|
|
|
| Prediction of spontaneous circulatory recovery in patients with cardiopulmonary resuscitation after out-of-hospital cardiac arrest based on machine learning algorithm |
| CHEN Ying1 ZHANG Jiaqi1 TIAN Jiangtao2 NIE Yingjie1 LI Ruiyue1 HAO Meilin1 LI Wentao1 ZHANG Yingqi1▲ |
1.Department of Emergency, the First Hospital of Hebei Medical University, Hebei Province, Shijiazhuang 050030, China;
2.China Mobile Communications Group Hebei Co., LTD, Hebei Province, Shijiazhuang 050011, China |
|
|
|
|
Abstract Objective To predict the recovery of spontaneous circulation in patients with out-of-hospital cardiac arrest and cardiopulmonary resuscitation (CPR) by machine learning algorithm, so as to provide data support for improving the success rate of CPR in patients with out-of-hospital cardiac arrest. Methods From the medical records of 1 201 patients with cardiac arrest and CPR in the emergency patient database (EPD) of Hebei Provincial Emergency Technology Innovation Center from September 2018 to April 2022, 463 patients with out-of-hospital cardiac arrest were screened out. The data were preprocessed with python language pandas and combined with clinical characteristics. The 14 variables with the highest accuracy were determined. 75% of the samples were divided into training sets to build a model, and four machine learning algorithms including logistic regression, parameter interpretation, gradient lifting, and random forest were used to train and test the data. 25% of the samples were divided into test sets for verification. The model performance was evaluated according to accuracy, accuracy, recall, receiver characteristic operating characteristic curve (ROC), etc., and the appropriate model was selected for influencing factor analysis. Results There were statistically significant differences in age, CPR start time, history of electrolyte disturbance, witness of cardiac arrest, CPR, defibrillation, and airway management using simple respirator between the return of spontaneous circulation(ROSC) group(57 cases) and failed group(406 cases) (P＜0.05). The area under the curve (AUC) values of logistic regression, random forest, parameter interpretation, and gradient lifting were 0.73, 0.87, 0.90, and 0.86, respectively. The random forest model (accuracy=0.89, accuracy=0.90, recall=0.89, AUC=0.87) was selected to calculate the importance of each characteristic value. The results showed that the main factors affecting the recovery of spontaneous circulation in patients with out-of-hospital cardiac arrest were age, start time of CPR, previous history, witnessing cardiac arrest, giving external chest compression, and electrical defibrillation. Conclusion Machine learning has the potential to predict spontaneous circulatory recovery in patients with out-of-hospital cardiac arrest and CPR, and the random forest model works best.
|
|
|
|
|
|
[1] Nanayakkara S，Fogarty S，Tremeer M，et al. Characterising risk of in-hospital mortality following cardiac arrest using machine learning：A retrospective int-ernational registry study [J]. PLoS Med，2018，15（11）：e1002709.
[2] Chen L，Han Z，Wang J，et al. The emerging roles of machine learning in cardiovascular diseases：a narrative review [J]. Ann Transl Med，2022，10（10）：611.
[3] Lu H，Yao Y，Wang L，et al. Research Progress of Machine Learning and Deep Learning in Intelligent Diagnosis of the Coronary Atherosclerotic Heart Disease [J]. Comput Math Methods Med，2022，2022：3016532.
[4] Bujak K，Nadolny K，Ladny IR，et al. Epidemiology，management，and survival rate of out of hospital cardiac arrest in Upper Silesia, Poland：an Utstein-style report [J]. Postepy Kardiol Interwencyjnej，2021，17（4）：366-375.
[5] Chen N，Callaway CW，Guyette FX，et al.Arrest etiology among patients resuscitated from cardiac arrest [J]. Resuscitation，2018，130：33-40.
[6] Cummins DA，Abramson NS，Eisenberg MS，et al. Recommended guidelines for uniform reporting of data from out-of-hospital cardiac arrest：the Utstein Style [J]. CIRCULATION，1991，84（2）：960-975.
[7] Perkins G，Jacobs I，Nadkarni V，et al. Cardiac Arrest and Cardiopulmonary Resuscitation Outcome Reports：Update of the Utstein Resuscitation Registry Templates for Out-of- Hospital Cardiac Arrest [J]. Resuscitation，2015，96：328-340.
[8] Namrata P，Sargam G. Data Pre-Processing for Machine Lear- ning Models using Python Libraries [J]. Int J Eng Adv Technol，2022，9（4）：1995-1999.
[9] De Velasco Oriol J，Vallej E，Estrada K，et al. Benchmarking machine learning models for late-onset alzheimer's disease prediction from genomic data [J]. BMC Bioinformatics，2019，20（1）：709.
[10] Nghia H. Machine Learning-based Prediction Models for Diagnosis and Prognosis in Inflammatory Bowel Diseases：A Systematic Review [J]. J Crohns Colitis，2022，16（3）：398- 413.
[11] Suzuki S. Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis [J]. PLoS One，2019，14（9）：p.e0221911.
[12] Yamashita T，Sakama T，Neumar，et al. Part 1：Executive Summary：2015 American Heart Association Guidelines Update for Cardiopulmonary Resuscitation and Emergency Car- diovascular Care [J]. Circulation，2015，132（18 Suppl 2）：S315-67.
[13] Kleinman M. 2017 American Heart Association Focused Update on Adult Basic Life Support and Cardiopulmonary Resuscitation Quality [J]. Circulation，2018，137（1）：e7- e13.
[14] Kotini-Shah P，Del Rios M，Khosla S，et al. Sex differences in outcomes for out-of-hospital cardiac arrest in the United States [J]. Resuscitation，2021，163：6-13.
[15] McNally B，Robb R，Mehta M，et al. Out-of-hospital cardiac arrest surveillance Cardiac Arrest Registry to Enhance Survival（CARES） [J]. United States：MMWR Surveill Summ，2011，60（8）：1-19.
[16] 张瑛琪，张帆，高原，等.625名在职护士心肺复苏培训1年前后技术掌握情况的调查分析[J].中国中西医结合急救杂志，2021，38（5）：606-609.
[17] 张瑛琪，高原，褚晨晨，等.住培医师心肺复苏技能掌握情况分析及思考[J].中国继续医学教育，2021，13（35）：68-72.
[18] 靳贝贝，张瑛琪.河北省非医务人员心肺复苏认知度的调查与分析[J].中国急救复苏与灾害医学杂志，2021， 16（12）：1357-1361.
[19] 韩彩莉，高原，张帆，等.1607名在职护理人员心肺复苏知识掌握现状调查与影响因素分析[J].中国急救复苏与灾害医学杂志，2022，17（3）：406-409.
[20] Bougouin W. Extracorporeal cardiopulmonary resuscitation in out-of-hospital cardiac arrest：a registry study [J]. Eur Heart J，2020，41（21）：1961-1971.
[21] McMullan J，Gerecht R，Bonomo J，et al. Airway management and out-of-hospital cardiac arrest outcome in the CARES registry [J]. Resuscitation，2014，85（5）：617-622.
[22] Gr?覿sner JT，Lefering R，Koster RW，et al. EuReCa ONE-27 Nations，ONE Europe，ONE Registry：A prospective one month analysis of out-of-hospital cardiac arrest outcomes in 27 countries in Europe [J]. Resuscitation，2016，105：188- 195.
[23] 中国研究型医院学会心肺复苏学专业委员会.《中国心肺复苏专家共识》之腹部提压心肺复苏临床操作指南[J].中华危重病急救医学，2019（4）：385-389.
[24] 王立祥，宋维，张思森，等.腹部提压心肺复苏多中心临床实验报告[J].中华急诊医学杂志，2017（3）：333-336.
[25] 詹峰，宋维，张君，等.腹部提压心肺复苏临床效果分析[J].中华危重病急救医学，2019（2）：228-231. |
|
|
|
