Motivation and Background
Alzheimer’s disease affects more than 5 million people claiming over 500,000 Americans annually . As the sixth leading cause of death in Americans , its management is challenging. Current reactive healthcare costs more than 17% of GDP in the US [3, 4]. Alzheimer’s related healthcare costs alone are around $150 billion a year to Medicare and Medicaid . To add to the challenge, dementia is an umbrella term that encompasses various forms of the disease such as Alzheimer’s disease, vascular dementia, and Huntington’s disease, to name a few . Not only are the healthcare costs associated with dementia staggering, but the impact on the caregivers is also a critical challenge; in 2013, 15.5 million family and friends provided 17.7 billion hours of unpaid care to those with Alzheimer's and other forms of dementia – care valued at $220.2 billion . With the exponential rise of the older population due to the baby boomers, the number of people with Alzheimer’s disease (the most prevalent form of dementia) is estimated to reach around 13.8 million [1,6]. This creates the strong need for unobtrusive sensing modalities that can help monitor people with dementia and support caregivers.
Dementia: Challenges and Opportunities
With increasing adoption of mobile devices and low-cost sensors, an unprecedented amount of data is being collected . However, in the context of dementia, it is challenging to convert this huge amount of data into actionable information that can: a) help detect behavioral changes in an individual with dementia and b) provide relevant information to the clinician supporting them in treating chronic illness. In our previous work, we derived actionable information from physical and physiological data collected from children diagnosed with asthma. We have developed kHealth kit [9, 28] a semantics-enabled smart mobile application with sensors, to capture observations from machine sensors (quantitative) and people (qualitative) in the domain of asthma . We also have active clinical collaborations to investigate and evaluate the use of kHealth technology for reducing readmission of GI (gastrointestinal) and ADHF (acute decompensated heart failure) patients after their discharge from the hospital.
kHealth for Dementia
The aim of this study is to detect changes in behavior (agitation, depression, and apathy, see here) and activity patterns of patients with dementia by using a combination of wearable and environmental sensors using a mobile platform. Detecting these behavior changes will result in a deeper understanding of the causes of mood and behavioral changes. This will involve detecting fluctuations in sleep patterns and evaluating the effects on stress using standard clinical methods. This can help predict mood events, which in turn can help alert clinicians for early intervention. The study will revolve around 10-20 dyads, each comprising a person with dementia (PwD) and his or her main caregiver (Cg). The person with dementia and caregiver must live in the same house or apartment. Sensors will be monitoring the sleep patterns of the patient as well as activity patterns using wearable sensors like the Jawbone UP24 to track parameters like number of steps, location, gait speed as well as wearable garments such as the Sensoria socks for an additional modality to measure gait parameters including speed, cadence, step count, etc. Environmental sensors like the Sense can be used to detect the activity trends. The data can be collected via Bluetooth and processed using an Android-based smartphone. Any abnormal changes in these patterns can then be validated using physical tests like TUG (obtained from the clinician), as well as cognitive tests like the Zarit Burden Interview (obtained from the caregiver). In addition, the effects of psychoactive medications for behavioral disturbances in patients will be associated with changes in their sleep and daily movements. This can provide long-term benefit to patients with dementia to monitor cognitive behavior as well as enable early intervention using ubiquitous sensors in an affordable and non-invasive manner.
Figure 1. The kHealth Dementia application will measure physiological signals from the person with dementia as well as the caregiver to provide a deeper understanding of the behavior changes contributing to dementia.
Current Team Members
Faculty: Dr. Tanvi Banerjee (CECS, Kno.e.sis, Wright State University), Dr. Amit Sheth (CECS, Kno.e.sis, Wright State University), Dr. Larry Lawhorne (Boonshoft School of Medicine, Wright State University)
Graduate Students: Pramod Anantharam, Vaikunth Sridharan
Undergraduate Students: Quintin Oliver
kHealth User Manual
Related Talks and Presentations
This project is sponsored by the National National Institutes of Health (NIH) Grant No. 1K01LM012439 to the Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis) titled: Managing Dementia through a Multisensory Smart Phone Application to Support Aging in Place. Any opinions, findings, conclusions or recommendations expressed in this material are those of the investigator(s) and do not necessarily reflect the views of the National Institutes of Health.
 Alzheimer’s Association description of Alzheimer’s statistics, Available online at: http://www.alz.org/alzheimers_disease_facts_and_figures.asp #quickFacts
 Dementia related facts, Available online at: http://www.cdc.gov/mentalhealth/basics/mental-illness/dementia.htm
 D. A. Squires, “The U.S. Health System in Perspective: A Comparison of Twelve Industrialized Nations,” June 2011, Available online at: http://bit.ly/oZwhFZ
 Health Costs: How the U.S. Compares With Other Countries, Available online at: http://www.pbs.org/newshour/rundown/2012/10/health-costs-how-the-us-compares-with-other-countries.html
 Quantified Self http://quantifiedself.com/
 G. K. Vincent, V. A. Velkof, “The next four decades: The older population in the United States: 2010 to 2050.” Washington, D.C.: U.S. Census Bureau; 2010.
 Hexoskin. www.hexoskin.com
 A. Pasolini, "Sensor-packed Hexoskin shirt measures performance in real time". Available at: http://www.gizmag.com/hexoskin-sensor-t-shirt-body-metrics/29098/ Gizmag. September 19, 2013.
 kHealth: A knowledge-enabled semantic platform to enhance decision making and improve health, fitness, and well-being, Available online at: http://knoesis.org/projects/khealth (Accessed May 27, 2013).
 V. Santhisagar, T. Ioannis, B. Diane, J. C. Faquir, P. Fotios, "Emerging synergy between nanotechnology and implantable biosensors: A review." Biosensors and Bioelectronics 25.7: 1553-1565, 2010.
 J. S. Karlsson, U. Wiklund, L. Berglin, N. Östlund, M. Karlsson, T. Bäcklund, & L. Sandsjö, “Wireless monitoring of heart rate and electromyographic signals using a smart T-shirt.” In Proceedings of International Workshop on Wearable Micro and Nanosystems for Personalised Health, 2008.
 M. Chan, E. Campo, D. Estève, & J. Y. Fourniols, "Smart homes—current features and future perspectives. " Maturitas, 64(2), 90-97, 2009.
 E. Topol, “The creative destruction of medicine: How the digital revolution will create better health care.” Basic Books (AZ), 2012.
 T. Banerjee, M. Skubic, J. M. Keller & C. C. Abbott, "Sit-To-Stand Measurement For In Home Monitoring Using Voxel Analysis," IEEE Journal of Biomedical and Health Informatics, 18(4):1502-1509, 2014.
 T. Banerjee, M. Rantz, M. Li, M. Popescu, E. Stone & M. Skubic, "Monitoring Hospital Rooms for Safety Using Depth Images," Proceedings, AAAI Fall Symposium Series - AI for Gerontechnology, Washington DC, November 2-4, 2012.
 M. Gietzelt, K. H. Wolf, M. Kohlmann, M. Marschollek, and R. Haux. "Measurement of Accelerometry-based Gait Parameters in People with and without Dementia in the Field." Methods Inf. Med 52, no. 4: 319-325, 2013.
 E. Stone & M. Skubic, "Evaluation of an Inexpensive Depth Camera for In-Home Gait Assessment," Journal of Ambient Intelligence and Smart Environments, 3(4):349-361, 2011.
 A. L. Bleda, R. Maestre, A. J. Jara, & A. G. Skarmeta, “Ambient Assisted Living Tools for a Sustanaible Aging Society.” In Resource Management in Mobile Computing Environments pp. 193-220. Springer International Publishing, 2014.
 J. L. Cummings, “The Neuropsychiatric Inventory: Assessing psychopathology in dementia patients.” Neurology 48 (Supple 6): S10-S16,1997.
 W. E. Haley, E. G. Levine, S. L. Brown, and A. A. Bartolucci. "Stress, appraisal, coping, and social support as predictors of adaptational outcome among dementia caregivers." Psychology and aging 2, no. 4: 323, 1987.
 Fitbit sensor. www.fitbit.com
 S. H. Zarit, K. E Reever, J. Bach-Peterson, “Relatives of the impaired elderly: correlates of feelings of burden.” Gerontologist. 20:649–55, 1980.
 D. Tobon Vallejo, T. Falk, M. Maier, "MS-QI: A Modulation Spectrum-Based ECG Quality Index for Telehealth Applications," Biomedical Engineering, IEEE Transactions on, 2015.
 R. T. Warne, "A primer on multivariate analysis of variance (MANOVA) for behavioral scientists". Practical Assessment, Research & Evaluation 19 (17): 1–10, 2014.
 K. V. Mardia, J. T. Kent, J. M. Bibby, “Multivariate Analysis.” Academic Press, 1979.
 J. Schmid Jr., "The Relationship between the Coefficient of Correlation and the Angle Included between Regression Lines". The Journal of Educational Research 41 (4), 1947.
 Hexoskin data validation. Available at: https://cdn.shopify.com/s/files/1/0284/7802/files/CSEP_Hexo skin_Poster_-_University_of_Waterloo.pdf?11148
 A. Sheth, P. Anantharam, K. Thirunarayan, “kHealth: Proactive Personalized Actionable Information for Better Healthcare,” Workshop on Personal Data Analytics in the Internet of Things (PDA@IOT 2014), collocated at VLDB 2014, Hangzhou, China, September 5th 2014.
 C.R. Rao. “Estimation of variance and covariance components in linear models.” Journal of the American Statistical Association, 67(337), 112-115, 1972.
 P. Anantharam, T. Banerjee, A. Sheth, K. Thirunarayan, S. Marupudi, V. Sridharan, S. G. Forbis, "Knowledge-driven Personalized Contextual mHealth Service for Asthma Management in Children", IEEE 4th International Conference on Mobile Services, June 27 - July 2, 2015, New York, USA