Source check: Source checked. Not independent scientific confirmation.
Finding: Machine learning used physical measurements of urinary extracellular vesicles to distinguish prostate cancer from benign prostatic hyperplasia in a three-hospital biopsy cohort.
Technology: Five ML algorithms use urinary extracellular-vesicle physical measurements in 222 biopsy-indicated patients recruited at three centers (65 pathology-confirmed cancer, 157 BPH); model predicts cancer status as a possible adjunct biomarker.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Five ML algorithms use urinary extracellular-vesicle physical measurements in 222 biopsy-indicated patients recruited at three centers (65 pathology-confirmed cancer, 157 BPH); model predicts cancer status as a possible adjunct biomarker.
- Test and result
- The study compared five algorithms against biopsy pathology in 222 patients, including 65 with cancer. It drew its 67-patient test set from the same cohort.
- Limitation / still unknown
- No external-site test was reported. The study did not establish whether the model improves biopsy decisions.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41598-026-54920-3
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 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Source check: Source checked. Not independent scientific confirmation.
Finding: Transfer-learned YOLOv3, RCNN and MobileNet segmented/detected carotid plaque in MRI; reported test/validation performance included 94.81%, 92.53% and 90.23% accuracy with sensitivity/specificity assessment. Full-text Methods and Results were checked; the AI operation, first result-bearing version, measured result and validation are confirmed, with no catalog or lane duplicate. Original Results report held-out, independent, external, cross-fold, or biological validation as applicable; limitations remain bounded to the reported study design.
Technology: Original Methods explicitly describe the learned model/algorithm and its operation on the study data; this is more than generic computation or writing assistance.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Original Methods explicitly describe the learned model/algorithm and its operation on the study data; this is more than generic computation or writing assistance.
- Test and result
- Transfer-learned YOLOv3, RCNN and MobileNet segmented/detected carotid plaque in MRI; reported test/validation performance included 94.81%, 92.53% and 90.23% accuracy with sensitivity/specificity assessment.
- Limitation / still unknown
- Original Results report held-out, independent, external, cross-fold, or biological validation as applicable; limitations remain bounded to the reported study design. The source does not establish benefits beyond the reported evaluation.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.3389/fcvm.2023.1101765 · https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9998982/
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.