Moving Beyond Mutation: AI-driven Functional Precision Medicine for Cancer

Accurate prediction of anticancer drug efficacy on each patient’s cancer before the initiation of therapy has the potential to significantly reduce the treatment burden and enhance clinical outcomes. Because cancer is a systematic disease, we need to analyze a patient’s cancer cells in many aspects and combine complex biological and clinical data. This session will introduce a precision medicine platform that predicts anticancer drug efficacy and prognosis evaluation by combining a patient’s live-cell-based ex vivo drug sensitivity assay, immune profiling, blood work, and genotyping with computational modeling that uses artificial intelligence (AI) algorithms. We will cover basic concepts of AI and machine-learning-based predictive models and see how powerful it is to apply machine learning algorithms in improving cancer treatment outcomes.

Learning Objectives:

1. Discuss the concepts of machine learning (ML) and functional precision medicine.

2. Explain the essentials to build successful machine learning models.

3. Discuss how artificial intelligence (AI) models built on patients' live-cell analytics help predict anticancer drug response and prognosis and provides clinical benefits in risk stratification and treatment selection in the real world.