A multimodal AI biomarker PATH-ORACLE improves prediction of recurrence in stage I lung adenocarcinoma

Key Points

The model achieves over 85% accuracy in predicting recurrence of stage I lung adenocarcinoma, outperforming traditional methods.
A primary focus is on refining risk stratification for patients in both stage IA and IB of lung adenocarcinoma through advanced analysis.
PATH-ORACLE integrates histology and transcriptomics to create a comprehensive risk assessment tool.
Implementation of this multimodal AI biomarker may enhance clinical decisions regarding adjuvant therapy and surveillance.

Abstract

Multimodal AI model (PATH-ORACLE) integrates histology and transcriptomics to predict stage I LUAD recurrencePATH-ORACLE outperforms IASLC grading and transcriptomic or image-based models aloneModel achieves >85% recurrence prediction accuracy across independent international cohortsPATH-ORACLE refines risk stratification within both stage IA and IB lung adenocarcinomaBiomarker may guide adjuvant therapy selection and surveillance in early-stage disease.

Bookmark

View Full Paper

Cite This Study

Kilim et al. (Fri,) studied this question.

synapsesocial.com/papers/69a75f15c6e9836116a2a38c https://doi.org/https://doi.org/10.64898/2026.01.28.26344973

Bookmark

View Full Paper