Αποθηκεύτηκε σε:
| Κύριος συγγραφέας: | |
|---|---|
| Μορφή: | Recurso digital |
| Γλώσσα: | |
| Έκδοση: |
Zenodo
2025
|
| Θέματα: | |
| Διαθέσιμο Online: | https://doi.org/10.5281/zenodo.17986365 |
| Ετικέτες: |
Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
|
Πίνακας περιεχομένων:
- <p><a href="https://ijetrm.com/issues/files/Dec-2025-19-1766138750-DEC50.pdf" target="_blank" rel="noopener">Systemic Lupus Erythematosus (SLE)</a> is a complex autoimmune disease characterized by heterogeneous clinical<br>manifestations and fluctuating disease severity. Accurate severity grading is essential for effective treatment planning<br>and disease management. Traditional diagnostic approaches often rely on limited clinical indicators and fail to capture<br>the complex interactions among diverse patient data. This study proposes a multimodal deep learning framework for<br>severity grading of SLE by integrating clinical features and laboratory test results. The proposed model employs<br>specialized neural network modules to extract complementary representations from each data modality and fuses them<br>using an attention-based mechanism to capture inter-modal relationships. To address the ordered nature of disease<br>severity levels, an ordinal learning strategy is incorporated to ensure consistent and clinically meaningful predictions.<br>Experimental evaluation on SLE patient datasets demonstrates that the multimodal approach significantly outperforms<br>unimodal models in terms of accuracy, robustness, and severity discrimination. The results highlight the effectiveness<br>of multimodal deep learning in capturing complex disease patterns and its potential to support intelligent clinical<br>decision-making for SLE management.</p>