The Clinical Application of Machine Learning-Based Models for Early Prediction of Hemorrhage in Trauma Intensive Care Units

被引:8
作者
Lee, Shih-Wei [1 ]
Kung, His-Chun [2 ]
Huang, Jen-Fu [2 ]
Hsu, Chih-Po [2 ]
Wang, Chia-Cheng [2 ]
Wu, Yu-Tung [2 ]
Wen, Ming-Shien [3 ]
Cheng, Chi-Tung [2 ]
Liao, Chien-Hung [2 ]
机构
[1] Chang Gung Mem Hosp, Dept Gen Surg, Taoyuan 333, Taiwan
[2] Chang Gung Univ, Chang Gung Mem Hosp, Linkou Med Ctr, Dept Trauma & Emergency Surg, Taoyuan 333, Taiwan
[3] Chang Gung Univ, Chang Gung Mem Hosp, Coll Med, Dept Cardiol, Taoyuan 333, Taiwan
关键词
machine learning; intensive care unit; traumatic hemorrhage; prediction; MASSIVE TRANSFUSION; HOSPITAL MORTALITY; SYSTEM; BLOOD; NEED;
D O I
10.3390/jpm12111901
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Uncontrolled post-traumatic hemorrhage is an important cause of traumatic mortality that can be avoided. This study intends to use machine learning (ML) to build an algorithm based on data collected from an electronic health record (EHR) system to predict the risk of delayed bleeding in trauma patients in the ICU. We enrolled patients with torso trauma in the surgical ICU. Demographic features, clinical presentations, and laboratory data were collected from EHR. The algorithm was designed to predict hemoglobin dropping 6 h before it happened and evaluated the performance with 10-fold cross-validation. We collected 2218 cases from 2008 to 2018 in a trauma center. There were 1036 (46.7%) patients with positive hemorrhage events during their ICU stay. Two machine learning algorithms were used to predict ongoing hemorrhage events. The logistic model tree (LMT) and the random forest algorithm achieved an area under the curve (AUC) of 0.816 and 0.809, respectively. In this study, we presented the ML model using demographics, vital signs, and lab data, promising results in predicting delayed bleeding risk in torso trauma patients. Our study also showed the possibility of an early warning system alerting ICU staff that trauma patients need re-evaluation or further survey.
引用
收藏
页数:10
相关论文
共 26 条
[1]   A Conformation Variant of p53 Combined with Machine Learning Identifies Alzheimer Disease in Preclinical and Prodromal Stages [J].
Abate, Giulia ;
Vezzoli, Marika ;
Polito, Letizia ;
Guaita, Antonio ;
Albani, Diego ;
Marizzoni, Moira ;
Garrafa, Emirena ;
Marengoni, Alessandra ;
Forloni, Gianluigi ;
Frisoni, Giovanni B. ;
Cummings, Jeffrey L. ;
Memo, Maurizio ;
Uberti, Daniela .
JOURNAL OF PERSONALIZED MEDICINE, 2021, 11 (01) :1-16
[2]   Predicting hospital mortality for intensive care unit patients: Time-series analysis [J].
Awad, Aya ;
Bader-El-Den, Mohamed ;
McNicholas, James ;
Briggs, Jim ;
El-Sonbaty, Yasser .
HEALTH INFORMATICS JOURNAL, 2020, 26 (02) :1043-1059
[3]  
Badnjevic A, 2021, PSYCHIAT DANUB, V33, P101
[4]   Use of Advanced Machine-Learning Techniques for Noninvasive Monitoring of Hemorrhage [J].
Convertino, Victor A. ;
Moulton, Steven L. ;
Grudic, Gregory Z. ;
Rickards, Caroline A. ;
Hinojosa-Laborde, Carmen ;
Gerhardt, Robert T. ;
Blackbourne, Lorne H. ;
Ryan, Kathy L. .
JOURNAL OF TRAUMA-INJURY INFECTION AND CRITICAL CARE, 2011, 71 :S25-S32
[5]   Elevated C-reactive protein levels at ICU discharge as a predictor of ICU outcome: a retrospective cohort study [J].
Gulcher, S. Sophie ;
Bruins, Nynke A. ;
Kingma, W. Peter ;
Boerma, E. Christiaan .
ANNALS OF INTENSIVE CARE, 2016, 6 :1-8
[6]   Artificial Intelligence in the Intensive Care Unit [J].
Gutierrez, Guillermo .
CRITICAL CARE, 2020, 24 (01)
[7]   Predicting Complications in Critical Care Using Heterogeneous Clinical Data [J].
Huddar, Vijay ;
Desiraju, Bapu Koundinya ;
Rajan, Vaibhav ;
Bhattacharya, Sakyajit ;
Roy, Shourya ;
Reddy, Chandan K. .
IEEE ACCESS, 2016, 4 :7988-8001
[8]   Prediction of sepsis patients using machine learning approach: A meta-analysis [J].
Islam, Md. Mohaimenul ;
Nasrin, Tahmina ;
Walther, Bruno Andreas ;
Wu, Chieh-Chen ;
Yang, Hsuan-Chia ;
Li , Yu-Chuan .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2019, 170 :1-9
[9]   A deep learning model for real-time mortality prediction in critically ill children [J].
Kim, Soo Yeon ;
Kim, Saehoon ;
Cho, Joongbum ;
Kim, Young Suh ;
Sol, In Suk ;
Sung, Youngchul ;
Cho, Inhyeok ;
Park, Minseop ;
Jang, Haerin ;
Kim, Yoon Hee ;
Kim, Kyung Won ;
Sohn, Myung Hyun .
CRITICAL CARE, 2019, 23 (01)
[10]   Frequency of Passive EHR Alerts in the ICU: Another Form of Alert Fatigue? [J].
Kizzier-Carnahan, Vanessa ;
Antis, Kathryn A. ;
Mohan, Vishnu ;
Gold, Jeffrey A. .
JOURNAL OF PATIENT SAFETY, 2019, 15 (03) :246-250