A wearable sensor to assist ALS sufferers talk
All components of the sensor device can easily be mass-produced. The researchers estimate that each device would cost around $ 10. Photo credit: David Sadat
People with amyotrophic lateral sclerosis (ALS) have a gradual decline in their ability to control their muscles. As a result, they often lose the ability to speak, which makes it difficult to communicate with others.
A team of MIT researchers has now developed a stretchable, skin-like device that can be attached to a patient’s face and measure small movements such as twitching or smiling. With this approach, patients could communicate a variety of feelings such as “I love you” or “I’m hungry” with small movements that are measured and interpreted by the device.
The researchers hope that their new device will allow patients to communicate more naturally without having to deal with bulky devices. The wearable sensor is thin and can be camouflaged with makeup to match any skin tone, making it unobtrusive.
“Our devices are not only malleable, soft, disposable and lightweight, but also optically invisible,” says Canan Dagdeviren, assistant professor of media development and media studies at LG Electronics at MIT and head of the research team. “You can disguise it and no one would think you have anything on your skin.”
The researchers tested the original version of their device on two ALS patients (one woman and one woman to maintain gender balance) and showed that three different facial expressions could be accurately distinguished – smiling, open mouth, and pursed lips.
MIT graduate Farita Tasnim and former scientist Tao Sun are the lead authors on the study, which appears today in Nature Biomedical Engineering. Other MIT authors include Rachel McIntosh, postdoc Dana Solav, and scientist Lin Zhang. Yuandong Gu from the A * STAR Institute for Microelectronics in Singapore and Nikta Amiri, Mostafa Tavakkoli Anbarani and M. Amin Karami from the University of Buffalo are also authors.
A skin-like sensor
Dagdeviren’s laboratory, the Conformable Decoders group, specializes in developing adaptable (flexible and stretchable) electronic devices that can adhere to the body for a variety of medical applications. After meeting Stephen Hawking in 2016, when the world-famous physicist attended Harvard University and Dagdeviren was a Junior Fellow in the Harvard Society of Fellows, she became interested in ways to help patients with neuromuscular disorders communicate.
Hawking, who passed away in 2018, suffered from a slowly progressive form of ALS. He was able to communicate with an infrared sensor that detected twitches in his cheek that moved a cursor over rows and columns of letters. While this process is effective, it can be time consuming and require bulky equipment.
Other ALS patients use similar devices that measure the electrical activity of the nerves that control the muscles of the face. However, this approach also requires cumbersome equipment and is not always accurate.
“These devices are very hard, planar, and box-shaped, and reliability is a big problem. You may not get consistent results even with the same patients on the same day,” says Dagdeviren.
A team of MIT researchers has now developed a stretchable, skin-like device that can be attached to a patient’s face and measure small movements such as twitching or smiling. Photo credit: David Sadat
Most ALS patients also eventually lose the ability to control their limbs, so typing is not a viable strategy to help them communicate. The MIT team set out to design a wearable interface that would allow patients to communicate in a more natural way, without the bulky devices required by current technologies.
The device they created consists of four piezoelectric sensors embedded in a thin silicone film. The aluminum nitride sensors can detect mechanical deformations of the skin and convert it into an easily measurable electrical voltage. All of these components are easy to mass-produce, so the researchers estimate that each device would cost around $ 10.
The researchers used a process called digital image correlation on healthy volunteers to help them choose the most useful places to place the sensor. They painted a random black and white pattern of spots on the face and then took many pictures of the area with multiple cameras while the subjects made facial movements such as smiling, twitching the cheek, or shaping the mouth of certain letters. The images were processed by software that analyzes how the small dots move relative to each other to determine the stress in a single area.
“We had subjects making different movements and we made stress maps for every part of the face,” says McIntosh. “Then we looked at our stretch maps and determined where on the face was the correct amount of stretch for our device and determined that this is a convenient place to place the device for our tests.”
Researchers also used the measurements of skin deformations to train a machine learning algorithm to differentiate between a smile, an open mouth, and pursed lips. Using this algorithm, they tested the devices with two ALS patients and were able to achieve an accuracy of around 75 percent in distinguishing between these different movements. The accuracy rate in healthy subjects was 87 percent.
Based on these recognizable facial movements, a library of phrases or words could be built that correspond to various combinations of movements, the researchers say.
“We can create customizable messages based on the movements you can make,” says Dagdeviren. “You can technically create thousands of messages for which no other technology is currently available. It all depends on your library configuration, which can be developed for a particular patient or group of patients.”
The information from the sensor is sent to a hand processing unit, which analyzes it using the algorithm the researchers trained to distinguish between facial movements. In the current prototype, that device is connected to the sensor, but the connection could also be made wirelessly for ease of use, the researchers say.
The researchers have applied for a patent for this technology and are now planning to test it with more patients. In addition to helping patients communicate, the device could also be used to track the progression of a patient’s disease or to measure whether treatments they are receiving are having an impact, the researchers say.
“There are many clinical trials testing whether or not a particular treatment is effective in reversing ALS,” says Tasnim. “Instead of just relying on patients to report that they feel better or stronger, this device could provide a quantitative measure to track effectiveness.”
How to rebound from outstretched stretchable sensors
Natural Biomedical Engineering (2020). DOI: 10.1038 / s41551-020-00612-w Provided by the Massachusetts Institute of Technology
Quote: A wearable sensor for communicating with ALS patients (2020, October 22nd), accessed on October 22nd, 2020 from https://medicalxpress.com/news/2020-10-wearable-sensor-als-patients.html
This document is subject to copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.