Abstract
The use of depth-sensing computer vision to capture bodily movement is increasingly being exploited in healthcare. Yet, there are few descriptions of how real-world practices influence the design of such applications. To this end, we present the development and empirical evaluation of ASSESS MS, a system to support the clinical assessment of Multiple Sclerosis using Kinect. A key issue for developing machine-learning based systems is the need for standardized data on which statistical inferences can be made. We demonstrate that there are many aspects of clinical practice that are at odds with the need to capture standardized data for a computer vision system. We offer three design guidelines so address these: 1) Standardization is a multi-disciplinary issue and needs to be addressed early in the development process; 2) Tools that provide a view into what the camera “sees” can support the achievement of standardized data capture in real environments; 3) Tools to support standardized data capture should maintain the agency of human interaction. More broadly we show that when considering every day contexts, the traditional focus on measurement accuracy is only a small part of the effort needed to make a technology “work” in practice.
Additional information
Funding
Notes on contributors
Cecily Morrison
Cecily Morrison ([email protected]) is an Interdisciplinary Researcher with an interest in healthcare and well-being; she is a Postdoc Researcher in the Human Experience & Design Group at Microsoft Research Cambridge, UK. Kit Huckvale ([email protected]) is a PhD candidate working on the use of apps in Healthcare at the Global eHealth Unit, Department of Primary Care and Public Health at Imperial College London; he was a Research Intern at Microsoft Research Cambridge when this work was carried out. Bob Corish ([email protected]) is a Design Researcher with an interest in UX and critical design working in the Human Experience & Design Group at Microsoft Research Cambridge, UK. Jonas Dorn ([email protected]) is a materials engineer turned computational cell biologist with an interest in image and data analysis. He is a Senior Modeler at Novartis Pharma AG, Basel, Switzerland. Peter Kontschieder ([email protected]) is a Computer Scientist with interest in Machine Learning for Computer Vision problems like image/video categorization and semantic segmentation. He is currently a Postdoc Researcher in the Machine Learning and Perception group of Microsoft Research in Cambridge, UK. Kenton O’Hara ([email protected]) is a Social Scientist with an interest in sociotechnical practices; he is a Research Scientist in the Human Experiences and Design Group at Microsoft Research, Cambridge and a Visiting Professor in Computer Science at the University of Bristol. ASSESS MS Team is composed of our clinical colleagues who participated in the ASSESS MS project: Dr. Frank Dahlke ([email protected]), Global Program Head at Novartis Pharma AG; Prof. Dr. Ludwig Kappos, Chair of Neurology, University Hospital Basel, Basel, Switzerland ([email protected]); Prof. Dr. Bernard Uitdehaag, Director of MS Center Amsterdam, VUmc, Amsterdam, the Netherlands ([email protected]); Dr. Jessica Burggraaff ([email protected]), Neurologist at Department of Neurology, VU University Medical Center, Amsterdam, the Netherlands; Dr. Christian Kamm ([email protected]) and Dr. Saskia Steinheimer ([email protected]), Neurologists at Department of Neurology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland; Dr. Marcus D’Souza ([email protected]), Neurologist at Department of Neurology, University Hospital Basel, Basel, Switzerland. Antonio Criminisi ([email protected]) is a Research Scientist with an interest in computer vision and machine learning; he is a Principal Researcher in the Machine Learning and Perception group of Microsoft Research, Cambridge. Abigail Sellen ([email protected]) is a Cognitive Scientist with an interest in different aspects of HCI; she is Manager of the Human Experience & Design group at Microsoft Research Cambridge, UK.