All Times EDT
Keywords: ML; machine learning; DL; deep learning; AI; artificial intelligence; clinical trials; data science
Pharmaceutical research and development has been slow to apply machine learning (ML) to guide the development and approval of new therapies. However, often the target patient population is heterogeneous and represents a complex disease etiology that limits the performance of traditional statistical method to characterize treatment response. The use of ML methods in disease areas with complex high-dimensional data, where the number of predictors/observations may be large, will allow for better interpretation of complex diseases. The framework may allow for extension from discussing disease correlation to disease mechanism, network, and causation. Further, recent emergence of data science and bioinformatics technology has called upon researchers to respond to arising challenges and embracing the use of ML for drug development and clinical trial optimization in the “Era of Big Data." In this session, we intend to discuss the analytical and computational challenges faced in clinical research and propose novel solutions for drug development and clinical trials that integrate power from various fields of data science to motivating problems. This problem-solving approach attempts to initiate an early discussion in key translational questions of the field. Our goal is to engage the field in the innovation of powerful predictive analytics and connect recent developments in ML to clinical drug development and clinical trial design. In addition, a discussion on the challenges and future of ML will bring efficient and accurate decision making to the forefront of clinical trial design and analysis. The speakers will focus on recent development in ML and delve into solutions for prediction and classification with applications in biomarker, multinomics, and imaging analysis. The group will interactively discuss current uses of ML to learn from and improve upon clinical trials and connect the growing field of ML/AI to the future of clinical trials.