用简单模型融合文本与数值数据，提升前列腺癌分类准确率。
Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI
- 结合BERT与随机森林，通过新融合策略整合临床文本与检验数据。
- 在PLCO-NIH数据集上达到98%准确率，中间阶段癌症召回率达0.900。
- 模型可解释性强，适合临床部署，兼顾性能与效率。
前列腺癌是男性第二常见的恶性肿瘤，亟需先进的诊断工具。本文提出一种可解释AI系统，将BERT（用于文本病历）与随机森林（用于数值检验数据）通过新颖的多模态融合策略结合，在PLCO-NIH数据集上实现98%准确率和99% AUC。尽管多模态融合已成熟，本研究证明，一个简单且可解释的BERT+RF流程能显著提升分类性能，尤其在中等风险癌症阶段（类别2/3召回率：联合为0.900，仅数值为0.824，仅文本为0.725）。SHAP分析提供透明特征重要性排序，消融实验验证了文本特征的互补价值。该方法在保持高精度（F1=89%）、计算高效的同时具备临床可解释性，满足前列腺癌诊断的关键需求。
原文摘要 · Abstract (English)
Prostate cancer, the second most prevalent male malignancy, requires advanced diagnostic tools. We propose an explainable AI system combining BERT (for textual clinical notes) and Random Forest (for numerical lab data) through a novel multimodal fusion strategy, achieving superior classification performance on PLCO-NIH dataset (98% accuracy, 99% AUC). While multimodal fusion is established, our work demonstrates that a simple yet interpretable BERT+RF pipeline delivers clinically significant improvements - particularly for intermediate cancer stages (Class 2/3 recall: 0.900 combined vs 0.824 numerical/0.725 textual). SHAP analysis provides transparent feature importance rankings, while ablation studies prove textual features' complementary value. This accessible approach offers hospitals a balance of high performance (F1=89%), computational efficiency, and clinical interpretability - addressing critical needs in prostate cancer diagnostics.
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。