Artificial Intelligence for Multi-omics Breast Cancer Subtype Prediction and Discovery: A Systematic Review
4 affiliations
- 1Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC 3353, Australia .
- 2School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney, NSW 2751, Australia .
- 3Children’s Cancer Institute, Health Translational Hub, Sydney, NSW 20, Australia .
- 4School of Clinical Medicine, UNSW Medicine & Health, Sydney, NSW 2031, Australia .
Abstract
Artificial intelligence models integrate molecular omics to reproduce breast cancer subtype labels or discover patient groups, but heterogeneous endpoints, cohorts, and validation hinder interpretation. We searched PubMed/MEDLINE, Europe PMC, and OpenAlex through 2026 September 8, supplemented by citation searching and targeted retrieval through Google Scholar and IEEE Xplore. Eligible studies combined at least 2 molecular omics in one machine-learning model for breast cancer subtype prediction or discovery. Findings were synthesized by endpoint without meta-analysis. Of 705 exported records, 301 duplicates were removed, 404 unique records were screened, and 70 studies were included. Fifty-seven addressed intrinsic subtype or Prediction Analysis of Microarray 50 (PAM50) prediction, and 11, subtype discovery or recovery. Sixty-two publications used The Cancer Genome Atlas Breast Invasive Carcinoma, and 9 used the Molecular Taxonomy of Breast Cancer International Consortium, demonstrating extensive reuse of limited patient populations. Among 59 supervised prediction studies, only 1 independently evaluated a complete multi-omics model in another cohort, and none reported prospective or nested full-pipeline validation. Calibration, uncertainty reporting, and external validation were uncommon, although 34 studies provided code or software. Among 11 discovery studies, 4 assessed resampling stability and 3 attempted independent subtype recovery. All 57 PAM50 studies used expression, and none reported excluding PAM50 classifier genes or close proxies. Thirty-nine included a matched expression-only baseline, but only one tested the complete model independently. Risk of bias was high in 48/59 prediction studies. Graph, hypergraph, attention, and uncertainty-aware models are increasingly used, but evidence of transportability and calibrated clinical value remains limited.
Related
- Before Sepsis Strikes: Artificial Intelligence for Early Prediction of Postoperative Sepsis and Sepsis-Related Complications After Major Abdominal Surgery—A Systematic Review
- Artificial Intelligence in Eye Disease: A Systematic Review of Screening, Diagnosis, Prognosis, Treatment-Response Prediction, and Clinical Decision Support
- Artificial intelligence and machine learning for prediction of postoperative complications: A systematic review focused on anesthesiology, perioperative risk stratification, and clinical applicability.
- Artificial intelligence empowering the diagnosis and treatment of rotator cuff tears: A systematic review from image optimization to prognosis prediction.
- Artificial intelligence-driven imaging-based prediction models for hemorrhagic transformation after mechanical thrombectomy in acute ischemic stroke: a systematic review and meta-analysis
BibTeX
@article{pilodiya2026artificial,
title = {{Artificial Intelligence for Multi-omics Breast Cancer Subtype Prediction and Discovery: A Systematic Review}},
author = {Deepali Pilodiya and Azadeh Noori Hoshyar and Cameron Foale and Madhu Chetty and Piyushkumar A. Mundra},
journal = {Computational and Structural Biotechnology Journal},
year = {2026},
month = oct,
doi = {10.34133/csbj.0243},
url = {https://doi.org/10.34133/csbj.0243},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial Intelligence for Multi-omics Breast Cancer Subtype Prediction and Discovery: A Systematic Review
AU - Deepali Pilodiya
AU - Azadeh Noori Hoshyar
AU - Cameron Foale
AU - Madhu Chetty
AU - Piyushkumar A. Mundra
PY - 2026
DA - 2026/10/26
JO - Computational and Structural Biotechnology Journal
DO - 10.34133/csbj.0243
UR - https://doi.org/10.34133/csbj.0243
AB - Artificial intelligence models integrate molecular omics to reproduce breast cancer subtype labels or discover patient groups, but heterogeneous endpoints, cohorts, and validation hinder interpretation. We searched PubMed/MEDLINE, Europe PMC, and OpenAlex through 2026 September 8, supplemented by citation searching and targeted retrieval through Google Scholar and IEEE Xplore. Eligible studies combined at least 2 molecular omics in one machine-learning model for breast cancer subtype prediction or discovery. Findings were synthesized by endpoint without meta-analysis. Of 705 exported records, 301 duplicates were removed, 404 unique records were screened, and 70 studies were included. Fifty-seven addressed intrinsic subtype or Prediction Analysis of Microarray 50 (PAM50) prediction, and 11, subtype discovery or recovery. Sixty-two publications used The Cancer Genome Atlas Breast Invasive Carcinoma, and 9 used the Molecular Taxonomy of Breast Cancer International Consortium, demonstrating extensive reuse of limited patient populations. Among 59 supervised prediction studies, only 1 independently evaluated a complete multi-omics model in another cohort, and none reported prospective or nested full-pipeline validation. Calibration, uncertainty reporting, and external validation were uncommon, although 34 studies provided code or software. Among 11 discovery studies, 4 assessed resampling stability and 3 attempted independent subtype recovery. All 57 PAM50 studies used expression, and none reported excluding PAM50 classifier genes or close proxies. Thirty-nine included a matched expression-only baseline, but only one tested the complete model independently. Risk of bias was high in 48/59 prediction studies. Graph, hypergraph, attention, and uncertainty-aware models are increasingly used, but evidence of transportability and calibrated clinical value remains limited.
SN - 2001-0370
ER -