Prehospital diagnostic algorithm for acute coronary syndrome using machine learning: a prospective observational...

Area of Science:

• Cardiology
• Artificial Intelligence
• Emergency Medicine

Background:

• Prehospital recognition of acute coronary syndrome (ACS) is crucial for timely intervention and improved patient outcomes.
• Current diagnostic methods in prehospital settings may have limitations in speed and precision.

Purpose of the Study:

• To evaluate the predictive performance of machine learning (ML)-based prehospital algorithms for acute coronary syndrome (ACS) detection.
• To assess the feasibility of using ML models for real-time ACS prediction by emergency medical services.

Main Methods:

• A multicenter observational prospective study involving 10 Japanese facilities.
• Analysis of data from adult patients with suspected ACS identified by emergency medical services.
• Evaluation of nine ML algorithms using nested cross-validation, including a voting classifier and support vector machine.

Main Results:

• The voting classifier model, utilizing 43 features, achieved a high Area Under the Curve (AUC) of 0.861 for ACS prediction.
• Reduced feature sets (17 features) maintained high predictive performance, with AUCs of 0.864 for both voting classifier and support vector machine models.
• External validation confirmed the robustness of the ML models' accuracy.

Conclusions:

• Machine learning-based prehospital algorithms demonstrate significant predictive power for identifying acute coronary syndrome (ACS).
• These algorithms offer a promising tool for enhancing the accuracy and efficiency of prehospital ACS diagnosis.
• The findings support the integration of ML into emergency medical services for critical cardiac event detection.