June 2, 2022
Researchers from RTI International (RTI), a nonprofit research and global development institute, and the University of North Carolina at Chapel Hill (UNC) have leveraged machine learning technology to detect trachomatous trichiasis (TT), the painful end stage of the neglected tropical disease trachoma, which can lead to blindness if not promptly diagnosed and treated with surgery.
The research team has created a new smartphone-based app called the “TT Screener” that uses an algorithm to assess high-quality photos of eyelids and detect trichiasis in 13 seconds with an estimated 92% rate of accuracy. The simple app interface prompts the user to take a picture of the person’s eyelid, and then runs the algorithm to detect whether they have trichiasis. The first of its kind, the app has the potential to reduce costs associated with identifying cases as well as improve the accuracy of screening.
“Currently, trachoma programs rely on highly trained doctors and specially trained community members to go door-to-door to identify the disease and refer patients for surgery,” said Rebecca Flueckiger, associate director of Monitoring, Evaluation, Research, Learning and Adapting at RTI. “As we get closer to our goal of eliminating blinding trachoma as a public health problem, it is becoming more difficult, expensive and nuanced to find and then provide services to those who have trichiasis. We believe that this technology could make trichiasis diagnosis easier and more efficient by allowing community members without prior experience to easily be trained to use the app.”
Trachoma is a bacterial eye infection affecting 136 million of the world’s most impoverished people. If left untreated, it can result in scarring that turns the eyelid inward and leads the eyelashes to scratch the eye. This is the painful stage known as “trichiasis,” which often leads to blindness. It is responsible for the blindness or visual impairment of about 1.9 million people worldwide.
Although the new app offers the public health community another tool in its toolbox in fighting this disease, the research team emphasizes that the collective efforts of local governments and healthcare workers in endemic countries remain critical in reaching the last mile.
“Neglected tropical diseases impact more than 1.7 billion people across the world,” said Emily Gower, PhD, the study’s lead investigator and associate professor of epidemiology at the UNC Gillings School of Global Public Health. “We hope this app will help ensure that all those who develop trichiasis can be identified and informed of surgical services to manage this painful condition and prevent progression to blindness.”
The TT Screener is expected to undergo further field testing throughout 2022.
The technology was developed through a collaboration between RTI International and UNC as part of RTI’s $3 million research investment over five years (2019-2023) to support global neglected tropical disease (NTD) control and elimination efforts and fill gaps in knowledge. The partnership leverages UNC researchers’ extensive experience using machine learning methods to develop technology for low-resourced settings.
Contact the UNC Gillings School of Global Public Health communications team at email@example.com.