用仿真数据提升小样本患者治疗效果预测精度
Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion
- 双通道知识蒸馏融合低精度仿真与高精度试验数据
- 在慢阻肺数据上误差降低超6.67%，对数据量变化鲁棒
- 可解释版本助力分析治疗效果相关特征模式
基于小样本和罕见患者群体的临床试验数据进行个性化治疗效果预测，是精准医疗中的关键任务。然而，试验数据成本高且稀缺，制约了预测性能。为此，我们提出跨保真度知识蒸馏与自适应融合网络（CFKD-AFN），利用大量但保真度较低的仿真数据来增强对少量高保真度试验数据的预测能力。CFKD-AFN包含双通道知识蒸馏模块，从低保真度模型中提取互补知识，并引入注意力引导融合模块，自适应整合多源信息。在慢性阻塞性肺疾病数据上的实验表明，相较于对比方法，CFKD-AFN将均方误差降低6.67%~74.55%，平均绝对百分比误差降低1.43%~51.54%，且对高保真度数据集大小变化保持鲁棒。此外，我们将框架扩展为可解释变体，用于探索与治疗结果相关的特征重要性模式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。