'Eye-Catching' Smartphone App could Make it Easy to Screen for Neurological Disease at Home

Researchers at the University of California San Diego have developed a smartphone app that could allow people to screen for Alzheimer's disease, ADHD and other neurological diseases and disorders - by recording closeups of their eye.

The app uses a near-infrared camera, which is built into newer smartphones for facial recognition, along with a regular selfie camera to track how a person’s pupil changes in size. These pupil measurements could be used to assess a person's cognitive condition.

The technology is described in a paper that will be presented at the ACM Computer Human Interaction Conference on Human Factors in Computing Systems (CHI 2022), which will take place from April 30 to May 5 in New Orleans as a hybrid-onsite event.

"While there is still a lot of work to be done, I am excited about the potential for using this technology to bring neurological screening out of clinical lab settings and into homes," said Colin Barry, an electrical and computer engineering Ph.D. student at UC San Diego and the first author of the paper, which received an Honorable Mention for Best Paper award. "We hope that this opens the door to novel explorations of using smartphones to detect and monitor potential health problems earlier on."

Pupil size can provide information about a person’s neurological functions, recent research has shown. For example, pupil size increases when a person performs a difficult cognitive task or hears an unexpected sound.

Measuring the changes in pupil diameter is done by performing what's called a pupil response test. The test could offer a simple and easy way to diagnose and monitor various neurological diseases and disorders. However, it currently requires specialized and costly equipment, making it impractical to perform outside the lab or clinic.

Engineers in the Digital Health Lab, led by UC San Diego electrical and computer engineering professor Edward Wang, collaborated with researchers at the UC San Diego Center for Mental Health Technology (MHTech Center) to develop a more affordable and accessible solution.

"A scalable smartphone assessment tool that can be used for large-scale community screenings could facilitate the development of pupil response tests as minimally-invasive and inexpensive tests to aid in the detection and understanding of diseases like Alzheimer's disease. This could have a huge public health impact," said Eric Granholm, a psychiatry professor at UC San Diego School of Medicine and director of the MHTech Center.

The app developed by the UC San Diego team uses a smartphone's near-infrared camera to detect a person's pupil. In the near-infrared spectrum, the pupil can be easily differentiated from the iris, even in eyes with darker iris colors. This enables the app to calculate pupil size with sub-millimeter accuracy across various eye colors. The app also uses a color picture taken by the smartphone’s selfie camera to capture the stereoscopic distance between the smartphone and the user. The app then uses this distance to convert the pupil size from the near-infrared image into millimeter units.

The app's measurements were comparable to those taken by a device called a pupillometer, which is the gold standard for measuring pupil size.

The researchers also included various features in their app to make it more user friendly for older adults.

"For us, one of the most important factors in technology development is to ensure that these solutions are ultimately usable for anyone. This includes individuals like older adults who might not be accustomed to using smartphones," said Barry.

The researchers worked with older adult participants to design a simple app interface that allows users to self administer pupil response tests. This interface included voice commands, image-based instructions, and a cheap, plastic scope to direct the user to place their eye within the view of the smartphone camera.

"By testing directly with older adults, we learned about ways to improve our system's overall usability and even helped us innovate older adult specific solutions that make it easier for those with different physical limits to still use our system successfully," said Wang, who is also a faculty member in the UC San Diego Design Lab. "When developing technologies, we must look beyond function as the only metric of success, but understand how our solutions will be utilized by end-users who are very diverse."

The Digital Health Lab is continuing this work in a project to enable similar pupillometry function on any smartphone rather than just the newer smartphones. Future studies will also involve working with older adults to evaluate home use of the technology. The team will work with older individuals with mild cognitive impairment to test the app as a risk screening tool for early stage Alzheimer's disease.

This work was funded by the National Institute of Aging.

To learn more about this project and other works by the UCSD Digital Health Lab, see their webpage at https://digihealth.eng.ucsd.edu

Colin Barry, Jessica de Souza, Yinan Xuan, Jason Holden, Eric Granholm, Edward Jay Wang.
At-Home Pupillometry using Smartphone Facial Identification Cameras.
In CHI Conference on Human Factors in Computing Systems (CHI '22). Association for Computing Machinery, Article 235, 1-12, 2022. doi: 10.1145/3491102.3502493

Most Popular Now

AI Catches One-Third of Interval Breast …

An AI algorithm for breast cancer screening has potential to enhance the performance of digital breast tomosynthesis (DBT), reducing interval cancers by up to one-third, according to a study published...

Great plan: Now We need to Get Real abou…

The government's big plan for the 10 Year Health Plan for the NHS laid out a big role for delivery. However, the Highland Marketing advisory board felt the missing implementation...

Researchers Create 'Virtual Scienti…

There may be a new artificial intelligence-driven tool to turbocharge scientific discovery: virtual labs. Modeled after a well-established Stanford School of Medicine research group, the virtual lab is complete with an...

From WebMD to AI Chatbots: How Innovatio…

A new research article published in the Journal of Participatory Medicine unveils how successive waves of digital technology innovation have empowered patients, fostering a more collaborative and responsive health care...

New AI Tool Accelerates mRNA-Based Treat…

A new artificial intelligence (AI) model can improve the process of drug and vaccine discovery by predicting how efficiently specific mRNA sequences will produce proteins, both generally and in various...

AI also Assesses Dutch Mammograms Better…

AI is detecting tumors more often and earlier in the Dutch breast cancer screening program. Those tumors can then be treated at an earlier stage. This has been demonstrated by...

RSNA AI Challenge Models can Independent…

Algorithms submitted for an AI Challenge hosted by the Radiological Society of North America (RSNA) have shown excellent performance for detecting breast cancers on mammography images, increasing screening sensitivity while...

AI could Help Emergency Rooms Predict Ad…

Artificial intelligence (AI) can help emergency department (ED) teams better anticipate which patients will need hospital admission, hours earlier than is currently possible, according to a multi-hospital study by the...

Head-to-Head Against AI, Pharmacy Studen…

Students pursuing a Doctor of Pharmacy degree routinely take - and pass - rigorous exams to prove competency in several areas. Can ChatGPT accurately answer the same questions? A new...

NHS Active 10 Walking Tracker Users are …

Users of the NHS Active 10 app, designed to encourage people to become more active, immediately increased their amount of brisk and non-brisk walking upon using the app, according to...

New AI Tool Illuminates "Dark Side…

Proteins sustain life as we know it, serving many important structural and functional roles throughout the body. But these large molecules have cast a long shadow over a smaller subclass...

Deep Learning-Based Model Enables Fast a…

Stroke is the second leading cause of death globally. Ischemic stroke, strongly linked to atherosclerotic plaques, requires accurate plaque and vessel wall segmentation and quantification for definitive diagnosis. However, conventional...