AI and Cancer Research ── Prostate ── 2026-11-12
Prostate cancer: treatment, trials and AI
- Abstract
Introduction: Whether bone metastasis is present at diagnosis determines curative versus systemic treatment of prostate cancer, yet referral for advanced staging relies on imperfect risk stratification; magnetic resonance imaging (MRI) radiomics has been proposed to predict metastatic status from routinely acquired staging imaging.
Methods: This systematic review (PROSPERO CRD420261463568) searched PubMed, Embase and Cochrane CENTRAL for studies of radiomic, deep-learning or hybrid models predicting bone-metastatic status from prostate MRI; incremental value over clinical predictors, reporting completeness, radiomics methodology and risk of bias were appraised.
Results: Six retrospective studies (1240 patients, 491 with bone metastasis, all from China; 322 contributed to the principal validation estimates) were included. Clinical-plus-radiomics models achieved validation areas under the receiver operating characteristic curve (AUCs) of 0.893–0.920 internally and 0.903 externally, with the highest estimate (0.928) from a multimodal model lacking clinical predictors. Only two studies compared clinical-only with combined models (AUC increments of 0.060 and 0.081).
Conclusions: Reported discrimination was generally high, but current evidence cannot establish that radiomics adds value beyond routine clinical predictors. These models are best understood as predictive biomarkers rather than detection tools; a potential triage role among patients below routine staging thresholds remains untested, and transportability beyond the high-prevalence cohorts studied is unproven; prospective multicentre validation is required before clinical use.
Journal IF-equivalent: 4.9 (OpenAlex 2-year mean citedness, value as of 2026-11-09, retrieved 2026-11-11; not the official Clarivate IF)Reference: Clausen NA, Temperley HC, Mulhall CB, Curtain BMM, McLoughlin LC, Kelly ME, et al. Radiomics-Based Prediction of Bone Metastases from Baseline Prostate MRI in Prostate Cancer: A Systematic Review and Critical Appraisal. BioTech. 2026 Nov 8;15(5):102. doi:10.3390/biotech15050102.Checked: Abstract only - Abstract
Prostate cancer is one of the most common and dangerous malignancies in men globally, and so a systematic and mathematically rigorous approach should be used to assess and rank therapeutic agents. This study introduces the computational model which combines graph theoretic molecular descriptors, fuzzy machine learning and fuzzy multi-criteria decision making in analyzing and ranking prostate cancer drugs. The molecular graphs of the selected prostate cancer drugs are partitioned based on their eccentricity, and a set of topological indices are obtained. These indices are structural finger prints that encode the geometry and connectivity of every drug molecule in a mathematically accurate way. Two fuzzy machine learning models, i.e. Fuzzy Random Forest (Fuzzy RF) and Fuzzy Artificial Neural Network (Fuzzy ANN), are used to predict the physicochemical properties of the drug candidates. The models provide accurate and reliable predictions that effectively capture the inherent uncertainty in molecular property data by integrating fuzzy logic into the learning process, as validated through comparison with conventional (non-fuzzy) baseline models. The predicted physicochemical properties and the calculated topological indices are subsequently analyzed by the Fuzzy Measurement of Alternatives and Ranking based on the Compromise Solution (Fuzzy MARCOS), the Fuzzy MARCOS, which is an effective fuzzy multi-criteria approach to decision-making. This strategy involves comparing all drug candidates simultaneously to an ideal and an anti-ideal reference point, which results in an uncertainty aware ranking and an in silico objective prioritization of each drug candidate taking into account both structural and physicochemical features. The findings indicate that the suggested integrated model offers a clear, coherent, and mathematically justified foundation of the evaluation of drugs used in prostate cancer, which can be useful to pharmaceutical scientists and clinical decision makers.
Journal IF-equivalent: 3.1 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Ahmed W, Raza A, Zaman S, Abbas M, Ali P. Multi-criteria drug ranking for prostate cancer using graph-theoretic descriptors and fuzzy machine learning with MARCOS decision analysis. Computational Biology and Chemistry. 2027 Feb;126:109499. doi:10.1016/j.compbiolchem.2026.109499.Checked: Abstract only