October 2, 2025JAMIA OpenOpen Access

Early auxiliary diagnosis model for chest pain triad based on artificial intelligence multimodal fusion

View Full Paper

Ask AI

Bookmark

Authors

Discussion

This model classifies causes of chest pain in emergency settings, suggesting AI can enhance triage efficiency.

The model achieved an accuracy of 88.40% in classifying chest pain causes.
SHAP analysis identified key features like d-dimer and high-sensitivity troponin as clinically relevant.
Gradient boosting was used for developing the AI model, demonstrating superior performance and robustness.
Integration of clinical workflows with the AI model is crucial for effective implementation in emergency settings.

Tang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

October 2, 2025JAMIA OpenOpen Access

View Full Paper

Ask AI

Bookmark

Authors

This model classifies causes of chest pain in emergency settings, suggesting AI can enhance triage efficiency.

The model achieved an accuracy of 88.40% in classifying chest pain causes.
SHAP analysis identified key features like d-dimer and high-sensitivity troponin as clinically relevant.
Gradient boosting was used for developing the AI model, demonstrating superior performance and robustness.
Integration of clinical workflows with the AI model is crucial for effective implementation in emergency settings.

Tang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark