Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion
Read the original on arXiv AI →The paper introduces CFKD-AFN, a cross‑fidelity knowledge distillation and adaptive fusion network that uses abundant low‑fidelity simulation data to improve personalized treatment outcome predictions from scarce high‑fidelity trial data. The dual‑channel distillation module extracts complementary knowledge from the low‑fidelity model, while an attention‑guided fusion module adaptively integrates multi‑source information. Experiments on chronic obstructive pulmonary disease data demonstrate significant reductions in mean squared error (6.67%–74.55%) and mean absolute percentage error (1.43%–51.54%) compared to competing methods, and the framework can be extended to an interpretable variant for feature‑attribution analysis.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.