AI-Driven Predictive Biomarker Discovery with Contrastive Learning to Improve Clinical Trial Outcomes

Résumé fourni par la source

ABSTRACT Modern clinical trials can capture tens of thousands of clinicogenomic measurements per individual. Discovering predictive biomarkers, as opposed to prognostic markers, is challenging when using manual approaches. To address this, we present an automated neural network framework based on contrastive learning—a machine learning approach that involves training a model to distinguish between similar and dissimilar inputs. We have named this framework the Predictive Biomarker Modeling Framework (PBMF). This general-purpose framework explores potential predictive biomarkers in a systematic and unbiased manner, as demonstrated in simulated “ground truth” synthetic scenarios resembling clinical trials, well-established clinical datasets for survival analysis, real-world data, and clinical trials for bladder, kidney, and lung cancer. Applied retrospectively to real clinicogenomic data sets, particularly for the complex task of discovering predictive biomarkers in immunooncology (IO), our algorithm successfully found biomarkers that identify IO-treated individuals who survive longer than those treated with other therapies. In a retrospective analysis, we demonstrated how our framework could have contributed to a phase 3 clinical trial ( NCT02008227 ) by uncovering a predictive biomarker based solely on early study data. Patients identified with this predictive biomarker had a 15% improvement in survival risk, as compared to those of the original trial. This improvement was achieved with a simple, interpretable decision tree generated via PBMF knowledge distillation. Our framework additionally identified potential predictive biomarkers for two other phase 3 clinical trials ( NCT01668784 , NCT02302807 ) by utilizing single-arm studies with synthetic control arms and identified predictive biomarkers with at least 10% improvement in survival risk. The PBMF offers a broad, rapid, and robust approach to inform biomarker strategy, providing actionable outcomes for clinical decision-making.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.