A new test under development by researchers at the University of California, Los Angeles (UCLA) that uses artificial intelligence (AI) and a format similar to that of at-home COVID-19 tests has been shown to accurately identify Lyme disease within 20 minutes.
In findings published in Nature Communications, the team from the California NanoSystems Institute at UCLA showed that their test provides results that are as accurate as the traditional Lyme disease testing regimen.
The test kit consists of a cartridge-based test unit containing Lyme disease antibody-specific synthetic peptides and a paper-based platform that is then run on a digital reader that analyzes the collected sample using an AI algorithm. It is run as a single test, providing results in approximately 20 minutes.
The current gold-standard Lyme testing regimen requires a two-part test performed at centralized labs; results take one to two weeks. Furthermore, traditional testing may fall short in diagnosing early-stage Lyme disease, when treatment is most effective at preventing long-term effects of the disease.
"A lot of folks find out they have Lyme disease well after the point at which they could have been treated very easily," co-corresponding author Dino Di Carlo, the Armond and Elena Hairapetian Professor of Engineering and Medicine at the UCLA Samueli School of Engineering, said.
"If we can measure rapidly, in a way that's cost-effective and not a burden to the health system and the patient, then testing can be done more routinely. If you were out in the woods and have signs of a tick bite or other symptoms, it might be prudent to quickly test either at home or the local clinic, which could enable potential treatment earlier," Di Carlo said.
The researchers trained the test's algorithm with samples provided by the Bay Area Lyme Foundation's Lyme Disease Biobank, including early-stage Lyme disease samples. They blindly analyzed the test using new samples from the biobank, achieving 95.5% sensitivity in detecting Lyme disease and 100% specificity, ruling out samples without the disease. Using additional samples from the U.S. Centers for Disease Control, the team demonstrated that the test's results corresponded closely with conventional lab-based test results in correctly detecting Lyme disease and differentiating it from other diseases.
The test uses synthetic peptides provided by Ridgefield, CT-based Biopeptides. In the Nature Communications article, the team noted that peptides have several advantages over the full-length recombinant proteins used in conventional lab tests for Lyme disease, including high specificity and a lower potential for cross-reactivity, as well as longer shelf life and being easier and less expensive to produce.
In aiming to create an accurate, portable test with the potential for same-day results in the clinic, affordability was a consideration for the research team. The test paper for each test cost $3; the reader used in the test was adapted from a $200 smartphone, the researchers said.
The research team is currently seeking partners to scale the technology to accelerate further testing in anticipation of the test becoming available in a few years. Additionally, they are working to adapt the test to use whole blood instead of serum samples and are looking to further improve and streamline the test.
The research received support from the U.S. National Institutes of Health and the National Science Foundation.
