Title: Oblivious physiological monitoring to anticipate health events

Abstract: In this talk, I will share some of the experiences we made bringing novel sensing technologies into the wild and deploying them in representative environments for real-world insights. My talk will focus on our efforts in cardiovascular monitoring and its interplay with sleep quality, which jointly are considerable enablers and inhibitors of daytime performance and quality of life.

Bio: Christian Holz is an assistant professor in Computer Science at ETH Zürich, where he leads the Sensing, Interaction and Perception Lab. His research focuses on wearable and continuous healthcare monitoring as well as building platforms for automated health monitoring and predictive diagnostics. Christian's background is in human-computer interaction, which he combines with hardware engineering, machine learning, and experimental methods for validation under ecologically valid conditions. Before joining ETH, Christian was a research scientist at Microsoft Research in Redmond, Washington. More info here.

Title: Sensors at Work: Personal Devices for Supporting Well-Being and Productivity

Abstract: Personal devices – such as smartphones, smartwatches, and the like – can nowadays support their users in a plethora of tasks, including, e.g., tracking water intake or monitoring sleep quality. At the workplace, such devices, combined with ambient intelligence, can help people improve their well-being and productivity. In this talk, we will discuss the relationship between well-being and productivity and showcase examples from our recent work on how indicators related to productivity can be inferred leveraging multi-sensory data.

Bio: Silvia Santini is an Associate Professor at the Faculty of Informatics of the Università della Svizzera italiana (USI) in Lugano, Switzerland. She previously held appointments as Assistant Professor at TU Darmstadt and as Associate Professor TU Dresden, Germany, as well as senior researcher at ETH Zurich, Switzerland. She holds a master’s degree (with honors) in telecommunication engineering from the Sapienza University of Rome and a PhD in Computer Science from ETH Zurich. Silvia’s research focus is on mobile and wearable computing and in particular on the design of novel models and systems for modeling human behavior and supporting well-being and productivity at work. Silvia is one of the founding Editors and the current Editor-in-Chief of the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Computing Technologies (PACM IMWUT), the leading journal for research on ubiquitous and wearable computing systems. She is a member of the Steering Committee of the UbiComp conference series and has served on the Technical Program Committees of several leading venues in the fields of mobile computing, ubiquitous and wearable computing, internet of things and cyber-physical systems, including MobiSys, SenSys, IPSN, InfoCom, and more. Silvia is also a member of USI’s University Senate and of USI’s University Council, and an engaged promoter of a more inclusive leadership culture within academia and beyond.

Title: Machine Learning in Mental Health

Abstract: Recent advances in AI and machine learning (ML) promise significant transformations in the future delivery of (mental) healthcare. Despite a surge in research and development, few works have moved beyond demonstrations of technical feasibility and algorithmic performance. However, to realize many of the ambitious visions for how AI can contribute to clinical impact requires the closer design and study of ML tools or interventions within specific health and care contexts. This talk draws on Project Talia, a recently retired, three-year research collaboration between Microsoft Research and SilverCloud Health, to describe current challenges and opportunities for applications of ML in mental health when designing for real-world implementation. SilverCloudHealth is an evidence-based, digital, on-demand mental health platform that delivers Cognitive-Behavioral Therapy (iCBT) programs for patients with mild-to-moderate symptoms of depression, anxiety, and stress. Patients work through therapy contents by themselves in their own time in combination with regular assistance from an iCBT supporter, who provides guidance and continuous encouragement to the patient and helps them work through identified difficulties. Aiming to maximize the effects and outcomes of human support in this format, the collaboration explored how methods of ML could assist iCBT supporters in providing more effective, personalized care to their patients. To this end, the talk will give an introduction to three specific invstigations for deriving ML insights: (1) user subtyping based on patterns of engagement; (2) extracting context-specific communication patterns; and (3) predicting reliable improvement outcomes. It closes with broader socio-technical considerations and challenges involved for the responsible design and workflow integration of ML within sensitive healthcare contexts.

Bio: Anja is a Senior Researcher in the Biomedical Imaging team within Microsoft Health Futures, based at Microsoft Research Cambridge. Her research explores innovative approaches for applying AI and Machine Learning in real-world healthcare contexts with a focus towards end-to-end AI application development. As a researcher with a background in human-computer interaction (HCI) much of her work focuses on the responsible design of AI technology to benefit people.