A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults
ObjectiveNeurological 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...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2024.1502153/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841561013375205376 |
|---|---|
| author | Daisu Abe Motoki Inaji Takeshi Hase Eiichi Suehiro Naoto Shiomi Hiroshi Yatsushige Shin Hirota Shu Hasegawa Hiroshi Karibe Akihiro Miyata Kenya Kawakita Kohei Haji Hideo Aihara Shoji Yokobori Takeshi Maeda Takahiro Onuki Kotaro Oshio Nobukazu Komoribayashi Michiyasu Suzuki Taketoshi Maehara |
| author_facet | Daisu Abe Motoki Inaji Takeshi Hase Eiichi Suehiro Naoto Shiomi Hiroshi Yatsushige Shin Hirota Shu Hasegawa Hiroshi Karibe Akihiro Miyata Kenya Kawakita Kohei Haji Hideo Aihara Shoji Yokobori Takeshi Maeda Takahiro Onuki Kotaro Oshio Nobukazu Komoribayashi Michiyasu Suzuki Taketoshi Maehara |
| author_sort | Daisu Abe |
| collection | DOAJ |
| description | ObjectiveNeurological 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.MethodsThis 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 h 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.ResultsA 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.ConclusionIn 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. |
| format | Article |
| id | doaj-art-0c7be28eff664155b4956df8b31112e8 |
| institution | Kabale University |
| issn | 1664-2295 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj-art-0c7be28eff664155b4956df8b31112e82025-01-03T06:46:58ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-01-011510.3389/fneur.2024.15021531502153A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adultsDaisu Abe0Motoki Inaji1Takeshi Hase2Eiichi Suehiro3Naoto Shiomi4Hiroshi Yatsushige5Shin Hirota6Shu Hasegawa7Hiroshi Karibe8Akihiro Miyata9Kenya Kawakita10Kohei Haji11Hideo Aihara12Shoji Yokobori13Takeshi Maeda14Takahiro Onuki15Kotaro Oshio16Nobukazu Komoribayashi17Michiyasu Suzuki18Taketoshi Maehara19Department of Neurosurgery, Tokyo Medical and Dental University, Bunkyo-ku, JapanDepartment of Neurosurgery, Tokyo Medical and Dental University, Bunkyo-ku, JapanInstitute of Education, Innovative Human Resource Development Division, Tokyo Medical and Dental University, Bunkyo-ku, JapanDepartment of Neurosurgery, School of Medicine, International University of Health and Welfare, Narita, JapanEmergency Medical Care Center, Saiseikai Shiga Hospital, Ritto, Shiga, JapanDepartment of Neurosurgery, NHO Disaster Medical Center, Tachikawa, JapanDepartment of Neurosurgery, Tsuchiura Kyodo General Hospital, Tsuchiura, Ibaraki, JapanDepartment of Neurosurgery, Kumamoto Red Cross Hospital, Kumamoto, JapanDepartment of Neurosurgery, Sendai City Hospital, Sendai, Miyagi, JapanDepartment of Neurosurgery, Chiba Emergency Medical Center, Chiba, Japan0Emergency Medical Center, Kagawa University Hospital, Kita-gun, Kagawa, Japan1Department of Neurosurgery, Yamaguchi University School of Medicine, Ube, Yamaguchi, Japan2Department of Neurosurgery, Hyogo Prefectural Kakogawa Medical Center, Kakogawa, Hyogo, Japan3Department of Emergency and Critical Care Medicine, Graduate School of Medicine, Nippon Medical School, Bunkyo-ku, Japan4Department of Neurological Surgery, Nihon University School of Medicine, Itabashi-ku, Japan5Department of Emergency Medicine, Teikyo University School of Medicine, Itabashi-ku, Japan6Department of Neurosurgery, St. Marianna University School of Medicine, Kawasaki, Kanagawa, Japan7Iwate Prefectural Advanced Critical Care and Emergency Center, Iwate Medical University, Yahaba, Iwate, Japan1Department of Neurosurgery, Yamaguchi University School of Medicine, Ube, Yamaguchi, JapanDepartment of Neurosurgery, Tokyo Medical and Dental University, Bunkyo-ku, JapanObjectiveNeurological 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.MethodsThis 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 h 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.ResultsA 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.ConclusionIn 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.https://www.frontiersin.org/articles/10.3389/fneur.2024.1502153/fullmild traumatic brain injuryneurological deteriorationmachine learningpredictive modelXGBoost |
| spellingShingle | Daisu Abe Motoki Inaji Takeshi Hase Eiichi Suehiro Naoto Shiomi Hiroshi Yatsushige Shin Hirota Shu Hasegawa Hiroshi Karibe Akihiro Miyata Kenya Kawakita Kohei Haji Hideo Aihara Shoji Yokobori Takeshi Maeda Takahiro Onuki Kotaro Oshio Nobukazu Komoribayashi Michiyasu Suzuki Taketoshi Maehara A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults Frontiers in Neurology mild traumatic brain injury neurological deterioration machine learning predictive model XGBoost |
| title | A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| title_full | A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| title_fullStr | A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| title_full_unstemmed | A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| title_short | A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| title_sort | machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults |
| topic | mild traumatic brain injury neurological deterioration machine learning predictive model XGBoost |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2024.1502153/full |
| work_keys_str_mv | AT daisuabe amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT motokiinaji amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takeshihase amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT eiichisuehiro amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT naotoshiomi amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hiroshiyatsushige amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shinhirota amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shuhasegawa amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hiroshikaribe amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT akihiromiyata amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT kenyakawakita amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT koheihaji amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hideoaihara amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shojiyokobori amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takeshimaeda amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takahiroonuki amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT kotarooshio amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT nobukazukomoribayashi amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT michiyasusuzuki amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT taketoshimaehara amachinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT daisuabe machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT motokiinaji machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takeshihase machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT eiichisuehiro machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT naotoshiomi machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hiroshiyatsushige machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shinhirota machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shuhasegawa machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hiroshikaribe machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT akihiromiyata machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT kenyakawakita machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT koheihaji machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT hideoaihara machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT shojiyokobori machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takeshimaeda machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT takahiroonuki machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT kotarooshio machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT nobukazukomoribayashi machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT michiyasusuzuki machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults AT taketoshimaehara machinelearningmodeltopredictneurologicaldeteriorationaftermildtraumaticbraininjuryinolderadults |