-
1
The study introduces the Multimodal Pulmonary Risk Prediction Network (MPRPN) for early detection of pulmonary diseases in athletes.
-
2
MPRPN integrates visual, textual, and physiological data using an Adaptive Modality Weighting Strategy and a Hierarchical Risk Prediction Strategy.
-
3
Experimental results indicate MPRPN achieves accuracy improvements up to 89.92%, F1-score of 90.23%, and AUC of 90.47%.
-
4
The proposed framework effectively leverages multimodal information, enhancing predictive capability for pulmonary disease risk assessment.
-
5
MPRPN shows potential for real-world applications in sports medicine and preventive healthcare, addressing limitations of traditional methods.
