LO
CapabilityCognitive automation2024-05-15
Agreement among 21 pathologists scoring PD-L1 in breast cancer rose from 0.618 by eye to 0.931 with AI assistance, a multi-institutional ring study found
Pathologistoccupation page →
Event date / reported
2024-05-15
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Scoring biomarkers
Quantifying stains such as PD-L1 that decide whether a patient gets a treatment.
Being augmented≈ Platform inference
Where this applies
A study in which 21 pathologists of different levels from four institutions scored PD-L1 combined positive score in triple-negative breast cancer by eye and with a deep-learning model the authors built. With AI assistance there were no significant differences between pathologists, the intraclass correlation rose from 0.618 to 0.931, and 80% of the AI results were accepted overall, most by junior pathologists. One biomarker in one cancer.
What this means
Where pathologists' counts disagree, AI makes them agree — and junior pathologists lean on it most.
What it does not yet show
A ring study, not routine practice; agreement is not the same as accuracy against outcomes.
What you can check
Open the Histopathology ring study on AI and PD-L1 CPS and find "0.618".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Li et al. — Artificial intelligence enhances whole-slide interpretation of PD-L1 CPS in triple-negative breast cancer: A multi-institutional ring study, Histopathology (first published 15 May 2024) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.