research
A Biopsy Model Inferred the Transcriptome Before Predicting Response
The two-stage system compressed pathology into inferred expression, then combined it with clinical variables.
Summary
The two-stage system compressed pathology into inferred expression, then combined it with clinical variables.
The first stage learned transcriptomic signals from histopathology across 8,742 patients and 32 cancer types. A second stage predicted pathological complete response to neoadjuvant therapy from inferred expression and clinical data. Developed on 1,080 patients and evaluated on 1,412 across nine cohorts, the model reported a pooled AUROC of 0.79; it is a research result, not clinical approval.
Why it matters
The two-stage system compressed pathology into inferred expression, then combined it with clinical variables.
Limits and context
- Developed on 1,080 patients and evaluated on 1,412 across nine cohorts, the model reported a pooled AUROC of 0.79; it is a research result, not clinical approval.
Key claims
The two-stage system compressed pathology into inferred expression, then combined it with clinical variables.
Qualification: Developed on 1,080 patients and evaluated on 1,412 across nine cohorts, the model reported a pooled AUROC of 0.79; it is a research result, not clinical approval.
Evidence: source-2026-10-05-010
Sources
- arXiv preprint 2610.03693arXiv · primary research
Corrections
No corrections have been recorded for this story.