Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI

TL;DR

This paper introduces an explainable AI system that combines textual clinical notes and numerical lab data using a multimodal fusion strategy, achieving high accuracy and interpretability for prostate cancer classification.

Contribution

It demonstrates that a simple BERT and Random Forest pipeline with multimodal fusion improves prostate cancer classification performance and interpretability over existing methods.

Findings

Achieved 98% accuracy and 99% AUC on the PLCO-NIH dataset.

Improved recall for intermediate cancer stages (Class 2/3) to 0.900.

Provided transparent feature importance via SHAP analysis.

Abstract

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.