Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Asma Sadia, Khan, Fariba Tasnia, Mahmud, Tanjim, Khan, Salman Karim, Chakma, Rishita, Sharmen, Nahed, Hossain, Mohammad Shahadat, Andersson, Karl
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908469464924160
author Khan, Asma Sadia
Khan, Fariba Tasnia
Mahmud, Tanjim
Khan, Salman Karim
Chakma, Rishita
Sharmen, Nahed
Hossain, Mohammad Shahadat
Andersson, Karl
author_facet Khan, Asma Sadia
Khan, Fariba Tasnia
Mahmud, Tanjim
Khan, Salman Karim
Chakma, Rishita
Sharmen, Nahed
Hossain, Mohammad Shahadat
Andersson, Karl
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20714
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI
Khan, Asma Sadia
Khan, Fariba Tasnia
Mahmud, Tanjim
Khan, Salman Karim
Chakma, Rishita
Sharmen, Nahed
Hossain, Mohammad Shahadat
Andersson, Karl
Machine Learning
Artificial Intelligence
Quantitative Methods
Applications
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.
title Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI
topic Machine Learning
Artificial Intelligence
Quantitative Methods
Applications
url https://arxiv.org/abs/2507.20714