*mHealth Connect attendee
|#1||Fitabase Ernesto Ramirez*|
|#2||Online Actions with Offline Impact: How Online Social Networks Influence Online and Offline User Behavior Tim Althoff*, Pranav Jindal, Jure Leskovec|
Many of today’s most widely used computing applications utilize social networking features and allow users to connect, follow each other, share content, and comment on others’ posts. However, despite the widespread adoption of these features, there is little understanding of the consequences that social networking has on user retention, engagement, and online as well as offline behavior. Here, we study how social networks influence user behavior in a physical activity tracking application. We analyze 791 million online and offline actions of 6 million users over the course of 5 years, and show that social networking leads to a significant increase in users’ online as well as offline activities. Specifically, we establish a causal effect of how social networks influence user behavior. We show that the creation of new social connections increases user online in-application activity by 30%, user retention by 17%, and user offline real-world physical activity by 7% (about 400 steps per day). By exploiting a natural experiment we distinguish the effect of social influence of new social connections from the simultaneous increase in user’s motivation to use the app and take more steps. We show that social influence accounts for 55% of the observed changes in user behavior, while the remaining 45% can be explained by the user’s increased motivation to use the app. Further, we show that subsequent, individual edge formations in the social network lead to significant increases in daily steps. These effects diminish with each additional edge and vary based on edge attributes and user demographics. Finally, we utilize these insights to develop a model that accurately predicts which users will be most influenced by the creation of new social network connections.
|#3||Amazfit Frederik Hermann*, Joseph Munaretto*, Fei Wang*|
|#4||Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) Simona Carini1*, Jim Rehg2*|
1UC San Francisco, 2Georgia Tech
|#5||Embrace, a Wearable Seizure Detection System: Case Study of a Patient Monitored for 3 Months R. Picard1,2, G. Regalia1, C. Caborni1, M. Migliorini1, F. Onorati1|
Presented by Matteo Lai1*
2MIT Media Lab, Massachusetts Institute of Technology Embrace is a wrist-worn device and smartphone-based convulsive seizure (CS) detection and alert system, which analyses acceleration and electrodermal activity data from the patient and provides an alert to caregivers when an unusual event is detected. A patient with Dravet Syndrome (14 y.) was enrolled in the first trial of Embrace in the outpatient setting and wore the device over a period of 113 days. The patient’s caregiver annotated the occurrence of each CS and any activity triggering an alert. The number of false alarms (FAs) was obtained by subtracting the number of recognized CSs from the total alerts. Embrace detected 22 out of 24 CSs (Sensitivity=92%), missing 2 CSs with mild brief motor convulsions. The total number of FAs was 39 (FA rate=0.48 per day worn), typically generated by activities such as hands clapping and car transport. These performances are comparable to results obtained in best-case clinical settings[1-3].  Poh M-Z, Loddenkemper T, Reinsberger C, et al. Convulsive seizure detection using a wrist-worn electrodermal activity and accelerometry biosensor. Epilepsia 2012; 53(5):e93–7.
 Regalia G, Onorati F, Migliorini M, Picard R W, “An improved wrist-worn convulsive seizure detector based on accelerometry and electrodermal activity sensors”, American Epilepsy Society Annual Meeting, Philadelphia (PA), USA, 2015.
 Onorati F, Regalia G, Caborni C, Picard R W, “Improvement of a convulsive seizure detector relying on accelerometer and electrodermal activity collected continuously by a wristband,” Epilepsy Pipeline Conference, San Francisco (CA), USA, 2016.
|#6||Digital Health: Consumer Wearable Devices for Health Surveillance and Disease Monitoring Jessilyn Dunn*, Xiao Li, Denis Salins, Michael Snyder*, Scott Delp*|
A new wave of portable biosensors allows frequent measurement of health-related physiology. We investigated the use of these devices to monitor human physiological changes during various activities and their role in managing health and diagnosing and analyzing disease. By recording over 250,000 daily measurements for up to 43 individuals, we found personalized circadian differences in physiological parameters, replicating previous physiological findings. We combined biosensor information with frequent medical measurements and found that wearable devices were useful in identification of early signs of Lyme disease and inflammatory responses; we used this information to develop a personalized, activity-based normalization framework to identify abnormal physiological signals from longitudinal data for facile disease detection. Overall, our results indicate that portable biosensors provide useful information for monitoring personal activities and physiology and are likely to play an important role in managing health and enabling affordable health care access to groups traditionally limited by socioeconomic class or remote geography.
|#7||Samsung Health and GearHUB Overview Nitesh Jain*|
Samsung Health is the single destination for all health needs. Samsung GearHUB is an API platform for wearables to launch turnkey health, productivity and safety services.
|#8||Quantifying Rehabilitation Outcomes from Wearables and Smartphones Data Chaithanya K Mummidisetty MS*, Luca Lonini, PhD, Megan K. O’Brien, PhD, Chandrasekaran Jayaraman, PhD, Nicholas Shawen, MS, Ilona Shparii, BS, Saninder Kaur, MD, Aakash Gupta BS; Konrad Kording, PhD, Arun Jayaraman, PT PhD|
Rehabilitation Institute of Chicago
Max Nader Center for Rehabilitation Technologies and Outcomes Research exclusively focus on advanced wearable patient monitoring wireless sensors for reliable activity recognition/performance metrics. This exhibit highlights some of our recent projects using wearables and smartphone data to create and quantify rehabilitation outcomes: 1) Activity recognition in patients with assistive devices: strategies for setting machine-learning models. 2) Activity recognition in individuals with stroke – smart phone based outcome tool. A study highlighting the need for population specific model in improving the accuracy of activity recognition. 3) Fall detection in amputees using smartphone – An app to detect falls and provide valuable information on consequences that lead to the fall and its impact. 4) Spasticity detection with flexible wearable sensors – A pilot study to detect spastic episodes during activities in individuals with stroke/spinal cord injury.
|#9||Lumo Bodytech Monisha Perkash*, Charles Wang*, Derek Chang*, Daniel Ly*|
|#10||Evidation Health Jennifer Liao*|
|#11||Efficacy of Reminders to Move, Fitbit’s Feature for Motivating Users to Become Less Sedentary Karla Gleichauf*, Jacob Arnold|
In April 2016, Fitbit launched Reminders to Move (RTM), a feature that nudges users to walk at least 250 steps each hour. The goal of this study is to determine the efficacy of RTM in helping users reduce their sedentary time since excessive sitting is a serious health hazard, independent of the amount of exercise one gets. Over a 6 month period, over 60,000 users’ sedentary behavior and steps were compared before and after having RTM. RTM was found to be effective at helping to reduce sedentary time, especially so for its intended audience, the most sedentary. Sedentary users, defined as users who had <4 workday hours with >250 steps, were active for an additional hour a day (+42%) and took 830 extra daily steps (+22%) with 2 weeks of RTM. After several months with RTM, most sedentary users formed the habit of being more active throughout the day, requiring fewer RTM to become less sedentary.
|#12||Motion & Sports Performance Laboratory Michael Orendurff*|
Motion & Sports Performance Laboratory, Stanford Children’s Health
The staff at the Stanford Motion & Sports Performance Laboratory has a lengthy publication record using wearable sensors to quantify and validate mobility and exercise behavior in real world settings. Using sets of complex algorithms we have developed methods of understanding the effects of orthopedic injuries, interventions and injury prevention strategies during the real world activity and mobility of adults, adolescents and children.
|#13||Monitoring and Modeling Family Eating Dynamics Jack A. Stankovic, Donna Spruijt-Metz*, John Lach, Kayla de la Haye, Brooke M. Bell, Asif Salekin, Zeya Chen, Mohsin Y. Ahmed, Ridwan Alam, Jessica Rayo Abu Mondol, Meiyi Ma, Sarah M. Preum, Ifat Emi|
U Virginia, USC, CSULB
Approximately 12.7 million children and adolescents in the United States are considered obese. Family eating behaviors, home food environment, and parenting styles have been shown to impact dietary intake. However, monitoring dietary intake historically relies on self-reporting tools. These tools have many limitations, e.g., biased and inaccurate reporting, do not capture proximal factors that drive eating (e.g., mood, interpersonal influence, home environment). Monitoring eating behaviors, mood, social interactions and spatial location in real-time can provide unique and important insights into obesity-related eating patterns. M2FED uses a cyber-physical system (CPS) linked to Ecological Momentary Assessment (EMA) to understand and intervene on family eating dynamics (FED) in real-time.
|#14||Eureka Research Platform Lisa Lim*, Hannah Gittleman*|
Eureka Research Platform
|#15||VascTrac: A Study of Peripheral Artery Disease via Smartphones to Improve Remote Disease Monitoring and Postoperative Surveillance Neil Gandhi1*, Raheel Ata1, Hannah Rasmussen1, Kerolos Nakhla1, Osama El-Gabalawy1,2, Santiago Gutierrez2, Michael Doshi2, Shashank Kothapalli1, Saatchi Bhalla1, Sunaina Kongara3, Anika Agarwal1, Bakar Majeed1, Oliver Aalami1*|
1Division of Vascular Surgery, Stanford University School of Medicine, Stanford University, 2Department of Computer Science, Stanford University, 3University of California, Santa Barbara
VascTrac is the first smartphone-based longitudinal study that tracks the progression of peripheral artery disease (PAD). Using the Apple ResearchKit framework, we have built VascTrac, an iPhone app that monitors vascular risk factors, symptoms, medications, and surgeries. Using the iPhone accelerometer, we also collect physical activity data, which consists of the clinically validated 6-minute walk test (6MWT), and a completely passive component, which includes our novel indicator of disease severity Maximum Steps without Stopping (MSWS). Preliminary data shows that MSWS is smaller for PAD group (n=3) compared to non-PAD (n=24), consistent with our hypothesis. We aim to collect data on 3,000 users (both PAD patients and controls) over two years, paving the path for smartphone-based postoperative surveillance for PAD care. VascTrac could represent a personalized medicine approach to PAD surveillance and help identify patients at risk for treatment failure.
|#16||Harnessing Ubiquitous Computing and Big Data to Transform Care of Brain Health Dennis Wall*, Nick Haber, Catalin Voss, Jena Daniels, Jessey Schwartz, Aaron Kline, Azar Fazel, Peter Washington, Nate Stockham, Kelley Paskov, Christine Tataru, Jessica Keating, Terry Winograd, Carl Feinstein|
Wall Lab, Stanford University (Dept. Peds/System Medicine) Neuropsychiatric disorders are the single greatest cause of disability due to non-communicable disease worldwide, accounting for 14% of the global burden of disease. Diagnostic and therapeutic advances in brain health are limited in part due to a paucity of objective and reliable measures of behavior and neurological function — particularly those that are applicable outside the clinic. Advances in ubiquitous computing including mobile and wearable technologies, together with advances in artificial intelligence and computer vision, makes viable the deployment of tools to large patient populations that go beyond simple wearable health consumer tools (e.g. Fitbit) that can not only deliver diagnostic, scientific, and therapeutic value but that can establish a communication portal between patients and clinicians. Our work to-date has focused on developing several versions of mobile technologies that fit within this paradigm for the maintenance of brain health. We now intend to expand by evaluating the efficacy of ubiquitous computing for patient-driven change in data collection and to establish an iterative dialogue between patients and doctors, enabling positive adaptation of our abilities to treat neurological, psychiatric, developmental, and behavioral health (collectively brain health) beginning with one of the most pressing developmental conditions, autism. Using autism as a case study, we aim to show that it is possible to remotely collect large amounts of behavioral/phenotypic data and high-density enviro-molecular data from an entirely virtual population in need of care, while simultaneously robust diagnostic information and therapeutic intervention entirely outside of clinical settings. Finally, we will show how this data feedback loop can drive rapid innovation in detection, treatment, and monitoring progress for the entire autism population. If we succeed, we will not only create a series of mobile tools that can make the traditional approaches to patient care more efficient, but also set the stage for repeating the same process for a host of other brain health conditions across the lifecourse.
|#17||Head Impact Classification Using an Instrumented Mouthguard Lyndia Wu*, Livia Zarnescu, Vaibhav Nangia, Bruce Cam, David Camarillo*|
Head impacts in contact sports can cause concussions and cumulative head impact exposure may be associated with long term brain changes. Detecting and recording head impacts is essential for tracking impact exposure and studying acute and chronic injury mechanisms. We developed an instrumented mouthguard with accelerometers and gyroscopes to measure head impacts in sports. In addition, we designed a head impact detection classification system combining an infrared sensor and a machine learning classifier to detect and count head impacts accurately using the mouthguard. In the future, this wearable device may be further developed into an real-time on field diagnostic tool to measure and track head impact exposure.
|#18||Modus Health LLC Teri Rosenbaum-Chou*, David Boone*|
Modus Health, LLC
|#19||Microsoft Healthcare NExT Kay Hofmeester*|