Prediction of Prognosis in Patients with Trauma by Using Machine Learning

被引:2
作者
Lee, Kuo-Chang [1 ]
Hsu, Chien-Chin [1 ,2 ]
Lin, Tzu-Chieh [3 ]
Chiang, Hsiu-Fen [3 ]
Horng, Gwo-Jiun [3 ]
Chen, Kuo-Tai [1 ]
机构
[1] Chi Mei Med Ctr, Emergency Dept, Tainan 710402, Taiwan
[2] Southern Taiwan Univ Sci & Technol, Dept Biotechnol, Tainan 71005, Taiwan
[3] Southern Taiwan Univ Sci & Technol, Dept Comp Sci & Informat Engn, Tainan 71005, Taiwan
来源
MEDICINA-LITHUANIA | 2022年 / 58卷 / 10期
关键词
trauma; machine learning; prognostic predictor; mortality; trauma score; SURVIVAL;
D O I
10.3390/medicina58101379
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background and Objectives: We developed a machine learning algorithm to analyze trauma-related data and predict the mortality and chronic care needs of patients with trauma. Materials and Methods: We recruited admitted patients with trauma during 2015 and 2016 and collected their clinical data. Then, we subjected this database to different machine learning techniques and chose the one with the highest accuracy by using cross-validation. The primary endpoint was mortality, and the secondary endpoint was requirement for chronic care. Results: Data of 5871 patients were collected. We then used the eXtreme Gradient Boosting (xGBT) machine learning model to create two algorithms: a complete model and a short-term model. The complete model exhibited an 86% recall for recovery, 30% for chronic care, 67% for mortality, and 80% for complications; the short-term model fitted for ED displayed an 89% recall for recovery, 25% for chronic care, and 41% for mortality. Conclusions: We developed a machine learning algorithm that displayed good recall for the healthy recovery group but unsatisfactory results for those requiring chronic care or having a risk of mortality. The prediction power of this algorithm may be improved by implementing features such as age group classification, severity selection, and score calibration of trauma-related variables.
引用
收藏
页数:9
相关论文
共 22 条
  • [11] MACHINE LEARNING FOR PREDICTING OUTCOMES IN TRAUMA
    Liu, Nehemiah T.
    Salinas, Jose
    [J]. SHOCK, 2017, 48 (05): : 504 - 510
  • [12] Ministry of Health and Welfare, 2019, STAT PUBL STAT CAUS
  • [13] Statistical Machines for Trauma Hospital Outcomes Research: Application to the PRospective, Observational, Multi-Center Major Trauma Transfusion (PROMMTT) Study
    Moore, Sara E.
    Decker, Anna
    Hubbard, Alan
    Callcut, Rachael A.
    Fox, Erin E.
    del Junco, Deborah J.
    Holcomb, John B.
    Rahbar, Mohammad H.
    Wade, Charles E.
    Schreiber, Martin A.
    Alarcon, Louis H.
    Brasel, Karen J.
    Bulger, Eileen M.
    Cotton, Bryan A.
    Muskat, Peter
    Myers, John G.
    Phelan, Herb A.
    Cohen, Mitchell J.
    [J]. PLOS ONE, 2015, 10 (08):
  • [14] Mortality prediction in pediatric trauma
    Muisyo, Teddy
    Bernardo, Erika O.
    Camazine, Maraya
    Colvin, Ryan
    Thomas, Kimberly A.
    Borgman, Matthew A.
    Spinella, Philip C.
    [J]. JOURNAL OF PEDIATRIC SURGERY, 2019, 54 (08) : 1613 - 1616
  • [15] Validation of the Taiwan triage and acuity scale: a new computerised five-level triage system
    Ng, Chip-Jin
    Yen, Zui-Shen
    Tsai, Jeffrey Che-Hung
    Chen, Li Chin
    Lin, Shou Ju
    Sang, Yiing Yiing
    Chen, Jih-Chang
    [J]. EMERGENCY MEDICINE JOURNAL, 2011, 28 (12) : 1026 - 1031
  • [16] Using artificial intelligence to predict prolonged mechanical ventilation and tracheostomy placement
    Parreco, Joshua
    Hidalgo, Antonio
    Parks, Jonathan J.
    Kozol, Robert
    Rattan, Rishi
    [J]. JOURNAL OF SURGICAL RESEARCH, 2018, 228 : 179 - 187
  • [17] Pedregosa F, 2011, J MACH LEARN RES, V12, P2825
  • [18] Rau Cheng-Shyuan, 2018, PLoS One, V13, pe0207192, DOI 10.1371/journal.pone.0207192
  • [19] Survival prediction of trauma patients: a study on US National Trauma Data Bank
    Sefrioui, I.
    Amadini, R.
    Mauro, J.
    El Fallahi, A.
    Gabbrielli, M.
    [J]. EUROPEAN JOURNAL OF TRAUMA AND EMERGENCY SURGERY, 2017, 43 (06) : 805 - 822
  • [20] A comparative study on machine learning based algorithms for prediction of motorcycle crash severity
    Wahab, Lukuman
    Jiang, Haobin
    [J]. PLOS ONE, 2019, 14 (04):