Machine Learning and Clinical Predictors of Mortality in Cardiac Arrest Patients: A Comprehensive Analysis

Overview

Journal Med Sci Monit

Specialties General Medicine
Pathology

Date 2024 Aug 10

PMID 39126147

Authors

Lukasz Lewandowski

Michal Czapla

Izabella Uchmanowicz

Grzegorz Kubielas

Stanislaw Zielinski

Malgorzata Krzystek-Korpacka

Catherine Ross

Raul Juarez-Vela

Marzena Zielinska

Affiliations

Soon will be listed here.

Abstract

BACKGROUND Cardiac arrest (CA) is a global public health challenge. This study explored the predictors of mortality and their interactions utilizing machine learning algorithms and their related mortality odds among patients following CA. MATERIAL AND METHODS The study retrospectively investigated 161 medical records of CA patients admitted to the Intensive Care Unit (ICU). The random forest classifier algorithm was used to assess the parameters of mortality. The best classification trees were chosen from a set of 100 trees proposed by the algorithm. Conditional mortality odds were investigated with the use of logistic regression models featuring interactions between variables. RESULTS In the logistic regression model, male sex was associated with 5.68-fold higher mortality odds. The mortality odds among the asystole/pulseless electrical activity (PEA) patients were modulated by body mass index (BMI) and among ventricular fibrillation/pulseless ventricular tachycardia (VF/pVT) patients were by serum albumin concentration (decrease by 2.85-fold with 1 g/dl increase). Procalcitonin (PCT) concentration, age, high-sensitivity C-reactive protein (hsCRP), albumin, and potassium were the most influential parameters for mortality prediction with the use of the random forest classifier. Nutritional status-associated parameters (serum albumin concentration, BMI, and Nutritional Risk Score 2002 [NRS-2002]) may be useful in predicting mortality in patients with CA, especially in patients with PCT >0.17 ng/ml, as showed by the decision tree chosen from the random forest classifier based on goodness of fit (AUC score). CONCLUSIONS Mortality in patients following CA is modulated by many co-existing factors. The conclusions refer to sets of conditions rather than universal truths. For individual factors, the 5 most important classifiers of mortality (in descending order of importance) were PCT, age, hsCRP, albumin, and potassium.

Citing Articles

Cardiopulmonary resuscitation in obese patients: A scoping review.

Considine J, Couper K, Greif R, Ong G, Smyth M, Ng K Resusc Plus. 2024; 20:100820.

PMID: 39618429 PMC: 11607644. DOI: 10.1016/j.resplu.2024.100820.

References

Stiell I, Wells G, Field B, Spaite D, De Maio V, WARD R . Improved out-of-hospital cardiac arrest survival through the inexpensive optimization of an existing defibrillation program: OPALS study phase II. Ontario Prehospital Advanced Life Support. JAMA. 1999; 281(13):1175-81. DOI: 10.1001/jama.281.13.1175. View

Yan S, Gan Y, Jiang N, Wang R, Chen Y, Luo Z . The global survival rate among adult out-of-hospital cardiac arrest patients who received cardiopulmonary resuscitation: a systematic review and meta-analysis. Crit Care. 2020; 24(1):61. PMC: 7036236. DOI: 10.1186/s13054-020-2773-2. View

Viderman D, Abdildin Y, Batkuldinova K, Badenes R, Bilotta F . Artificial Intelligence in Resuscitation: A Scoping Review. J Clin Med. 2023; 12(6). PMC: 10054374. DOI: 10.3390/jcm12062254. View

Akirov A, Masri-Iraqi H, Atamna A, Shimon I . Low Albumin Levels Are Associated with Mortality Risk in Hospitalized Patients. Am J Med. 2017; 130(12):1465.e11-1465.e19. DOI: 10.1016/j.amjmed.2017.07.020. View

Czapla M, Zielinska M, Kubica-Cielinska A, Diakowska D, Quinn T, Karniej P . Factors associated with return of spontaneous circulation after out-of-hospital cardiac arrest in Poland: a one-year retrospective study. BMC Cardiovasc Disord. 2020; 20(1):288. PMC: 7291476. DOI: 10.1186/s12872-020-01571-5. View

Nanayakkara S, Fogarty S, Tremeer M, Ross K, Richards B, Bergmeir C . Characterising risk of in-hospital mortality following cardiac arrest using machine learning: A retrospective international registry study. PLoS Med. 2018; 15(11):e1002709. PMC: 6267953. DOI: 10.1371/journal.pmed.1002709. View

Hao R, Qi X, Xia X, Wang L, Li X . Malnutrition on admission increases the in-hospital mortality and length of stay in elder adults with acute ischemic stroke. J Clin Lab Anal. 2021; 36(1):e24132. PMC: 8761426. DOI: 10.1002/jcla.24132. View

Dorian P, Cass D, Schwartz B, Cooper R, Gelaznikas R, Barr A . Amiodarone as compared with lidocaine for shock-resistant ventricular fibrillation. N Engl J Med. 2002; 346(12):884-90. DOI: 10.1056/NEJMoa013029. View

Zhang X, Zhang X, Zhu Y, Tao J, Zhang Z, Zhang Y . Predictive Value of Nutritional Risk Screening 2002 and Mini Nutritional Assessment Short Form in Mortality in Chinese Hospitalized Geriatric Patients. Clin Interv Aging. 2020; 15:441-449. PMC: 7093094. DOI: 10.2147/CIA.S244910. View

10.

Shamout F, Zhu T, Clifton D . Machine Learning for Clinical Outcome Prediction. IEEE Rev Biomed Eng. 2020; 14:116-126. DOI: 10.1109/RBME.2020.3007816. View

11.

Janz D, Hollenbeck R, Pollock J, McPherson J, Rice T . Hyperoxia is associated with increased mortality in patients treated with mild therapeutic hypothermia after sudden cardiac arrest. Crit Care Med. 2012; 40(12):3135-9. PMC: 3502652. DOI: 10.1097/CCM.0b013e3182656976. View

12.

Norman K, Hass U, Pirlich M . Malnutrition in Older Adults-Recent Advances and Remaining Challenges. Nutrients. 2021; 13(8). PMC: 8399049. DOI: 10.3390/nu13082764. View

13.

Varon J, Marik P . Treatment of cardiac arrest with automatic external defibrillators: impact on outcome. Am J Cardiovasc Drugs. 2004; 3(4):265-70. DOI: 10.2165/00129784-200303040-00005. View

14.

Barbosa J, de Souza M, Costa J, Alves L, Oliveira L, Almeida R . Assessment of Malnutrition in Heart Failure and Its Relationship with Clinical Problems in Brazilian Health Services. Int J Environ Res Public Health. 2022; 19(16). PMC: 9408367. DOI: 10.3390/ijerph191610090. View

15.

Aqel S, Syaj S, Al-Bzour A, Abuzanouneh F, Al-Bzour N, Ahmad J . Artificial Intelligence and Machine Learning Applications in Sudden Cardiac Arrest Prediction and Management: A Comprehensive Review. Curr Cardiol Rep. 2023; 25(11):1391-1396. PMC: 10682172. DOI: 10.1007/s11886-023-01964-w. View

16.

Singer P, Reintam Blaser A, Berger M, Alhazzani W, Calder P, Casaer M . ESPEN guideline on clinical nutrition in the intensive care unit. Clin Nutr. 2018; 38(1):48-79. DOI: 10.1016/j.clnu.2018.08.037. View

17.

Akahane M, Ogawa T, Koike S, Tanabe S, Horiguchi H, Mizoguchi T . The effects of sex on out-of-hospital cardiac arrest outcomes. Am J Med. 2011; 124(4):325-33. DOI: 10.1016/j.amjmed.2010.10.020. View

18.

Annborn M, Dankiewicz J, Erlinge D, Hertel S, Rundgren M, Smith J . Procalcitonin after cardiac arrest - an indicator of severity of illness, ischemia-reperfusion injury and outcome. Resuscitation. 2013; 84(6):782-7. DOI: 10.1016/j.resuscitation.2013.01.004. View

19.

Sakamoto S, Taniguchi N, Nakajima S, Takahashi A . Extracorporeal life support for cardiogenic shock or cardiac arrest due to acute coronary syndrome. Ann Thorac Surg. 2012; 94(1):1-7. DOI: 10.1016/j.athoracsur.2012.01.032. View

20.

Van Walraven C, Stiell I, Wells G, Hebert P, Vandemheen K . Do advanced cardiac life support drugs increase resuscitation rates from in-hospital cardiac arrest? The OTAC Study Group. Ann Emerg Med. 1998; 32(5):544-53. DOI: 10.1016/s0196-0644(98)70031-9. View