Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion
On the map: Knowledge distillation → Distillation for medical imaging
Abstract (arXiv)
Personalized treatment outcome prediction based on trial data for small-sample and rare patient groups is a critical task in precision medicine. However, the high cost and scarcity of trial data limit the prediction performance. To address this issue, we propose a cross-fidelity knowledge distillation and adaptive fusion network (CFKD-AFN), which leverages abundant but low-fidelity simulation data to enhance the prediction on scarce but high-fidelity trial data. CFKD-AFN incorporates a dual-channel knowledge distillation module to extract complementary knowledge from the low-fidelity model, along with an attention-guided fusion module to adaptively integrate multi-source information. Experiments on chronic obstructive pulmonary disease show that CFKD-AFN reduces the mean squared error by 6.67% ~ 74.55% and the mean absolute percentage error by 1.43% ~ 51.54% compared to the evaluated competing methods and remains robust to varying high-fidelity dataset sizes. Furthermore, we extend the CFKD-AFN framework to an interpretable variant for exploratory analysis of feature-attribution patterns associated with treatment outcomes.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation. Builds on 16 of its 44 references that are in the map. First posted on arXiv 30 Oct 2025.
Builds on
16 of 44 references.
References · 16
- 2018MINE: Mutual Information Neural Estimationcited by 683
- 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
- 2021Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networkscited by 48
- 2022MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcarecited by 37
- 2021Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantitiescited by 31
- 2022Disentangled Contrastive Learning for Social Recommendationcited by 27
- 2020On transfer learning of neural networks using bi-fidelity data for uncertainty propagationcited by 26
- 2021Multi-Domain Active Learning: Literature Review and Comparative Studycited by 6
- 2017Random Forests of Interaction Trees for Estimating Individualized Treatment Effects in Randomized Trialscited by 5
- 2020Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Imagecited by 5
- 2022A Contextual Ranking and Selection Method for Personalized Medicinecited by 5
- 2019Errors-in-variables Modeling of Personalized Treatment-Response Trajectoriescited by 4
4 more
- 2022KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Descriptioncited by 4
- 2023Dataset Condensation for Recommendationcited by 4
- 2021CARRNN: A Continuous Autoregressive Recurrent Neural Network for Deep Representation Learning from Sporadic Temporal Datacited by 1
- 2024MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimizationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025MMCTOP: A Multimodal Textualization and Mixture-of-Experts Framework for Clinical Trial Outcome Prediction
- 2026AdaFuse: Adaptive Multimodal Fusion for Lung Cancer Risk Prediction via Reinforcement Learning
- 2025Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
- 2025REACT-LLM: A Benchmark for Evaluating LLM Integration with Causal Features in Clinical Prognostic Tasks
- 2026Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments
- 2025Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Data
- 2026Counterfactual Understanding via Retrieval-aware Multimodal Modeling for Time-to-Event Survival Prediction
- 2025MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Prediction