Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury

被引:2
|
作者
Tu, Kuan-Chi [1 ]
Tau, Eric Nyam Tee [1 ]
Chen, Nai-Ching [2 ]
Chang, Ming-Chuan [2 ]
Yu, Tzu-Chieh [2 ]
Wang, Che-Chuan [1 ,3 ]
Liu, Chung-Feng [4 ]
Kuo, Ching-Lung [1 ,3 ,5 ]
机构
[1] Chi Mei Med Ctr, Dept Neurosurg, Tainan 710402, Taiwan
[2] Chi Mei Med Ctr, Dept Nursing, Tainan 710402, Taiwan
[3] Southern Taiwan Univ Sci & Technol, Ctr Gen Educ, Tainan 710402, Taiwan
[4] Chi Mei Med Ctr, Dept Med Res, Tainan, Taiwan
[5] Natl Sun Yat sen Univ, Coll Med, Sch Med, Kaohsiung 804, Taiwan
关键词
artificial intelligence; machine learning; traumatic brain injury; mortality; intensive care unit; computer-assisted system; PROGNOSTIC MODELS; ACCURACY; SEVERITY; SEPSIS;
D O I
10.3390/diagnostics13183016
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Numerous mortality prediction tools are currently available to assist patients with moderate to severe traumatic brain injury (TBI). However, an algorithm that utilizes various machine learning methods and employs diverse combinations of features to identify the most suitable predicting outcomes of brain injury patients in the intensive care unit (ICU) has not yet been well-established. Method: Between January 2016 and December 2021, we retrospectively collected data from the electronic medical records of Chi Mei Medical Center, comprising 2260 TBI patients admitted to the ICU. A total of 42 features were incorporated into the analysis using four different machine learning models, which were then segmented into various feature combinations. The predictive performance was assessed using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and validated using the Delong test. Result: The AUC for each model under different feature combinations ranged from 0.877 (logistic regression with 14 features) to 0.921 (random forest with 22 features). The Delong test indicated that the predictive performance of the machine learning models is better than that of traditional tools such as APACHE II and SOFA scores. Conclusion: Our machine learning training demonstrated that the predictive accuracy of the LightGBM is better than that of APACHE II and SOFA scores. These features are readily available on the first day of patient admission to the ICU. By integrating this model into the clinical platform, we can offer clinicians an immediate prognosis for the patient, thereby establishing a bridge for educating and communicating with family members.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] Posttraumatic epilepsy in intensive care unit-treated pediatric traumatic brain injury patients
    Mikkonen, Era D.
    Skrifvars, Markus B.
    Reinikainen, Matti
    Bendel, Stepani
    Laitio, Ruut
    Hoppu, Sanna
    Ala-Kokko, Tero
    Karppinen, Atte
    Raj, Rahul
    EPILEPSIA, 2020, 61 (04) : 693 - 701
  • [22] Prediction of Mortality in Geriatric Traumatic Brain Injury Patients Using Machine Learning Algorithms
    Wang, Ruoran
    Zeng, Xihang
    Long, Yujuan
    Zhang, Jing
    Bo, Hong
    He, Min
    Xu, Jianguo
    BRAIN SCIENCES, 2023, 13 (01)
  • [23] Alcohol and Risk of Mortality in Patients With Traumatic Brain Injury
    Shandro, Jamie R.
    Rivara, Frederick P.
    Wang, Jin
    Jurkovich, Gregory J.
    Nathens, Avery B.
    MacKenzie, Ellen J.
    JOURNAL OF TRAUMA-INJURY INFECTION AND CRITICAL CARE, 2009, 66 (06): : 1584 - 1590
  • [24] Effect of antiplatelet and anticoagulant medication use on injury severity and mortality in patients with traumatic brain injury treated in the intensive care unit
    Vehvilainen, Juho
    Virta, Jyri J.
    Skrifvars, Markus B.
    Reinikainen, Matti
    Bendel, Stepani
    Ala-Kokko, Tero
    Hoppu, Sanna
    Laitio, Ruut
    Siironen, Jari
    Raj, Rahul
    ACTA NEUROCHIRURGICA, 2023, 165 (12) : 4003 - 4012
  • [25] Thrombocytopenia: A Risk Factor of Mortality for Patients with Sepsis in the Intensive Care Unit
    Burunsuzoglu, Bunyamin
    Salturk, Cuneyt
    Karakurt, Zuhal
    Ongel, Esra Akkutuk
    Takir, Huriye Berk
    Kargin, Feyza
    Horzum, Gulbanu
    Balci, Merih
    Mocin, Ozlem
    Adiguzel, Nalan
    Gungor, Gokay
    Yilmaz, Adnan
    TURKISH THORACIC JOURNAL, 2016, 17 (01): : 7 - 14
  • [26] Effect of antiplatelet and anticoagulant medication use on injury severity and mortality in patients with traumatic brain injury treated in the intensive care unit
    Juho Vehviläinen
    Jyri J. Virta
    Markus B. Skrifvars
    Matti Reinikainen
    Stepani Bendel
    Tero Ala-Kokko
    Sanna Hoppu
    Ruut Laitio
    Jari Siironen
    Rahul Raj
    Acta Neurochirurgica, 2023, 165 : 4003 - 4012
  • [27] Mortality Prediction in Severe Traumatic Brain Injury Using Traditional and Machine Learning Algorithms
    Wu, Xiang
    Sun, Yuyao
    Xu, Xiao W.
    Steyerberg, Ewout
    Helmrich, Isabel R. A. Retel
    Lecky, Fiona
    Guo, Jianying
    Li, Xiang
    Feng, Junfeng
    Mao, Qing
    Xie, Guotong
    Maas, Andrew I. R.
    Gao, Guoyi
    Jiang, Jiyao
    JOURNAL OF NEUROTRAUMA, 2023, 40 (13-14) : 1366 - 1375
  • [28] Machine Learning for Acute Kidney Injury Prediction in the Intensive Care Unit
    Gottlieb, Eric R.
    Samuel, Mathew
    Bonventre, Joseph V.
    Celi, Leo A.
    Mattie, Heather
    ADVANCES IN CHRONIC KIDNEY DISEASE, 2022, 29 (05) : 431 - 438
  • [29] Machine Learning to Predict In-Hospital Morbidity and Mortality after Traumatic Brain Injury
    Matsuo, Kazuya
    Aihara, Hideo
    Nakai, Tomoaki
    Morishita, Akitsugu
    Tohma, Yoshiki
    Kohmura, Eiji
    JOURNAL OF NEUROTRAUMA, 2019, : 202 - 210
  • [30] A predictive model for the risk of sepsis within 30 days of admission in patients with traumatic brain injury in the intensive care unit: a retrospective analysis based on MIMIC-IV database
    Hu, Fangqi
    Zhu, Jiaqiu
    Zhang, Sheng
    Wang, Cheng
    Zhang, Liangjia
    Zhou, Hui
    Shi, Hui
    EUROPEAN JOURNAL OF MEDICAL RESEARCH, 2023, 28 (01)