Ongoing uptake in the implementations of clinical trial management and electronic medical records infrastructure has resulted in creation of large amounts of medical data, detailing various stages of the disease onset, progression and outcomes, at an unprecedented level of detail. Given this enormous increase in healthcare data volumes, our ability to effectively share, integrate and analyze is critical to advancing our understanding of the disease and bringing affordable and efficacious treatments to patients. Due to the breadth and depth of the healthcare data across various modalities such as clinical, genomics, imaging and digital sensors, we need to move beyond traditional methods and bring advanced ML/AI implementations to maximally benefit from the richness of the collected data. As part of the drug development life-cycle vast amounts of clinical trials data are collected in order to identify targets of interest, discover biomarkers to stratify patients who could benefit from the drug, and to study the safety and benefit profile of the drug. Furthermore, after the drug is brought to the market its use in a broader population is collected in a wide range of real-world data sources including, but not limited to, electronic medical records, disease registries, health insurance claims, and digital devices. While in recent years we have seen innovative applications of AI/ML leveraging rich medical data, we as a community have not been able to combine the power of AI/ML and rich multi-modal datasets to deliver truly personalized care for patients.

This track will invite experts from industry, academia and startups to share their experiences in using AI/ML for Pharma R&D usecases in drug discovery and development to showcase successful implementations and also lay the roadmap of future methodological and application innovations accelerating use of ML/AI within Pharma research.