JMIR Publications

ABSTRACT

Background:

In-hospital cardiac arrest (IHCA) remains a public health conundrum with high morbidity and mortality rates. While early identification of high-risk patients could enable preventive interventions and improve survival, evidence on the effectiveness of current prediction methods remains inconclusive. Limited research exists on patients’ pre-arrest pathophysiological status, predictive, and prognostic factors of IHCA, highlighting the need for a comprehensive synthesis of predictive methodologies.

Objective:

This scoping review aims to synthesize and critically evaluate the quality and quantity of clinical features and machine learning (ML) models for predicting IHCA. The review will evaluate temporal characteristics, predictive and prognostic values of pre-arrest clinical features, and model performance metrics.

Methods:

Following PRISMA-ScR guidelines, peer-reviewed studies from April 2009 to April 2024 using ML to predict IHCA will be included. Data sources include PubMed, Web of Science, IEEE, and Embase. Two reviewers will independently screen, extract, and assess the quality of included studies. Data will be synthesized using descriptive statistics and narrative summaries.

Results:

The review will provide insights into common clinical predictors, data quantity and quality, and ML model metrics for IHCA prediction. Findings will identify gaps and offer practical recommendations for standardizing clinical features in ML modeling.

Conclusions:

This study will contribute to advancing ML applications for IHCA prediction by addressing data challenges and promoting standardization to improve clinical decision-making process.