By Mark Matthews, Saeed Abdullah, Geri Gay, and Tanzeem Choudhury
NOTE: This is an overview of the entire article, which appeared in the April 2014 issue of Computer magazine.
Click here to read the entire article.
Serious mental illnesses (SMI) are among the most pressing public health concerns. Continuous and unobtrusive sensing of social and physical functioning has tremendous potential to support lifelong health management by acting as an early warning system to detect changes in mental well-being, delivering context-aware micro-interventions to patients when and where they need them and significantly accelerating patient understanding of their illness.
One quarter of American adults suffer from a diagnosable mental disorder each year. People with SMI – including major depression, schizophrenia, bipolar disorder, obsessive-compulsive disorder, and post-traumatic stress disorder – will, on average, die 25 years earlier than those unaffected. The problems arising from mental illness are not limited to the individual sufferer: family, friends, and social networks can all be affected. SMIs are also expensive: they are among the top five conditions in the US for direct medical expenditure, with associated annual healthcare costs exceeding $30 billion.
A Cornell University study conducted by researchers Mark Matthews, Saeed Abdullah, Geri Gay, and Tanzeem Choudhury, outlines how mobile technologies not only have the potential to dramatically improve illness management, but could do so in a cost-effective way. The article discusses the importance of patient acceptance when introducing sensing for use with SMI patients, due to the significant stigma associated with mental illness.
The researchers in this study discuss the relationship between behavior and mental wellness. Using passive sensing, they tracked symptomatic behavior for a range of SMIs. The focus was on physical activity, social engagement, and sleep patterns, but the researchers underscored the potential for detecting many other behaviors.
One approach discussed in the article involves guiding the patient to better mental health through self-awareness and feedback data. Smartphone sensing provides immediate feedback to patients outside the clinic. Such feedback must consist of easy-to-understand visualizations, maintain user privacy, and be appropriate to patients’ current understanding of their illness. BeWell is a smartphone app developed by the researchers that maps the user’s overall well-being along three dimensions – physical activity, social engagement, and sleep patterns and displays the data on the phone’s wallpaper. If the user wants to find out more information along a specific dimension, tapping on the relevant icon provides additional details.
MoodRhythm uses passive sensing to extend interpersonal social rhythm therapy (IPSRT) to support the long-term treatment of bipolar disorder. (a) Social rhythm metric (SRM) self-report screen. (b) Badge screen displays badges awarded for adherence to self-report tasks and for reaching therapeutic goals. (c) Home screen displays ambient bubbles that represent the activities users are trying to keep in balance.
MoodRhythm, another mobile app utilized in this study, applies passive sensing to support the long-term treatment of bipolar disorder. Bipolar disorder is a common illness that affects between 3 and 6 percent of the world’s population in developing and industrialized countries, regardless of socioeconomic status or gender. The illness is associated with poor functional and clinical outcomes, high suicide rates, and huge societal costs. The app has the dual aim of motivating users to adhere to treatment and provide labeled data, taking advantage of the reward-sensitive neural characteristics associated with bipolar disorder.
To learn more about the various therapies and techniques used in developing these sensors, read the full article here.
ABOUT THE AUTHORS
Mark Matthews (firstname.lastname@example.org) is a Marie Curie postdoctoral fellow with the Interaction Design Lab in the Information Science Department at Cornell University. His research focuses on the design and evaluation of low-cost ubiquitous support systems for serious mental illnesses and is currently investigating the interplay between bipolar disorder and technology. Matthews received a PhD in computer science from Trinity College, Dublin, Ireland. He is a member of ACM.
Saeed Abdullah (email@example.com) is a PhD student in the Information Science Department at Cornell University. His work focuses on the design, implementation, and deployment of systems to help people maintain chronobiological stability; he is also exploring novel ways to infer internal body clock from low-level smartphone interaction patterns.
Geri Gay (firstname.lastname@example.org) is the Kenneth J. Bissett Professor of Communication and a Stephen H. Weiss Presidential Fellow at Cornell University. She is also a professor in the Information Science Department and director of the Interaction Design Lab. Her research focuses on social and technical issues in the design of interactive communication technologies, especially social navigation, affective computing, social networking, mobile computing, and design theory. Gay received a PhD in education from Cornell University. She is a member of ACM.
Tanzeem Choudhury (email@example.com) is an associate professor in the Information Science Department and directs the People-Aware Computing group at Cornell University. Her primary research interests are in mobile sensing of health and ubiquitous computing. Choudhury received a PhD from the MIT Media Lab. She is a member of ACM.