A learned RNA score associates with survival in archived bladder-cancer data
Source check: Source checked. Not independent scientific confirmation.
Finding: A ten-RNA LASSO score separated overall-survival groups in archived bladder-cancer data. The internal validation subset reported one-, two- and three-year AUCs of 0.663, 0.624 and 0.630. This is a retrospective association with outcome-informed screening, not a verified immunotherapy-response test.
Technology: LASSO
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- LASSO fitted the ten-RNA survival signature after univariate outcome screening, enabling the represented score-to-recorded-survival comparison.
- Test and result
- The TCGA analysis split 406 cases into 204 training and 202 validation records after prognostic screening; cohort-specific median scores defined high and low groups.
- Limitation / still unknown
- Outcome screening preceded the split, so the validation subset is not untouched. The separate 65-case local series is stated as collected in 2022–2023 yet reports three-year AUCs in a May 2024 article; that timeline is unresolved and its performance is excluded here. Cohort counts vary between 412 and 406. Treatment-response proxies, drug predictions and proposed molecular mechanisms are not validated clinical outcomes.
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/PMC11168393/ · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC11168393/unicode
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: 21 Nov 2026. Review scope: Primary computational Methods on score construction and cohort data; Results on TCGA survival; no experimental protocol review.
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 1/5 · 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.