Optimized graph neural network-multilayer perceptron fusion classifier for metastatic prostate cancer detection in Western and Asian populations.
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: Reactome-constrained GNN P-NETwa with downstream MLP and DeepLIFT attribution selects features and predicts metastatic prostate cancer. 18-gene panel accuracy/F1 .88/.75 internal test and .87/.85 external validation; selected genes are predictive signatures, not proven causal drivers. 1,360 development samples split 80/10/10 and two independent external datasets; retrospective public cohorts and Asian subgroup imbalance constrain use.
Technology: Reactome-constrained GNN P-NETwa with downstream MLP and DeepLIFT attribution selects features and predicts metastatic prostate cancer.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Reactome-constrained GNN P-NETwa with downstream MLP and DeepLIFT attribution selects features and predicts metastatic prostate cancer.
- Limitation / still unknown
- Both validations use retrospective public cohorts, with subgroup imbalance; the predictive gene panel does not establish causal drivers or prospective clinical utility.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12490683/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.