Prediction of ROSC After Cardiac Arrest Using Machine Learning

Area of Science:

• Emergency Medicine
• Data Science
• Public Health

Background:

• Out-of-hospital cardiac arrest (OHCA) presents a significant public health challenge with low survival rates.
• Return of spontaneous circulation (ROSC) is a key indicator of successful resuscitation in OHCA patients.

Purpose of the Study:

• To develop and evaluate a machine learning model for predicting ROSC in OHCA patients.
• To compare the predictive performance of the machine learning model against the established ROSC after cardiac arrest (RACA) score.

Main Methods:

• Development of a predictive model utilizing machine learning algorithms.
• Comparative analysis of the machine learning model's predictions against the RACA score for accuracy in forecasting ROSC.

Main Results:

• The study demonstrated the efficacy of machine learning in creating predictive models for ROSC.
• Machine learning models showed comparable or superior performance in predicting ROSC compared to the RACA score.

Conclusions:

• Machine learning offers a valuable tool for predicting ROSC in OHCA cases.
• The developed machine learning model shows potential for improving clinical decision-making in the management of OHCA.