Foundation Model for Predicting Prognosis and Adjuvant Therapy Benefit From Digital Pathology in GI Cancers

Clinical Snapshot

Key Findings

• P Value: Treatment-model interaction P = 0.01 (gastric) and 0.006 (colorectal)

• Effect Size: Concordance index 0.726-0.797 for gastric cancer, 0.714-0.757 for colorectal cancer

• Primary Outcome: Disease-free survival and disease-specific survival prediction

• Nnt Or Sensitivity: 5-year survival: high-risk 49-52% vs low-risk 76-92% (gastric), 43-72% vs 81-98% (colorectal)

• Confidence Interval: Not reported in abstract

Clinical Application

Requires digital pathology infrastructure and AI implementation, pending regulatory approval Relevant to Australian oncology practice; would require TGA approval for clinical use, potential integration with existing pathology services, alignment with Cancer Australia guidelines Patients with gastrointestinal cancers requiring prognostic assessment and adjuvant therapy decisions

Abstract

PURPOSE: Artificial intelligence (AI) holds significant promise for improving cancer diagnosis and treatment. Here, we present a foundation AI model for prognosis prediction on the basis of standard hematoxylin and eosin-stained histopathology slides. METHODS: In this multinational cohort study, we developed AI models to predict prognosis from histopathology images of patients with GI cancers. First, we trained a foundation model using over 130 million patches from 104,876 whole-slide images on the basis of self-supervised learning. Second, we fine-tuned deep learning models for predicting survival outcomes and validated them across seven cohorts, including 1,619 patients with gastric and esophageal cancers and 2,594 patients with colorectal cancer. We further assessed the model for predicting survival benefit from adjuvant chemotherapy. RESULTS: The AI models predicted disease-free survival and disease-specific survival with a concordance index of 0.726-0.797 for gastric cancer and 0.714-0.757 for colorectal cancer in the validation cohorts. The models stratified patients into high-risk and low-risk groups, with 5-year survival rates of 49%-52% versus 76%-92% in gastric cancer and 43%-72% versus 81%-98% in colorectal cancer. In multivariable analysis, the AI risk scores remained an independent prognostic factor after adjusting for clinicopathologic variables. Compared with stage alone, an integrated model consisting of stage and image information improved prognosis prediction across all validation cohorts. Finally, adjuvant chemotherapy was associated with improved survival in the high-risk group but not in the low-risk group (treatment-model interaction P = .01 and .006) for stage II/III gastric and colorectal cancer, respectively. CONCLUSION: The pathology foundation model can accurately predict survival outcomes and complement clinicopathologic factors in GI cancers. Pending prospective validation, it may be used to improve risk stratification and inform personalized adjuvant therapy.

References

1. 1.Wang, X., Jiang, Y., Yang, S., Wang, F., Zhang, X., Wang, W., Chen, Y., Wu, X., Xiang, J., Li, Y., Jiang, X., Yuan, W., Zhang, J., Yu, K.-H., Ward, R. L., Hawkins, N., Jonnagaddala, J., Li, G., & Li, R. (2025). Foundation model for predicting prognosis and adjuvant therapy benefit from digital pathology in GI cancers. Journal of Clinical Oncology. https://doi.org/10.1200/JCO-24-01501