神戸大学附属図書館デジタルアーカイブ
入力補助
English
カテゴリ
学内刊行物
ランキング
アクセスランキング
ダウンロードランキング
https://hdl.handle.net/20.500.14094/90007880
このアイテムのアクセス数:
7
件
(
2024-04-20
22:49 集計
)
閲覧可能ファイル
ファイル
フォーマット
サイズ
閲覧回数
説明
90007880 (fulltext)
pdf
68.2 MB
53
メタデータ
ファイル出力
メタデータID
90007880
アクセス権
open access
出版タイプ
Accepted Manuscript
タイトル
Machine Learning to Predict In-Hospital Morbidity and Mortality after Traumatic Brain Injury
著者
Matsuo, Kazuya ; Aihara, Hideo ; Nakai, Tomoaki ; Morishita, Akitsugu ; Tohma, Yoshiki ; Kohmura, Eiji
著者名
Matsuo, Kazuya
著者名
Aihara, Hideo
著者ID
A1534
研究者ID
1000060596089
KUID
https://kuid-rm-web.ofc.kobe-u.ac.jp/search/detail?systemId=c0c1e75c520f6e63520e17560c007669
著者名
Nakai, Tomoaki
中井, 友昭
ナカイ, トモアキ
所属機関名
医学研究科
著者名
Morishita, Akitsugu
著者名
Tohma, Yoshiki
著者ID
A0460
研究者ID
1000030225388
著者名
Kohmura, Eiji
甲村, 英二
コウムラ, エイジ
所属機関名
大学院医学研究科 医科学専攻
収録物名
Journal of Neurotrauma
巻(号)
37(1)
ページ
202-210
出版者
Mary Ann Liebert
刊行日
2019-12-11
公開日
2021-03-02
抄録
Recently, successful predictions using machine learning (ML) algorithms have been reported in various fields. However, in traumatic brain injury (TBI) cohorts, few studies have examined modern ML algorithms. To develop a simple ML model for TBI outcome prediction, we conducted a performance comparison of nine algorithms: ridge regression, least absolute shrinkage and selection operator (LASSO) regression, random forest, gradient boosting, extra trees, decision tree, Gaussian naïve Bayes, multi-nomial naïve Bayes, and support vector machine. Fourteen feasible parameters were introduced in the ML models, including age, Glasgow Coma Scale (GCS), systolic blood pressure (SBP), abnormal pupillary response, major extracranial injury, computed tomography (CT) findings, and routinely collected laboratory values (glucose, C-reactive protein [CRP], and fibrin/fibrinogen degradation products [FDP]). Data from 232 patients with TBI were randomly divided into a training sample (80%) for hyperparameter tuning and validation sample (20%). The bootstrap method was used for validation. Random forest demonstrated the best performance for in-hospital poor outcome prediction and ridge regression for in-hospital mortality prediction: the mean statistical measures were 100% sensitivity, 72.3% specificity, 91.7% accuracy, and 0.895 area under the receiver operating characteristic curve (AUC); and 88.4% sensitivity, 88.2% specificity, 88.6% accuracy, and 0.875 AUC, respectively. Based on the feature selection method using the tree-based ensemble algorithm, age, Glasgow Coma Scale, fibrin/fibrinogen degradation products, and glucose were identified as the most important prognostic factors for poor outcome and mortality. Our results indicate the relatively good predictive performance of modern ML for TBI outcome. Further external validation is required for more heterogeneous samples to confirm our results.
キーワード
artificial intelligence
machine learning
outcome predictor
traumatic brain injury
カテゴリ
医学研究科
学術雑誌論文
権利
This is the accepted version of the following article: Machine Learning to Predict In-Hospital Morbidity and Mortality after Traumatic Brain Injury. Kazuya Matsuo, Hideo Aihara, Tomoaki Nakai, Akitsugu Morishita, Yoshiki Tohma, and Eiji Kohmura. Journal of Neurotrauma. Jan 2020. 202-210., which has now been formally published in final form at Journal of Neurotrauma at https://doi.org/10.1089/neu.2018.6276. This original submission version of the article may be used for non-commercial purposes in accordance with the Mary Ann Liebert, Inc., publishers’ self-archiving terms and conditions.
詳細を表示
資源タイプ
journal article
言語
English (英語)
ISSN
0897-7151
OPACで所蔵を検索
CiNiiで学外所蔵を検索
eISSN
1557-9042
OPACで所蔵を検索
CiNiiで学外所蔵を検索
関連情報
DOI
https://doi.org/10.1089/neu.2018.6276
ホームへ戻る