11:00 - 11:05 amSunday, September 27
Lower Lobby - West
Intelligent sensor system for early illness alerts in senior housing
Lower Lobby - West
Intelligent sensor system for early illness alerts in senior housing
University of Missouri
Background: Chronic disease management is the biggest health care problem facing the United States today. In 2012, one in two American adults had at least one chronic condition, and 26% of the population... Read more

Description

Background: Chronic disease management is the biggest health care problem facing the United States today. In 2012, one in two American adults had at least one chronic condition, and 26% of the population had multiple chronic conditions, accounting for 84% of US health care costs. Chronic diseases especially affect older adults and often result in dramatic health decline, hospitalization, complex treatments, and high cost. Recognition of small changes in health conditions facilitates early interventions when treatment is most effective, prevention of dramatic decline is still possible, and costs can be controlled. In a previous pilot study, we showed significant differences in health outcomes for an intervention group of 21 seniors with a sensor-based early illness recognition system, compared to 20 seniors receiving normal care. The goal of this study is to conduct a larger randomized intervention study to further test the early illness recognition system that uses in-home sensors and automated health alerts sent to clinical staff.

Methods: A randomized intervention study is being conducted in 14 senior housing sites (assisted and independent living) with 70 seniors as controls receiving normal care and 70 seniors with in-home health alert systems. The health alert system functions as a clinical decision support system that analyzes data from sensors embedded in the home. A bed sensor captures quantitative pulse, respiration, and restlessness and records sleep patterns. An in-home gait analysis system using a depth camera estimates in-home walking speed, stride time, and stride length by opportunistically capturing walking paths in the home. Motion sensors capture room to room movement and overall activity level. Smart algorithms generate health alert emails based on changing patterns in the sensor data. Alerts are sent to clinical staff, who determine whether an intervention is warranted. Each health alert email includes embedded links to a web interface for visualizing sensor data trends and a feedback web interface for clinicians to rate the clinical relevance of the alert.

Results: The study is in progress. Recruitment is ongoing with 126 subjects thus far. Sensor systems have been installed in the apartments of the intervention group; health alerts are being generated. Preliminary results show the following parameters act as biomarkers for early illness recognition: time in bed, pulse and respiration rates, bed restlessness, walking speed, stride time, stride length, activity in the bathroom, bedroom, living room, and kitchen, and motion density (motion events per unit time). Quarterly clinical assessments include the SF-12 Health Survey, Geriatric Depression Scale, Mini Mental State Exam, Activities of Daily Living, and Independent Activities of Daily Living.  Primary care and specialty office visits, emergency room (ER) visits, hospitalizations, nursing home stays, and falls are recorded for each subject.  Costs for primary care and specialty office visits, ER visits, hospitalizations, nursing home stays, and falls will be estimated and tabulated.  Changes in marital status, medical diagnoses, or medication use will be updated quarterly.  The clinical assessment measures will be analyzed quarterly to investigate differences in health outcomes between the intervention and control groups.

Conclusions: Results will be forthcoming.

Marjorie Skubic received her Ph.D. in Computer Science from Texas A&M University, where she specialized in distributed telerobotics and robot programming by demonstration. She is currently a Professor in the Electrical and Computer Engineering Department at the University of Missouri with a joint appointment in Computer Science. In addition to her academic experience, she has spent 14 years working in industry on real-time applications such as data acquisition and automation. Her current research interests include sensory perception, spatial referencing interfaces, human-robot interaction, sensor networks for eldercare, and preventative screening tools. In 2006, Dr. Skubic established the Center for Eldercare and Rehabilitation Technology at the University of Missouri and serves as the Center Director for this interdisciplinary team. The center's work supports proactive models of healthcare such as monitoring systems that noninvasively track the physical and cognitive health of elderly residents in their homes and generate alerts that flag health changes. Recent work has also investigated automated screening of athletes and pianists to flag injury risks, with support for preventative exercises to reduce the risk.

Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text. captcha txt

Start typing and press Enter to search