Special care

Tanvi Banerjee, assistant professor of computer science and engineering (pictured), is working with Jennifer Hughes, assistant professor of social work, to study burnout of dementia patients’ caregivers using word games, computer apps and skin sensors. (Photo by Erin Pence)

An unusual and creative approach to detecting burnout among those who care for dementia patients is being studied by Wright State University computer science and social work researchers.

It involves word games, computer apps and skin sensors.

The project began in 2014 and last year received a three-year, $500,000 grant from the National Institutes of Health. The study has currently tested a commercial sensor called the Hexoskin vest with 40-and-older adults and will involve as many as 20 patient/caregiver couples for a longer-term study.

Alzheimer’s disease affects more than 5 million people, claiming over 500,000 Americans annually and is the sixth leading cause of death in the United States. Alzheimer’s-related health care costs alone are about $150 billion a year to Medicare and Medicaid.

The spouses of dementia patients are frequently the caregivers. Often they must give around-the-clock attention to the patients.

“The chore of caregiving can become so overwhelming that we call it ‘caregiver burnout,’” said Tanvi Banerjee, assistant professor of computer science and engineering with Kno.e.sis, Wright State University’s Ohio Center of Excellence in Knowledge-Enabled Computing. “That has become a big problem. It can result in the patient ending up in an alternative care facility, or nursing home, not to mention severe physical and cognitive deterioration in the caregiver’s health.”

The study led by Banerjee and Jennifer Hughes, an assistant professor of social work, is investigating how to use technology in a non-intrusive way to monitor chronic conditions of dementia patients and to measure the stress on the caregiver.

Hughes said leaders in the field of dementia-related illness are interested in developing technology to assist caregivers beyond existing technology that helps with things such as medication management and appointment reminders.

One aim of the study is to detect changes in activity patterns of patients as well as changes in their behavior such as agitation, depression, and apathy by using wearable sensors such as the vests that measure heartrate and breathing. The hope is it will result in a deeper understanding of the causes of mood and behavioral changes and provide opportunity for early intervention.

The study also involves attaching a Fitbit-like device to the caregiver that detects stress through a galvanic skin response. That data is combined with the caregiver’s heartrate and activity pattern.

The caregivers are asked to use gaming technology on their mobile devices or tablets to play Word Scramble daily over a period of two to four weeks, where the users create words from a jumbled puzzle. An algorithm developed by the researchers learns the caregivers’ game-play patterns and develops a standard model for each individual caregiver.

Changes in the game-play patterns may be a red flag. For example, a caregiver may normally be able to reach a certain level of the game in three minutes. But if the caregiver takes much longer than that or even skips a word, it may indicate a higher level of stress that could be caused from the caregiving.

“It’s telling us something is different that day,” said Banerjee.

From left: Tanvi Banerjee, Abby Edwards, Alexandrea Oliver, Garrett Goodman, Morgan Freeman, JoAnna Meyer and Jennifer Hughes.

The researchers then look at the data from the caregiver’s skin sensor to see if it is detecting higher stress. If so, that may be a sign that the caregiver is approaching burnout.

Social workers would then step in by offering additional resources for the caregivers such as offering daycare services to give them a break or bringing meals into the home.

Banerjee said the goal is to enable both the patient and the caregiver to be able to stay in their home and maintain a high quality of life for a longer period of time.

“Patients, families and communities all benefit when ailing loved ones remain at home for longer periods of time,” said Hughes. “There is a tremendous cost savings and better patient outcomes when this happens.”

Banerjee said the technology is a nonintrusive and less expensive approach to detecting changes in caregivers and their patients. And she said the relaxation effect of playing Word Scramble might in itself prove to be an effective intervention. She anticipates additional games being added to the mix.

In November, Banerjee and Hughes showcased their research and provided a demonstration of the gaming application during Annual Science Night hosted by the Alzheimer’s Association in Dayton. About 330 people attended, including caregivers, community workers and researchers studying Alzheimer’s.

Testing of the approach began in the first week of December and is expected to continue through the spring.

For more information, visit the project page at wiki.knoesis.org/index.php/Dementia.