Konrad Tollman of KTH, Frank Bentley of Motorola, John Moore of New Media Medicine, and Alex Olwal of Camera Culture are organizing a Mobile Wellness workshop at Mobile HCI 2011 on August 30th, 2011 in Stockholm, Sweden. The full-day workshop will focus on the ways in which our mobile devices can aggregate and visualize well-being data and how these data streams can be presented to encourage interaction, increased awareness and positive behavior change. We expect to have outstanding researchers participating from all over the world, so the discussion should be exciting.
Please consider submitting a paper and participating in the workshop. The deadline is April 20th, 2011. More details here.
The Reede Scholars Health Equity Symposium will be held on Thursday May 12, 2011 from 4-7pm at the Joseph B. Martin Conference Center at Harvard Medical School in Boston, MA. The objective of the symposium is to host a multidisciplinary forum to enlist diverse perspectives for creating strategies that promote health equity. John Moore will talk about the potential of technology to improve health literacy and numeracy by engaging patients in personalized experiential learning. The keynote speaker will be Dr. David Blumenthal, the current National Coordinator for Health Information Technology under President Barack Obama.
This is one of the most exciting efforts to address interoperability that we have seen. It does not aim to replace a personal health record, which we are glad to hear since we are big supporters of patient ownership and control of health information and Indivo X in particular. Instead the goal of the platform is to standardize services that are critical for data capture, storage, retrieval, and analysis. This will hopefully accelerate the development of innovative applications for patient empowerment and also help to ensure that these applications reach the people who need them. So we are looking forward to seeing what you build!
During Health and Wellness Innovation 2011, The Microsoft Kinect was also used by Jin Joo Lee (Personal Robots group at the MIT Media Lab) to advance her research in modeling the dynamics of social interaction. Her goal is to better understand the subtle cues in human-human communication in order to improve human-robot interactions. Her project applies machine learning and gesture recognition algorithms to the motion capture data from the Kinect in order to detect nonverbal cues including mimicry and synchronous movement.
Improved understanding and tracking of the dynamics of social interaction will have a significant impact on the future of healthcare delivery. Remote medical care is becoming a reality. Many healthcare institutions have telemonitoring programs, and a number of solutions, like American Well, are becoming available online. The issue is that the fidelity of social interactions is currently blunted by the affordances of the technology being used, namely simple webcams. Important social cues will be dropped, but the efficiency and cost-effectiveness of new models of care delivery will likely prove their benefit even in the case of its failures due to miscommunication. New technologies for tracking social cues, however, will improve fidelity and allow even greater advances in care. Body language tracking and facial expression tracking will cue clinicians in to unnoticed patient needs and will help to bolster rapport. This technology may even prove helpful in face-to-face interactions.
Automated on-screen agents and physical robots will also have a significant role in the future of healthcare delivery. Tim Bickmore of Northeastern University, a graduate of the Affective Computing group, has shown overwhelmingly positive patient responses to relational agents, especially in a recent study of the hospital discharge process. Cory Kidd, a graduate from the Personal Robots Group and the founder of Intuitive Automata, produced a substantial research study on the use of a robot as a home weight loss coach. Their research has been successful, even though current on-screen agents and physical robots lack the ability to develop rapport as rich as a humans, because they leveraged the advantages of technology. An on-screen agent has infinite patience. It does not interrupt or keep its hand on the doorknob during conversations. A robot can be there for the patient 24 hours a day, can log information carefully, and can provide meaningful feedback for self-reflection. Improved tracking of the dynamics of social interaction will only improve the potential of these tools. They will be more capable of engaging patients in their care and motivating them to make positive health-related behavior change.
The management of heart failure is the classic example the success of telemedicine. Hospital systems and clinics throughout the world have adopted solutions to measure daily weights and vital signs from patients. They have assembled teams to monitor the data and to communicate with the patients when trends suggest decompensation. Emergency rooms visits are prevented and healthcare costs are reduced.
The use of telemedicine for heart failure is a great step in the right direction, but there is definitely room for improvement. The problem with most systems is that their philosophy revolves around doctors or nurses siphoning data from patients and returning directives. This approach does not promote patient self-efficacy and is costly because of the heavy reliance on professionals to interpret data and make decisions. It helps to keep patients stable, but it does not motivate them to improve their condition.
The Esoma Exercise System aims to shift cardiac rehabilitation to a patient-centered approach. Patients will play games powered by Microsoft Kinect and computer vision algorithms that recognize the execution of rehab exercises. Patients will wear physiological sensors while playing the games that monitor heart rate, blood oxygenation, etc. Rich feedback about their progress and improvement in physiological state will be embedded in the game to motivate self-efficacy. There will still be clinicians on the other side of the server, but they will act more as coaches that help patients make decisions for themselves based on the data. The system is being built as a CollaboRhythm plug-in so that it can benefit from the powerful tools for data visualization, communication, and social support.
During Health and Wellness Innovation 2011, Ryan Orendorff from Tufts built a prototype of Esoma that tracks typical cardiac rehabilitation exercises for patients with relatively poor reserve. He is developing algorithms that allow the system to be taught new exercise through example. The system will then be able to track those trained exercises for any patient. The next steps will be to incorporate the algorithms into a game, to incorporate the physiological sensors, and to integrate with CollaboRhythm.
No respectable Health and Wellness Innovation activity would address diet management without also tackling physical activity. StepWatch was a collaboration between Frank Bentley of Motorola, Cristobal Viedma of the Mobile Services Lab of Wireless@KTH, and Peter Stephenson and Adam Bell of Humana. This group dug into the Indivo X code to enhance its flexibility and reporting functionality when dealing with vital signs. They were able to store pedometer data and execute powerful queries that supported novel visualizations of step counts. Daily step goals can be difficult to manage, so the visualizations of StepWatch provide constant feedback of progress throughout the day.
This project is an exciting example of how creative researchers working on a common platform will be able to accelerate progress. During Health and Wellness Innovation 2011, this team along with a number of other MIT Media Lab sponsors and research groups came together to discuss their approaches to storing health-related data. They were able to identify commonality in their needs and began extending Indivo X in a way that would support a broader range of research. More researchers using the same platform not only means faster progress and more collaboration, but it means new opportunities for studying correlations in data.
Obesity is epidemic in America. Researchers around the world are trying to use technology to quantify eating habits and caloric intake with the hope that this information can be used to change behavior. Maybe we will see some people at restaurants taking pictures of their food or scanning barcodes, but is more likely that these burdensome approaches will give way to more passive techniques. Ubiquitous computing developments will allow your cell phone to aggregate pictures of your food from cameras in the environments where you eat. And the earpiece that you wear to talk on the phone will record the sounds of mastication (check out the work of Dr. Oliver Amft at TU Eindhoven and Edward Sazanov at Clarkson University). And all this data will be linked with the purchases that you make. The purchases can be used to query detailed data about the food and analysis of the pictures and sound will reveal how much of it you actually ate and when, all without any effort on your part. So it is clear that it will be possible for people to aggregate detailed information about their eating habits in the near future. The main question to ask is: Is this going to help? Are people going to change their eating behavior just because it is quantified. The answer is probably no. But it may be possible to help them change if the information is presented through meaningful and actionable interfaces with gaming elements and social support layered on top.
Chang Beom Lee MD PhD from the Hanyang University Medical School in Korea is a Visiting Scholar at the Harvard School of Public Health. During Health and Wellness Innovation 2011, he focused on learning about the latest techniques for quantify dietary intake. As a start, he worked on daily visualizations of dietary feedback that aim to improve self-reflection and promote positive change. By leveraging the CollaboRhythm platform in the future, users will be able to share their progress, compete with friends, and receive supportive messages from their dietician.
Patient adherence to physical therapy regimens is poor, and there is a lack of quantitative data about patient performance, particularly at home. Oovit PT aims to build an end-to-end virtual rehabilitation system for supporting patient adherence to home exercise that addresses the multi-factorial nature of the problem. During Health and Wellness Innovation 2011, Sai Moturu of the New Media Medicine group at the MIT Media Lab developed Oovit PT into a 3D game. The heel-slide exercise becomes a fun variation of shuffleboard that encourages the patient to perform the exercise correctly in order to achieve higher scores. Oovit PT is being developed as a CollaboRhythm plug-in so that the physical therapist can remotely monitor rehab performance, adjust goals, and provide social support.