BACKGROUND
Cardiac arrest is a life-threatening cessation of heart activity. Early prediction of cardiac arrest is important as it provides an opportunity to take the necessary measures to prevent or intervene during the onset. Artificial intelligence technologies and big data have been increasingly used to enhance the ability to predict and prepare for the patients at risk.
OBJECTIVE
This study aims to explore the use of AI technology in predicting cardiac arrest as reported in the literature.
METHODS
Scoping review was conducted in line with guidelines of PRISMA Extension for Scoping Review (PRISMA-ScR). Scopus, Science Direct, Embase, IEEE, and Google Scholar were searched to identify relevant studies. Backward reference list checking of included studies was also conducted. The study selection and data extraction were conducted independently by two reviewers. Data extracted from the included studies were synthesized narratively.
RESULTS
Out of 697 citations retrieved, 41 studies were included in the review, and 6 were added after backward citation checking. The included studies reported the use of AI in the prediction of cardiac arrest. We were able to classify the approach taken by the studies in three different categories - 26 studies predicted cardiac arrest by analyzing specific parameters or variables of the patients while 16 studies developed an AI-based warning system. The rest of the 5 studies focused on distinguishing high-risk cardiac arrest patients from patients, not at risk. 2 studies focused on the pediatric population, and the rest focused on adults (n=45). The majority of the studies used datasets with a size of less than 10,000 (n=32). Machine learning models were the most prominent branch of AI used in the prediction of cardiac arrest in the studies (n=38) and the most used algorithm belonged to the neural network (n=23). K-Fold cross-validation was the most used algorithm evaluation tool reported in the studies (n=24).
CONCLUSIONS
: AI is extensively being used to predict cardiac arrest in different patient settings. Technology is expected to play an integral role in changing cardiac medicine for the better. There is a need for more reviews to learn the obstacles of implementing AI technologies in the clinical setting. Moreover, research focusing on how to best provide clinicians support to understand, adapt and implement the technology in their practice is also required.
We must identify patients at risk for pre-hospital sudden cardiac arrest at the early phase of myocardial infarction