Cardiac Arrest, Patient Characteristics and Prognosis: a Machine Learning Approach

Background Cardiac arrest is a severe medical emergency with poor prognosis. This study aimed to analyze the clinical characteristics of cardiac arrest patients and explore the key factors influencing their outcomes. Additionally, we applied machine learning methods to evaluate the performance of different models in predicting return of spontaneous circulation (ROSC), with the goal of optimizing strategies for managing cardiac arrest.
Material and methods We comprehensively assessed the demographic characteristics, physiological parameters, and laboratory results of 748 cardiac arrest patients, and compared the differences between the ROSC and non-ROSC groups. We applied LASSO regression analysis to identify the key variables predictive of ROSC. Furthermore, we evaluated the performance of various machine learning models, including GBDT and LGBM, in ROSC prediction, including calibration, decision curve analysis, and ROC curves.
Results Patients in the ROSC group were younger and predominately male. They had more normal blood pressure, temperature, and oxygen saturation, as well as less severe organ dysfunction, LASSO regression analysis identified age, WBC, and lactate as key predictors of ROSC. Among the machine learning models, GBDT and LGBM exhibited the best performance, with superior alibration, decision curve analysis, and ROC curves compared.
Conclusions This study identified key clinical factors influencing the prognosis of cardiac arrest patients, and it identified machine learning models that were superior for predicting ROSC.

1. Bakhsh A, Bakhashwain W, Alhazmi M, Bahwireth S, Binmahfooz S, Alghamdi R et al. Fever Prevention and Neurological Recovery in In-Hospital Cardiac Arrest Survivors at a Limited-Resource Setting. Therapeutic Hypothermia and Temperature Management. 2025; [Epub ahead of print]. DOI: 10.1089/ther.2024.0051

2. Jakobsen LK, Kjærulf V, Bray J, Olasveengen TM, Folke F. Drones delivering automated external defibrillators for out-of-hospital cardiac arrest: A scoping review. Resuscitation Plus. 2025;21:100841. DOI: 10.1016/j.resplu.2024.100841

3. Jeong D, Tak Lee G, Eun Park J, Yeon Hwang S, Gun Shin T, Do Shin S et al. Severity of metabolic derangement predicts survival after out-of-hospital cardiac arrest and the likelihood of benefiting from extracorporeal life support. Emergencias. 2024;36(6):408–16. DOI: 10.55633/s3me/093.2024

4. Motta F, Cerrato M, De Giorgio D, Salimbeni A, Merigo G, Magliocca A et al. Translational approach to assess brain injury after cardiac arrest in preclinical models: a narrative review. Intensive Care Medicine Experimental. 2025;13(1):3. DOI: 10.1186/s40635-024-00710-y

5. Breuer-Kaiser AFC, Lefering R, Weber TP, Gräsner J-T, Wnent J. Use of CPR feedback devices to treat out-of-hospital cardiac arrest in Germany: Associated with improved ROSC-rates, but infrequent usage, in a registry-based analysis of 107,548 cases. Resuscitation. 2024;110453. [Epub ahead of print]. DOI: 10.1016/j.resuscitation.2024.110453

6. Caputo ML, Baldi E, Burkart R, Wilmes A, Cresta R, Benvenuti C et al. Validation of Utstein-Based score to predict return of spontaneous circulation (UB-ROSC) in patients with out-of-hospital cardiac arrest. Resuscitation. 2024;197:110113. DOI: 10.1016/j.resuscitation.2024.110113

7. Dombrowski A, Curtis K, Wisniewski S, Nichols J, Irish L, Almahameed S et al. Post-ROSC Atrial fibrillation is not associated with rearrest but is associated with stroke and mortality following out of hospital cardiac arrest. Resuscitation. 2024;201:110270. DOI: 10.1016/j.resuscitation.2024.110270

8. Hubble MW, Martin MD, Kaplan GR, Houston SE, Taylor SE. The Route to ROSC: Evaluating the Impact of Route and Timing of Epinephrine Administration in Out-of-Hospital Cardiac Arrest Outcomes. Prehospital Emergency Care. 2025;29(6):826–34. DOI: 10.1080/10903127.2024.2414389

9. Choi H-J, Lee C, Chun J, Seol R, Lee YM, Son Y-J. Development of a Predictive Model for Survival Over Time in Patients With Out-of-Hospital Cardiac Arrest Using Ensemble-Based Machine Learning. Computers, Informatics, Nursing. 2024;42(5):388–95. DOI: 10.1097/CIN.0000000000001145

10. Kim YK, Seo W-D, Lee SJ, Koo JH, Kim GC, Song HS et al. Early Prediction of Cardiac Arrest in the Intensive Care Unit Using Explainable Machine Learning: Retrospective Study. Journal of Medical Internet Research. 2024;26:e62890. DOI: 10.2196/62890

11. Soundararajan K, Adams DJ, Nathanson BH, Mader TJ, Godwin RC, Melvin RL et al. Use of machine learning models to predict neurologically intact survival for advanced age adults following out‐of‐hospital cardiac arrest. Academic Emergency Medicine. 2025;32(2):169–71. DOI: 10.1111/acem.15018

12. Wu W, Kor C, Chou M, Hsieh H, Huang W, Huang W et al. Prediction model of in‐hospital cardiac arrest using machine learning in the early phase of hospitalization. The Kaohsiung Journal of Medical Sciences. 2024;40(11):1029–35. DOI: 10.1002/kjm2.12895

13. Karatsu S, Hirano Y, Kondo Y, Okamoto K, Tanaka H. A Machine Learning Prediction Model for Non-cardiogenic Out-of-hospital Cardiac Arrest with Initial Non-shockable Rhythm. Juntendo Medical Journal. 2023;69(3):222–30. DOI: 10.14789/jmj.JMJ22-0035-OA

14. Lee H-Y, Kuo P-C, Qian F, Li C-H, Hu J-R, Hsu W-T et al. Prediction of In-Hospital Cardiac Arrest in the Intensive Care Unit: Machine Learning–Based Multimodal Approach. JMIR Medical Informatics. 2024;12:e49142. DOI: 10.2196/49142

15. Lee S, Lee K-S, Park S-H, Lee SW, Kim SJ. A Machine Learning-Based Decision Support System for the Prognostication of Neurological Outcomes in Successfully Resuscitated Out-of-Hospital Cardiac Arrest Patients. Journal of Clinical Medicine. 2024;13(24):7600. DOI: 10.3390/jcm13247600

16. Zheng X, Hu T, Liu T, Wang W. Simplified acute physiology score III is excellent for predicting in-hospital mortality in coronary care unit patients with acute myocardial infarction: A retrospective study. Frontiers in Cardiovascular Medicine. 2022;9:989561. DOI: 10.3389/fcvm.2022.989561

17. Kokulu K, Sert ET. The role of the lactate/albumin ratio in predicting survival outcomes in patients resuscitated after out-of-hospital cardiac arrest: A preliminary report. The American Journal of Emergency Medicine. 2021;50:670–4. DOI: 10.1016/j.ajem.2021.09.059

18. Kong T, Chung SP, Lee HS, Kim S, Lee J, Hwang SO et al. The Prognostic Usefulness of the Lactate/Albumin Ratio for Predicting Clinical Outcomes in Out-of-Hospital Cardiac Arrest: a Prospective, Multicenter Observational Study (koCARC) Study. Shock. 2020;53(4):442–51. DOI: 10.1097/SHK.0000000000001405

19. Beaulieu J, St-Onge M. Antidote use for cardiac arrest or hemodynamic instability due to cardiac glycoside poisoning: A narrative review. Resuscitation Plus. 2024;19:100690. DOI: 10.1016/j.resplu.2024.100690

20. Dogan B, Kudu E, Danış F, Ozturk Ince E, Karaca MA, Erbil B. Comparative Analysis of Perfusion Index and End-Tidal Carbon Dioxide in Cardiac Arrest Patients: Implications for Hemodynamic Monitoring and Resuscitation Outcomes. Cureus. 2023;15(2):e50818. DOI: 10.7759/cureus.50818

21. Linde L, Beske RP, Meyer MAS, Mølstrøm S, Grand J, Helgestad OKL et al. Hemodynamic Characteristics and Prognostic Implication of Modified Society for Cardiovascular Angiography and Interventions Shock Classification in Comatose Patients With Out‐of-Hospital Cardiac Arrest. Journal of the American Heart Association. 2025;14(1):e036659. DOI: 10.1161/JAHA.124.036659

22. Seppä AMJ, Skrifvars MB, Vuopio H, Raj R, Reinikainen M, Pekkarinen PT. Association of white blood cell count with one-year mortality after cardiac arrest. Resuscitation Plus. 2024;20:100816. DOI: 10.1016/j.resplu.2024.100816

23. Szarpak L, Kurek K, Tomaszewska M, Pruc M. Lactate-to-albumin ratio in predicting neurological outcomes in patients who have survived cardiac arrest. The American Journal of Emergency Medicine. 2024;85:260–1. DOI: 10.1016/j.ajem.2024.08.002

24. Xiao L, Li F, Sheng Y, Hou X, Liao X, Zhou P et al. Predictive value analysis of albumin-related inflammatory markers for short-term outcomes in patients with In-hospital cardiac arrest. Expert Review of Clinical Immunology. 2025;21(2):249–57. DOI: 10.1080/1744666X.2024.2399700

25. Xie Y, Wang R. Enhancing neurological prognosis prediction in cardiac arrest survivors: Insights from lactate-to-albumin ratio and cholesterol levels. The American Journal of Emergency Medicine. 2024;85:258–9. DOI: 10.1016/j.ajem.2024.07.058

26. Drkic T, Sljivo A, Ljuhar K, Palikuca A, Knezevic A, Karamehic E et al. Outcomes of Out-of-Hospital Cardiac Arrest with Initial Shockable Rhythm: The Role of Bystander and Dispatch-Guided CPR in Sarajevo’s Physician-Led Emergency Medical Teams. Materia Socio Medica. 2024;36(2):115–9. DOI: 10.5455/msm.2024.36.115-119

27. Simpson R, Dankiewicz J, Nielsen N, Pareek N, Keeble TR. Coronary artery disease and outcomes in Out of Hospital Cardiac arrest according to presenting rhythm − A post hoc analysis of the TTM-2 trial. Resuscitation. 2025;206:110457. DOI: 10.1016/j.resuscitation.2024.110457