Prediction of Spontaneous Circulation Recovery in Out-of-Hospital Cardiac Arrest Cardiopulmonary Resuscitation Patients Using Machine Learning Algorithms

Authors

  • Wentao Li Emergency Department, The First Hospital of Hebei Medical University, NO.89 Donggang Road, Shijiazhuang, Hebei province, China, 050031
  • Jiaqi Zhang Emergency Department, The First Hospital of Hebei Medical University, NO.89 Donggang Road, Shijiazhuang, Hebei province, China, 050031
  • Lu Zhang Emergency Department, The First Hospital of Hebei Medical University, NO.89 Donggang Road, Shijiazhuang, Hebei province, China, 050031
  • Yingjie Nie Emergency Department, The First Hospital of Hebei Medical University, NO.89 Donggang Road, Shijiazhuang, Hebei province, China, 050031
  • Ying Chen* Emergency Department, The First Hospital of Hebei Medical University, NO.89 Donggang Road, Shijiazhuang, Hebei province, China, 050031 https://orcid.org/0000-0001-8490-5672

Keywords:

Machine learning, Forecast, Out-of-hospital cardiac arrest

Abstract

Background: Machine learning algorithms have proven a highly efficient means of processing medical data, but there is little research on such prediction models for the cardiopulmonary resuscitation(CPR) outcomes of in out-of-hospital cardiac arrest (OHCA) patients.

Objectives: In this study, we want to develop a machine learning algorithm for the prediction of spontaneous circulation recovery in OHCA patients, and which will provide data support for the improvement of CPR success rates in OHCA patients.

Methods: We identified 463 patients who had undergone CPR following OHCA. The 75% data of the cases were used in training set to establish the model, and 25% were used as a test set for model verification. The performance of the models was evaluated by the area under a receiver operating characteristic curve and the predictive accuracy.

Results: The area under the curve values for the logistic regression, random forest, parameter interpretation, and gradient boosting models were 0.73, 0.87,0.90, and 0.86, respectively. Using the random forest model to calculate the importance of each characteristic value, we concluded that the main predictors of spontaneous circulation recovery in OHCA patients are age, speed of CPR initiation, history of cardiopulmonary conditions, another person is present when cardiac arrest occurs, chest compressions and defibrillation.

Conclusions: Machine learning has the potential to predict the recovery of spontaneous circulation in OHCA patients. A Random Forest model was found to provide the most accurate predictions. This can be used to provide data support and as a reference source to improve the success rate of CPR.

Downloads

Published

2024-12-30

Issue

Vol. 94 No. 6 (2024): Volume 94, Issue 6

Section

Original Articles

How to Cite

Li, Wentao, Jiaqi Zhang, Lu Zhang, Yingjie Nie, and Ying Chen* , trans. 2024. “Prediction of Spontaneous Circulation Recovery in Out-of-Hospital Cardiac Arrest Cardiopulmonary Resuscitation Patients Using Machine Learning Algorithms”. Human Biology 94 (6): 927-34. https://www.humbiol.org/Home/article/view/223.

Most read articles by the same author(s)

<< < 1 2 3 4 5 6 7 > >>