Journal Watch · JAMA Oncology · 2026
Ancestry-Associated Performance Variability of Open-Source AI Models for EGFR Prediction in Lung Cancer.
AI-guided triage analyses showed a potential 57% reduction in rapid EGFR testing, while maintaining sensitivity of 0.84 and specificity of 0.99.<h4>Conclusions</h4>This cohort study found that AI-based pathology tools may serve as preliminary adjuncts for EGFR prediction in lung cancer, though performance differences by ancestry warrant careful interpretation.
TL;DR
AI-guided triage analyses showed a potential 57% reduction in rapid EGFR testing, while maintaining sensitivity of 0.84 and specificity of 0.99.<h4>Conclusions</h4>This cohort study found that AI-based pathology tools may serve as preliminary adjuncts for EGFR prediction in lung cancer, though performance differences by ancestry warrant careful interpretation.
Key findings
- In ancestry-stratified analyses of the DFCI cohort, AUCs for the higher-performing model were 0.84 (95% CI, 0.81-0.86) in patients of European ancestry, 0.85 (95% CI, 0.72-0.94) in African ancestry, and 0.68 (95% CI, 0.55-0.78) in Asian ancestry.
- In sample type analyses, performance declined in pleural (AUC, 0.66; 95% CI, 0.56-0.76) compared with lung specimens (AUC, 0.86; 95% CI, 0.83-0.88).
- AI-guided triage analyses showed a potential 57% reduction in rapid EGFR testing, while maintaining sensitivity of 0.84 and specificity of 0.99.<h4>Conclusions</h4>This cohort study found that AI-based pathology tools may serve as preliminary adjuncts for EGFR prediction in lung cancer, though performance differences by ancestry warrant careful interpretation.
Numbers at a glance (from the abstract)
Every figure above is taken verbatim from the abstract below. Check the full text for denominators, confidence intervals and subgroup detail.
What they did
Data analyses were performed from July 2025 to September 2025.<h4>Main outcomes</h4>The primary outcome was model performance for predicting EGFR mutation status, measured as the area under the receiver operating characteristic curve (AUC), evaluated overall and across ancestry subgroups and sample types.<h4>Results</h4>Overall, 2098 patients with LUAD were included (mean [SD] age, 66.6 [10.3] years; 1315 female individuals [63%] and 783 male individuals [37%]). In the DFCI cohort (n = 1759; 54 African, 101 American, 95 Asian, 1465 European), EGFR mutations were detected in 432 patients (25%). One AI-pathology model achieved an AUC of 0.83 (95% CI, 0.81-0.85) compared with 0.68 (95% CI, 0.65-0.70) for the other model. In the TNM-I cohort (n = 339), EGFR mutations were detected in 50 patients (15%), with AUCs of 0.81 (95% CI, 0.74-0.88) and 0.75 (95% CI, 0.68-0.83), respectively.
Full abstract (original)
Background: <h4>Importance</h4>Artificial intelligence (AI) models are emerging as rapid, low-cost tools for predicting targetable genomic alterations directly from routine pathology slides. Although these approaches could accelerate treatment decisions in lung cancer, little is known about whether their performance is consistent across diverse patient populations and tissue contexts.<h4>Objective</h4>To evaluate the performance and generalizability of 2 open-source AI pathology models for predicting EGFR mutation status in lung adenocarcinoma (LUAD) across independent cohorts and ancestral subgroups.<h4>Design, setting, and participants</h4>This cohort study included patients with LUAD from 2 cohorts: Dana-Farber Cancer Institute (DFCI) from June 2013 to November 2023, and a European-based trial (TNM-I) from August 2016 to February 2022. All patients had paired next-generation sequencing data and hematoxylin-eosin-stained whole-slide images. In the DFCI cohort, genetic ancestry was inferred using germline genotype data.
What they did: Data analyses were performed from July 2025 to September 2025.<h4>Main outcomes</h4>The primary outcome was model performance for predicting EGFR mutation status, measured as the area under the receiver operating characteristic curve (AUC), evaluated overall and across ancestry subgroups and sample types.<h4>Results</h4>Overall, 2098 patients with LUAD were included (mean [SD] age, 66.6 [10.3] years; 1315 female individuals [63%] and 783 male individuals [37%]). In the DFCI cohort (n = 1759; 54 African, 101 American, 95 Asian, 1465 European), EGFR mutations were detected in 432 patients (25%). One AI-pathology model achieved an AUC of 0.83 (95% CI, 0.81-0.85) compared with 0.68 (95% CI, 0.65-0.70) for the other model. In the TNM-I cohort (n = 339), EGFR mutations were detected in 50 patients (15%), with AUCs of 0.81 (95% CI, 0.74-0.88) and 0.75 (95% CI, 0.68-0.83), respectively.
Results & conclusions: In ancestry-stratified analyses of the DFCI cohort, AUCs for the higher-performing model were 0.84 (95% CI, 0.81-0.86) in patients of European ancestry, 0.85 (95% CI, 0.72-0.94) in African ancestry, and 0.68 (95% CI, 0.55-0.78) in Asian ancestry. In sample type analyses, performance declined in pleural (AUC, 0.66; 95% CI, 0.56-0.76) compared with lung specimens (AUC, 0.86; 95% CI, 0.83-0.88). AI-guided triage analyses showed a potential 57% reduction in rapid EGFR testing, while maintaining sensitivity of 0.84 and specificity of 0.99.<h4>Conclusions</h4>This cohort study found that AI-based pathology tools may serve as preliminary adjuncts for EGFR prediction in lung cancer, though performance differences by ancestry warrant careful interpretation.
Abstract © the authors / JAMA Oncology (2026). Reproduced here for discussion and indexing, with attribution. Read the original at https://doi.org/10.1001/jamaoncol.2025.6430 · PubMed 41678173.
Why it matters for pharma & biotech
- Directly relevant to teams in targeted oncology / immuno-oncology, AI in drug discovery / diagnostics — the abstract reports new data in that space, so competitive and pipeline teams should read the full text.
- Because it reports human data, it can inform indication, endpoint and comparator decisions faster than preclinical work.
- For searchers: the full abstract is reproduced below, so you can judge relevance before opening the publisher page.
Modalities & themes detected: targeted oncology / immuno-oncology · AI in drug discovery / diagnostics
Limitations & what to check in the full text
- This brief is based on the published abstract only. Effect sizes, subgroup results and safety detail in the full text may qualify the headline findings.
Frequently asked questions
What did this JAMA Oncology study find?
AI-guided triage analyses showed a potential 57% reduction in rapid EGFR testing, while maintaining sensitivity of 0.84 and specificity of 0.99.<h4>Conclusions</h4>This cohort study found that AI-based pathology tools may serve as preliminary adjuncts for EGFR prediction in lung cancer, though performance differences by ancestry warrant careful interpretation.
What type of study is this?
It is a cohort / observational clinical study, published in JAMA Oncology in 2026. Data analyses were performed from July 2025 to September 2025.<h4>Main outcomes</h4>The primary outcome was model performance for predicting EGFR mutation status, measured as the area under the receiver operating characteristic curve (AUC), evaluated overall and across ancestry subgroups and sample types.<h4>Results</h4>Overall, 2098 patients with LUAD were included (mean [SD] age, 66.6 [10.3] years; 1315 female individuals [63%] and 783 male individuals [37%]).
Where can I read the original paper?
The original is at the publisher via DOI 10.1001/jamaoncol.2025.6430. PubMed ID: 41678173. BioStudioAI reproduces the abstract for discussion and links to the source.
This brief: BioStudioAI Journal Watch, 29 October 2026. https://biostudioai.com/blog/papers/ancestry-associated-performance-variability-of-open-source-ai-models-for-256430/
Reading papers is step one. Analysing the data is the work.
BioStudioAI turns raw lab files into QC'd results, statistics, figures, reports and slides — hosted on your servers, every number computed, nothing typed.
Open BioStudioAI More guides