> ## Content Index
> Fetch the complete content index at: https://www.coios.me/llms.txt
> Use this file to discover other available public pages before exploring further.

# AI on breast biopsy slides flagged intermediate-risk patients who gained from chemotherapy
- URL: https://www.coios.me/ai-on-breast-biopsy-slides-flagged-intermediate-risk/
- Published: 2026-09-23T13:06:00.000Z
- Updated: 2026-09-23T21:35:33.000Z
- Description: Applied without retraining to 6,735 TAILORx trial participants, an AI model reading H&E slides alongside clinical variables predicted disease-free interval (C-index 0.736) and, within the intermediate-risk group, separated patients who gained from chemotherapy from those who did not.
- Author: Daniel Ryan
- Tags: Emergent technology, AI in medicine, Cancer, United States, #preprint, #refines, #item, #source-2026-09

A prespecified analysis of the TAILORx randomised trial applied an AI model reading H&E pathology slides alongside clinical variables to 6,735 node-negative, hormone receptor-positive breast cancer patients, with no TAILORx data used in training. The score was associated with disease-free interval in both treatment arms and remained significant after adjustment for the 21-gene Recurrence Score, and within the intermediate-risk group it identified a chemotherapy benefit (5 percentage points higher 5-year disease-free interval) that the genomic assay itself did not detect (interaction p=0.001 for the AI score against p=0.20 for the genomic score).

*Why it is interesting: An externally validated, prespecified test of image-based AI as a predictive rather than merely prognostic marker, in a randomised trial where the genomic assay itself found no such interaction.*

Source

[medRxiv, 20 September 2026](https://doi.org/10.64898/2026.09.12.26362500?ref=coios.me)

DOI

10.64898/2026.09.12.26362500

Type

Preprint

Design

Prespecified secondary analysis of the TAILORx phase 3 randomised trial, 6,735 patients with H&E slides and 21-gene Recurrence Score, using an AI model not trained on trial data

Verdict

Refines prior evidence

Driver

[AI in medicine](https://www.coios.me/d-ai-medicine/)

Driver

[Cancer](https://www.coios.me/d-cancer/)