Artificial Intelligence Design for Race-Based Prostate Cancer Stage Classification With Multilayer Perceptron: Feature Selection Optimization Approach
Clinical Snapshot
PICO Framework
| P — Population | Men with prostate cancer from TCGA-PRAD dataset, primarily White cohort with racial minority comparison groups |
| I — Intervention | Multilayer perceptron (MLP) model using DNA methylation data with differentially methylated position analysis and recursive feature elimination |
| C — Comparator | Performance comparison across racial groups (White vs racial minorities) |
| O — Outcomes | Prostate cancer stage classification accuracy (early stages I-II vs late stages III-IV), model performance metrics including AUC |
Bottom Line
This study developed a machine learning model using DNA methylation data to classify prostate cancer stages, achieving excellent performance (95% accuracy, 99% AUC) in White patients but poor generalization to racial minorities. While the technical approach using multilayer perceptrons with feature selection is sound, the model's racial bias severely limits clinical utility. The research highlights important disparities in genomic medicine but falls short of providing a clinically implementable solution. Australian clinicians should note that this model would not be suitable for our diverse population without significant modification. The study emphasizes the critical need for inclusive dataset development in precision medicine. Current clinical staging methods remain more appropriate until race-inclusive models are developed and validated.
Key Findings
P Value: Not reported
Effect Size: 95% accuracy in White cohort
Primary Outcome: Prostate cancer stage classification (early vs late stage)
Nnt Or Sensitivity: 99% area under the curve, sensitivity and specificity not specified
Confidence Interval: Not reported
Clinical Application
Requires DNA methylation profiling infrastructure and computational resources Limited applicability given Australia's multicultural population and poor model performance in racial minorities. Would require significant adaptation for Aboriginal and Torres Strait Islander populations and other ethnic groups. Not currently aligned with RACGP prostate cancer screening guidelines which rely on PSA and clinical assessment. Limited to White men with prostate cancer based on current model performance
Abstract
BACKGROUND: Prostate cancer progression exhibits significant variability influenced by biological and racial factors. DNA methylation profiling has shown potential in early cancer detection, but its integration with machine learning across racially diverse populations remains limited. OBJECTIVE: This study aimed to develop a prostate cancer stage classifier for the majority White cohort using DNA methylation data and a multilayer perceptron (MLP) model in order to classify prostate cancer stages into early (stages I-II) and late (stages III-IV) stages and assess its performance when applied to other racial groups to highlight the need for race-specific models. METHODS: Methylation and phenotype data from the TCGA-PRAD (The Cancer Genome Atlas Prostate Adenocarcinoma) dataset were processed using differentially methylated position (DMP) analysis to identify CpG sites correlated with cancer stages. These features were further refined through recursive feature elimination (RFE) and used to train MLP models. Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) were used to interpret the model and identify key DNA methylation features contributing to model predictions. RESULTS: The best-performing model achieved 95% accuracy and up to 99% area under the curve on the majority race (White) training data using 90 selected features. However, performance declined sharply in racial minority groups, revealing the effects of sample imbalance and race-specific methylation patterns. Feature importance examination indicated strong patterns within certain CpG sites driving model predictions. CONCLUSIONS: We propose a race-aware MLP model for prostate cancer stage classification using DNA methylation data, which has been optimized through DMP and RFE-based feature selection. SHAP and LIME confirmed the predictive relevance of selected CpG sites, supporting model transparency. The results highlight high performance within the White cohort but reveal poor generalization to racial minority groups, emphasizing the importance of race-specific modeling strategies.
References
- 1.Mulia, A., Adithama, A., Agustriawan, D., Overbeek, M., Widjaja, M., Kurniawan, V., Syechlo, J., Ahmad, M. I., Sathipati, S. Y., & Kurubanjerdjit, N. (2026). Artificial Intelligence Design for Race-Based Prostate Cancer Stage Classification With Multilayer Perceptron: Feature Selection Optimization Approach. JMIR Formative Research. https://doi.org/10.2196/82587
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
3 Aug 2026
European journal of radiology
A CT-based deep learning model to differentiate between benign and malignant adrenal lesions
3 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service