Ancestry-Associated Performance Variability of Open-Source AI Models for Prediction in Lung Cancer

Do open-source artificial intelligence (AI) models for predicting mutations from pathology slides perform consistently across patient populations and clinical settings?In this multicohort study of 2098 patients with lung adenocarcinoma from the US and Europe, open-source AI approaches achieved high accuracy for prediction and demonstrated overall robust performance. Subgroup analyses revealed lower accuracy in Asian patients and pleural tissue samples.AI-based histology tools show strong potential as rapid, low-cost adjuncts for identifying mutations; broader validation and recalibration across diverse populations and tissue types will help ensure equitable clinical adoption and maximize their impact in cancer care.

Corresponding Author: Mehrdad Rakaee, PhD, Department of Cancer Genetics, Institute for Cancer Research, Oslo University Hospital, Oslo 0379, Norway (mehrdadr@uio.no).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.