ArticleNature biomedical engineering2026
Confounding factors and biases abound when predicting molecular biomarkers from histological images.
Article in Nature biomedical engineering, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 7 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
7 citing papers in PubMed.
- Reading tumor ecosystems from routine histology.Cell research · 2026Article
- Subspecialty-specific foundation model for intelligent gastrointestinal pathology.NPJ digital medicine · 2026Article
- NeuroFM: Toward Precision Neuroimaging with Foundation Models for Individualized Brain Health Estimation.medRxiv : the preprint server for health sciences · 2026Article
- Pan-Cancer Prediction of Genomic Alterations from H&E Whole-Slide Images in a Real-World Clinical Cohort.Genes · 2026Article
- Peripheral blood biomarkers in PD-1/PD-L1 immunotherapy: distinguishing predictive from prognostic biomarkers.Frontiers in immunology · 2026Review
- An evaluation of pathology foundation models with weakly supervised learning for BRAF mutation prediction in melanoma whole slide images.Frontiers in medical technology · 2026Article
- Explainable AI for computational pathology identifies model limitations and tissue biomarkers.ArXiv · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
Deep learning models that infer clinically relevant biomarker status from tissue images are being explored as rapid and low-cost alternatives to molecular testing. Here we show, through statistical analysis across multiple cancer types, datasets and modelling approaches, that the datasets used to train these models contain strong dependencies between biomarkers and clinicopathological features, which prevent models from isolating the effect of a single biomarker and lead them to learn confounded signals. Consequently, their prediction accuracy varies substantially with the status of codependent biomarkers and clinicopathological variables, and for several biomarkers, the gain over what a pathologist can already infer from routine histopathological features, such as grade, remains modest. These findings indicate that current approaches are not yet suitable as substitutes for molecular testing but can support triage or complementary decision-making with caution. Unconfounded biomarker prediction will require models that learn causal rather than correlational relationships between biomarkers and tissue morphology.
Identifiers
41772176What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.