Morphologic learning distinguishes CLL progression patterns in biopsy tissue
Source check: Source checked. Not independent scientific confirmation.
Finding: A random forest combined nuclear size, staining intensity, cell density and cell spacing to distinguish chronic lymphocytic leukemia, accelerated CLL and Richter transformation in biopsy regions. The combined model reported 82.4% region-level accuracy with patient-separated evaluation. Manual selection of informative regions and retrospective single-centre sampling limit its clinical interpretation; this does not establish autonomous patient diagnosis or treatment benefit.
Technology: Random forest
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A random forest learns diagnostic relationships among quantified cytologic and spatial tissue features.
- Test and result
- Patient-separated biopsy-region classification against expert-confirmed lymphoma categories, with repeated patient-level splitting.
- Limitation / still unknown
- Prospective diagnostic performance and clinical benefit remain unestablished; manually selected regions excluded difficult artifacts and residual disease patterns.
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/PMC9526447/
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 relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..
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 2/5 · 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.