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
  • [31] The Intensive Care Unit Experience: Psychological Impact on Family Members of Patients With and Without Traumatic Brain Injury
    Warren, Ann Marie
    Rainey, Evan Elizabeth
    Weddle, Rebecca Joanne
    Bennett, Monica
    Roden-Foreman, Kenleigh
    Foreman, Michael L.
    REHABILITATION PSYCHOLOGY, 2016, 61 (02) : 179 - 185
  • [32] Burden and Psychological Distress of Intensive Care Unit Caregivers of Traumatic Brain Injury Patients
    Kanmani, Thiruchengodu Raju
    Thimmappur, Ramappa M.
    Birudu, Raju
    Reddy, Krishna N.
    Raj, Prabhu
    INDIAN JOURNAL OF CRITICAL CARE MEDICINE, 2019, 23 (05) : 220 - 223
  • [33] Anti-seizure prophylaxis in critically ill patients with traumatic brain injury in an intensive care unit
    Sundararajan, K.
    Milne, D.
    Edwards, S.
    Chapman, M. J.
    Shakib, S.
    ANAESTHESIA AND INTENSIVE CARE, 2015, 43 (05) : 646 - 651
  • [34] A New Risk Model based on the Machine Learning Approach for Prediction of Mortality in the Respiratory Intensive Care Unit
    Yan, Peng
    Huang, Siwan
    Li, Ye
    Chen, Tiange
    Li, Xiang
    Zhang, Yuan
    Wu, Huan
    Xu, Jianqiao
    Xie, Guotong
    Xie, Lixin
    Mo, Guoxin
    CURRENT PHARMACEUTICAL BIOTECHNOLOGY, 2023, 24 (13) : 1673 - 1681
  • [35] Predictive Modeling and Integrated Risk Assessment of Postoperative Mortality and Pneumonia in Traumatic Brain Injury Patients through Clustering and Machine Learning: Retrospective Study
    Kim, Jong-Ho
    Chung, Kyung-Min
    Lee, Jae-Jun
    Choi, Hyuk-Jai
    Kwon, Young-Suk
    BIOMEDICINES, 2023, 11 (11)
  • [36] Machine Learning for Early Prediction of Sepsis in Intensive Care Unit (ICU) Patients
    Alanazi, Abdullah
    Aldakhil, Lujain
    Aldhoayan, Mohammed
    Aldosari, Bakheet
    MEDICINA-LITHUANIA, 2023, 59 (07):
  • [37] Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure
    Chen, Zijun
    Li, Tingming
    Guo, Sheng
    Zeng, Deli
    Wang, Kai
    FRONTIERS IN CARDIOVASCULAR MEDICINE, 2023, 10
  • [38] Novel pneumonia score based on a machine learning model for predicting mortality in pneumonia patients on admission to the intensive care unit
    Wang, Bin
    Li, Yuanxiao
    Tian, Ying
    Ju, Changxi
    Xu, Xiaonan
    Pei, Shufen
    RESPIRATORY MEDICINE, 2023, 217
  • [39] One-year costs of intensive care in pediatric patients with traumatic brain injury
    Mikkonen, Era D.
    Skrifvars, Markus B.
    Reinikainen, Matti
    Bendel, Stepani
    Laitio, Ruut
    Hoppu, Sanna
    Ala-Kokko, Tero
    Karppinen, Atte
    Raj, Rahul
    JOURNAL OF NEUROSURGERY-PEDIATRICS, 2021, 27 (01) : 79 - 86
  • [40] Development of a machine learning model for the prediction of the short-term mortality in patients in the intensive care unit
    Yang, Jaeyoung
    Lim, Hong-Gook
    Park, Wonhyeong
    Kim, Dongseok
    Yoon, Jin Sun
    Lee, Sang-Min
    Kim, Kwangsoo
    JOURNAL OF CRITICAL CARE, 2022, 71