A groundbreaking diagnostic test developed by UCLA researchers promises faster and more reliable detection of Lyme disease. Using artificial intelligence and a portable reader, this innovative technology could revolutionize early diagnosis and treatment, potentially reaching clinics within a few years.
A team at the California NanoSystems Institute at UCLA has developed a cutting-edge diagnostic tool that promises to revolutionize the detection of Lyme disease. This innovative test, inspired by at-home COVID-19 testing, delivers results in just 20 minutes with remarkable accuracy and ease of use.
Lyme disease affects more than 600,000 people annually in the United States and is notoriously difficult to diagnose early due to its varied symptoms. Current testing methods, which are lab-based and take 1-2 weeks for results, miss up to 70% of early-stage cases according to the Bay Area Lyme Foundation.
Incorporating artificial intelligence, the new technology leverages a portable reader to analyze blood serum samples through a vertical flow of sponge-like paper infused with synthetic peptides. These lab-made peptides detect specific antibodies indicating the presence of the Lyme-causing bacteria. The AI algorithm interprets the complex patterns formed on the paper, providing results that match or exceed current testing accuracy.
Dino Di Carlo, the Armond and Elena Hairapetian Professor of Engineering and Medicine at UCLA Samueli School of Engineering and co-corresponding author of the study, explained the significant impact of this rapid testing.
“A lot of folks find out they have Lyme disease well after the point at which they could have been treated very easily,” Di Carlo said in a news release. “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.”
This groundbreaking study, recently published in Nature Communications, showcases the technology’s high sensitivity (95.5%) and perfect specificity (100%) in detecting Lyme disease, outperforming traditional methods.
Contributing to its development, the Bay Area Lyme Foundation’s Lyme Disease Biobank provided essential early-stage disease samples.
Aydogan Ozcan, Volgenau Professor of Engineering Innovation at UCLA Samueli and CNSI’s associate director and co-corresponding author, highlighted the test’s comprehensive analysis capabilities.
“If you can quantify a panel of indicators from a single sample, you can learn a lot of interesting things regarding the patient’s condition,” said Ozcan in the news release. “In Lyme disease, we are examining a panel of immune factors that can look very different in different patients, depending on their background, where they’re from, etc. We needed AI to make sense of such a complex signal.”
The study’s success hinges not only on AI but also on the precision of synthetic peptides developed by Connecticut-based Biopeptides, Corp. These peptides provide a more stable and cost-effective solution compared to whole proteins used in some lab tests, reducing diagnostic errors and extending test shelf life.
“The peptides are really critical,” Di Carlo added. “We want to focus on responses that are very specific to Lyme disease and not other related conditions or look-alike diseases. And at the same time, the tests can be cheaper, last longer and return fewer diagnostic errors.”
The research team is now seeking partners to scale up the technology, aiming for clinical availability within a few years. They are also working to simplify the test further by adapting it to use whole blood samples and developing a dedicated AI sample reader.
This innovation not only promises quicker, more accessible Lyme disease diagnoses but also stands as an early example of rapid diagnostic technologies that fully profile the human immune response, potentially paving the way for advancements in the detection of various diseases.