JMIR Publications

ABSTRACT

Background:

Currently, there is a lack of effective early assessment tools for predicting the onset and development of cardiac arrest (CA). With the increasing attention of clinical researchers on machine learning (ML), some studies have developed predictive models for the occurrence and prognosis of cardiac arrest (CA). However, these models lack systematic evidence to substantiate their efficacy.

Objective:

This systematic review and meta-analysis was conducted to evaluate the prediction value of ML in CA for the occurrence, good neurological prognosis, mortality, and the recovery of spontaneous circulation (ROSC), thereby providing evidence-based support for the development and refinement of applicable clinical tools.

Methods:

PubMed, Embase, Cochrane Library, and Web of Science were systematically searched from their establishment until May 17, 2024. The risk of bias in all prediction models was detected via the Prediction Model Risk of Bias Assessment Tool.

Results:

93 studies were selected, encompassing a total of 5,729,721 in-hospital and out-of-hospital patients. The meta-analysis revealed that for predicting CA, the pooled C-index, sensitivity, and specificity derived from imbalanced validation set data were 0.90 (95% CI: 0.87-0.93), 0.83 (95% CI: 0.79-0.87), and 0.93 (95% CI: 0.88-0.96), respectively. Based on balanced validation set data, the pooled C-index, sensitivity, and specificity were 0.88 (95% CI: 0.86-0.90), 0.72 (95% CI: 0.49-0.95), and 0.79 (95% CI: 0.68-0.91), respectively. For predicting the good-cerebral performance category score 1-2 (CPC1-2), the pooled C-index, sensitivity, and specificity based on validation set data were 0.86 (95% CI: 0.85-0.87), 0.72 (95% CI: 0.61-0.81), and 0.79 (95% CI: 0.66-0.88), respectively. For predicting CA mortality, the pooled C-index, sensitivity, and specificity based on validation set data were 0.85 (95% CI: 0.82-0.87), 0.83 (95% CI: 0.79-0.87), and 0.79 (95% CI: 0.74-0.83), respectively. For predicting ROSC, the pooled C-index, sensitivity, and specificity based on validation set data were 0.77 (95% CI: 0.74-0.80), 0.53 (95% CI: 0.31-0.74), and 0.88 (95% CI: 0.71-0.96), respectively. In predicting CA, the most significant modeling variables were respiratory rate (RR), Blood pressure (BP), age, and temperature. In predicting CPC1-2, the most significant modeling variables in the in-hospital cardiac arrest group were rhythm (shockable/non-shockable), age, medication use, and gender; the most significant modeling variables in the out-of-hospital cardiac arrest group were age, rhythm (shockable/non-shockable), and medication use, and return of spontaneous circulation.

Conclusions:

ML represents a currently promising approach for predicting the occurrence and outcomes of CA. Therefore, in future research on CA, we may attempt to systematically update traditional scoring tools based on the superior performance of ML in specific outcomes, achieving artificial intelligence-driven enhancements. Clinical Trial: Not applicable