score of 12 or below or who underwent surgical treatment immediately upon admission were excluded. Neurological deterioration was defined as a decrease of 2 or more points from a GCS score of 13 or more within 24 hours of hospital admission. The model predictive accuracy was judged with the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC), and the Youden index was used to determine the cutoff value.Results: A total of 421 of 721 patients registered in the Think FAST registry between December 2019 and May 2021 were included in our study, among whom 25 demonstrated neurological deterioration. Among several machine learning algorithms, eXtreme Gradient Boosting (XGBoost) demonstrated the highest predictive accuracy in cross-validation, with an AUROC of 0.81 (±0.07) and an AUPRC of 0.33 (±0.08). Through SHapley Additive exPlanations (SHAP) analysis, five important features (D-dimer, fibrinogen, acute subdural hematoma thickness, cerebral contusion size, and systolic blood pressure) were identified and used to construct a better performing model (cross-validation AUROC of 0.84 and AUPRC of 0.34; testing data AUROC of 0.77 and AUPRC of 0.19). At the cutoff value from the Youden index, the model showed a sensitivity, specificity, and positive predictive value of 60%, 96%, and 38%, respectively. When neurosurgeons attempted to predict neurological deterioration using the same testing data, their values were 20%, 94%, and 19%, respectively.Conclusions: In this study, our predictive model showed an acceptable performance in detecting neurological deterioration after mild TBI. Further validation through prospective studies is necessary to confirm these results.

    Keywords: mild traumatic brain injury, Neurological deterioration, machine learning, predictive model, XGBoost

    Received: 26 Sep 2024; Accepted: 10 Dec 2024.

    Copyright: © 2024 Abe, Inaji, Hase, Suehiro, Shiomi, Yatsushige, Hirota, Hasegawa, Karibe, Miyata, Kawakita, Kohei, Aihara, Yokobori, Maeda, Onuki, Oshio, Komoribayashi, Suzuki and Maehara. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Motoki Inaji, Tokyo Medical and Dental University, Tokyo, Japan

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.