DEVELOPMENT OF FEDERATED LYMPHOMA CLASSIFICATION MODELS ACROSS MULTIPLE HARMONIZED COHORTS OF PATIENTS WITH PRIMARY SJÖGREN’S SYNDROME

Primary Sjögren’s Syndrome (pSS) is a chronic autoimmune disease followed by exocrine gland dysfunction, where it has been long stated that 5% of pSS patients are prone to lymphoma development. In this work, we present a federated AI (artificial intelligence) strategy which enables the federated training and validation of AI algorithms for lymphoma classification across 21 European cohorts with pSS patients. Advanced AI algorithms were developed, including federated gradient boosting trees with and without dropouts, federated Multilayer Perceptron and federated Multinomial Naïve Bayes. Two large-scale case studies were conducted to demonstrate the applicability and robustness of the federated AI models, where emphasis is given on class imbalance handling and explainability analysis. The federated gradient boosting trees with dropouts achieved the best classification performance yielding more than 0.8 sensitivity and specificity along with 5 biomarkers as prominent for lymphoma development and progression.

Informatics Approaches to Address New Challenges in the Classification of Lymphoid Malignancies

Purpose Lymphoid malignancies are remarkably heterogeneous, with variations in outcomes and clinical, biologic, and histologic presentation complicating classification according to the World Health Organization guidelines. Incorrect classification of lymphoid neoplasms can result in suboptimal therapeutic strategies for individual patients and confound the interpretation of clinical trials involving personalized, class-based treatments. This review discusses the potential role of pathology informatics in improving the classification accuracy and objectivity for lymphoid malignancies. Design We identified peer-reviewed publications examining pathology informatics approaches for the classification of lymphoid malignancies, reviewed developments in the lymphoma classification systems, and summarized computational methods for pathologic assessment that can impact practice. Results Computer-assisted pathology image analysis algorithms in lymphoma most commonly have been applied to follicular lymphoma to address biologic heterogeneity and subjectivity in the process of classification. Conclusion Objective methods are available to assist pathologists in lymphoma classification and grading, and have been demonstrated to provide measurable benefits in specific contexts. Future validation and extension of these approaches will require datasets that link high resolution pathology images available for image analysis algorithms with clinical variables and follow up outcomes.