Deep Patient: Predict the Medical Future of Patients with Machine Learning and EHRs.

Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous healthcare data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records (EHRs), imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking sufficient domain knowledge. Deep learning provides effective paradigms to obtain end-to-end multi-modal learning models that promise to unlock relevant insights, which can boost medical research and clinical decision support. In this talk, we review the benefit of using deep learning technologies to advance the health care domain, with particular focus on applications to EHRs.

Dr. Riccardo Miotto is a Director of Machine Learning at Tempus Labs, working at the intersection between computer science and healthcare. His primary expertise encompasses the study and design of novel frameworks to process multi-modal data for personalized medicine and medical search engines.