Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI
This work addresses the need for advanced diagnostic tools in prostate cancer, offering a balance of high performance and interpretability for hospitals, though it is incremental as multimodal fusion is established.
The paper tackled prostate cancer classification by proposing an explainable AI system that fuses BERT for clinical notes and Random Forest for lab data, achieving 98% accuracy and 99% AUC on the PLCO-NIH dataset, with improved recall for intermediate stages.
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.