Shai Fine: "From Wearable Sensors to Deep Learning, and more"

Digital Health is rapidly becoming a major theme in the Healthcare realm. Coupled with Personalized Medicine, It provides the means to track and monitor condition, and suggest treatments that are far more effective than ever before. It also poses major challenges in collecting and digesting big amounts of data, which in turn should be analyzed in order to detect, predict and suggested the best course of action. Thus, in recent years, there's a growing interest in employing advanced Machine Learning methods using data from smart medical devices and from sensors (e.g. wearable, environmental), as well as patient-specific data from Electronic Medical Records (EMRs).

In this talk I will describe a recent work at the intersection of Digital Health and Machine learning, while focusing on modelling challenges and presenting a few practical use cases. A major part of the talk will be dedicated to mHealth challenges, where data is continuously collected from mobile and wearable devices in order to monitor, detect, and predict states and events of interest, such as movement disorder, sleep/wake patterns, onset of headache attacks, etc. The analysis of time series data using Deep Learning methods will be demonstrated, towards solving a state detection problems. In addition, a more generic analysis and characterization of Deep Learning and specifically Convolutional Neural Networks (CNN) will be briefly discussed. We will conclude with yet another Big Data Analytics use case, leveraging Real Word Evidence data to assess the risk of asthmatic patients to experience asthma exacerbation(s) in the future.