Related Experiment Video
Updated: Jun 17, 2025
Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research
Published on: November 3, 2023
Machine Learning and Clinical Predictors of Mortality in Cardiac Arrest Patients: A Comprehensive Analysis
Łukasz Lewandowski1, Michał Czapla2,3,4, Izabella Uchmanowicz5
1Department of Medical Biochemistry, Wrocław Medical Univeristy, Wrocław, Poland.
Insights
Predicting mortality after cardiac arrest (CA) involves multiple factors. Machine learning identified procalcitonin, age, hsCRP, albumin, and potassium as key predictors, with sex and nutritional status also influencing outcomes.
Area of Science:
- Critical Care Medicine
- Biostatistics
- Machine Learning in Healthcare
Background:
- Cardiac arrest (CA) presents a significant global public health challenge.
- Understanding mortality predictors is crucial for improving patient outcomes in intensive care units (ICUs).
Purpose of the Study:
- To explore mortality predictors and their interactions in patients following CA using machine learning.
- To determine mortality odds associated with various clinical parameters.
Main Methods:
- Retrospective analysis of 161 CA patient records from an ICU.
- Utilized random forest classifier to assess mortality parameters and identify key predictors.
- Employed logistic regression models to investigate conditional mortality odds and variable interactions.
Main Results:
- Male sex was linked to a 5.68-fold increase in mortality odds.
- Mortality odds were modulated by Body Mass Index (BMI) in asystole/pulseless electrical activity (PEA) patients and by serum albumin in ventricular fibrillation/pulseless ventricular tachycardia (VF/pVT) patients.
- Procalcitonin (PCT), age, hsCRP, albumin, and potassium were the top 5 predictors identified by the random forest classifier.
Conclusions:
- Mortality post-CA is influenced by a complex interplay of factors, not isolated variables.
- Nutritional status indicators (albumin, BMI, NRS-2002) show potential in predicting mortality, particularly when PCT levels are elevated (>0.17 ng/ml).
- The most influential individual mortality predictors were PCT, age, hsCRP, albumin, and potassium.
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.
