Abstract Background. Up to 80% of patients in the early stages of gastric cancer are asymptomatic, making early diagnosis and hence effective treatment challenging. The poor prognosis of patients with late diagnoses clearly necessitates the identification of markers for early detection and the development of streamlined screening protocols. This is particularly crucial in high-risk populations, for example regions in which Helicobacter Pylori infection and associated chronic inflammation, responsible for over 70% of gastric cancers worldwide, is prevalent. At present, an efficient and personalized program for early detection does not exist. Methods. Specific biomarkers for the progression of gastric cancer have been identified in preliminary studies, including CD44, Lgr5 and CD133. In retrospective tissue samples incremental increases in expression of these markers was observed during the progression from normal gastric tissue to precancerous histologic lesions such as intestinal metaplasia and ultimately dysplasia and carcinoma. We developed a mechanistic mathematical model capable of simulating these marker-positive population dynamics, calibrated using the existing clinical data. The predictive capability of the model is validated by comparison of simulated to actual marker expression patterns in an independent test cohort of endoscopic gastric biopsies taken at sequential points during individual patients’ disease progression. Results. Based on clinically obtainable, patient-specific tissue conditions, the computational model can simulate the dynamics of marker-positive cells and, when calibrated and validated with clinical data from specific patient populations, may forecast disease progression and suggest optimal screening schedules for individual patients. Conclusions. The tools of mathematical oncology have the potential to directly inform clinical screening protocols. Verified prognostic factors for disease progression can be incorporated into mathematical models to improve diagnostic accuracy and allow clinically-actionable screening optimization. This can guide personalized screening schedules according to current marker expression on a case-by-case basis to achieve more efficient prognosis and reduced healthcare costs. Citation Format: Rachel Walker, Jaime Mejia, Heiko Enderling, Jose M. Pimiento, Domenico Coppola. Cross-disciplinary methods for personalizing screening modalities for early gastric cancer intervention. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 1523.