To propose a novel Multimodal Pulmonary Risk Prediction Network (MPRPN) for early detection and risk prediction of pulmonary diseases in athletes.
Key Findings:
MPRPN achieved accuracy improvements up to 89.92%.
F1-score reached 90.23%.
AUC was up to 90.47%.
Interpretation:
The MPRPN effectively leverages complementary multimodal information, providing a reliable tool for early detection and personalized risk assessment of pulmonary diseases in athletes.
Limitations:
High computational demands and limited interpretability remain challenges.
The need for high-quality labeled data poses significant challenges for generalizability.
Conclusion:
The proposed framework has significant potential for real-world applications in sports medicine and preventive healthcare.
