Harnessing Digital Pathology And Causal Learning To Improve Eosinophilic Esophagitis Dietary Treatment Assignment

Eosinophilic esophagitis (EoE) is a chronic, food antigen-driven, allergic inflammatory condition of the esophagus associated with elevated esophageal eosinophils. Second only to gastroesophageal reflux disease, EoE is one of the leading causes of chronic refractory dysphagia in adults and children. Diagnosis of EoE heavily relies on counting eosinophils in histological slides, a manual, laborious, time-consuming task that limits the ability to extract complex patient-dependent features. The treatment for EoE typically involves a combination of medication and dietary changes, particularly food elimination. A personalized, tailor-made food elimination plan is crucial for the patient’s engagement and treatment efficiency. Previous attempts to predict the best food-elimination strategy did not yield significant results. In this work, on the one hand, we utilize AI for inferring many histological features from the entire biopsy slide, features that cannot be extracted manually. On the other hand, we develop causal learning models that can process this wealth of data. We applied our approach to the “Six-Food vs. One-Food Eosinophilic Esophagitis Diet Study” (SOFEED), where 112 symptomatic adults aged 18-60 years with active EoE were assigned to either a six-food elimination diet (6FED) or a one-food elimination diet (IFED) for six weeks. Our results show that the average treatment effect (ATE) of the 6FED treatment compared with the IFED treatment is not significant, that is, neither diet was superior to the other. We examined several causal models and show that the best treatment strategy was obtained using T-learner with two XGBoost modules. While IFED only and 6FED only provide improvement for 35%-38% of the patients, which is not significantly different from a random treatment assignment, our causal model yields a significantly better improvement rate of 58.4%. This work demonstrates the importance of AI in examining the distribution of molecular features within histological slides and integrating them with causal learning to provide better treatment planning. Our approach can be harnessed for other conditions that rely on histology for diagnosis and treatment.