Early detection of Lyme disease could be boosted by simpler, faster testing technology

For some unlucky people, time spent outdoors can lead to Lyme disease, a condition that causes headaches, joint and muscle pain, flu-like symptoms, fatigue and sometimes a rash. If left untreated, these effects can become debilitating and extend to paralysis, inflammation of the brain and heart, and memory, hearing and vision problems that can last for years.

Lyme disease, which is expected to affect more than 600,000 people in the United States this year, is caused by a spiral bacterium that is transmitted to humans through the bite of infected deer ticks. The microbe triggers a complex immune response that can mimic the response to other dangerous tick-borne bacteria, often making it difficult for doctors to initiate appropriate antibiotic treatment.

To detect Lyme disease, the Centers for Disease Control and Prevention currently recommends a two-tiered testing program, conducted in centralized laboratories; results take one to two weeks. Antibiotic treatment does not cure all cases, but it can help prevent long-term disease in 80 to 90 percent of patients at an early stage. However, according to the Bay Area Lyme Foundation, current tests fail to detect 7 out of 10 cases at an early stage.

Members of UCLA’s California NanoSystems Institute have developed a testing technology that is not unlike at-home kits for detecting COVID-19 infection. The results are interpreted in 20 minutes by a portable reader using artificial intelligence.

In a new study published in Nature CommunicationsThe researchers and their colleagues used patient samples to show that the single AI-enhanced test is as reliable as the traditional Lyme disease screening regimen, which requires two tests.

The speed, portability, and relatively low cost of the method suggest the possibility of same-day detection of Lyme disease, in the clinic where patients receive care.

“Many people find out they have Lyme disease long after they could have been treated very easily,” said co-corresponding author Dino Di Carlo, the Armond and Elena Hairapetian Professor of Engineering and Medicine at UCLA’s Samueli School of Engineering.

“If we can measure quickly, cost-effectively, and without burdening the health care system and the patient, then testing can be done more routinely. If you were out in the woods and had signs of a tick bite or other symptoms, it might be prudent to get tested quickly at home or at a local clinic, which could allow for earlier potential treatment.”

At-home COVID-19 tests, in which a sample is applied to a cartridge containing special paper, offer a useful point of comparison. The sample flows along the paper and past antibodies that latch onto a disease-specific protein, which are visualized by a second set of antibodies attached to tiny gold particles measured in billionths of a meter. After a brief wait, the results can be read by eye.

The Lyme disease detection technology takes a different tack: A blood serum sample is placed in a cartridge, followed by a buffer fluid, and is allowed to flow vertically from top to bottom through several layers of sponge paper. One layer of paper is loaded with a set of lab-made peptides (the building blocks of the proteins in the bacteria that cause Lyme disease) that each detect a unique set of antibodies formed in response to that microbe.

The pattern formed on the paper, which contains information about the presence and quantity of each antibody, is captured using a digital reader and analyzed by an AI algorithm that provides results. In the study, each test paper costs $3 and the reader was adapted from a $200 commercially available smartphone.

The new Lyme disease test is one of the first examples of rapid diagnostic technologies that can provide a comprehensive profile of the human immune response to disease.

“If you can quantify a panel of indicators from a single sample, you can learn a lot of interesting things about the patient’s condition,” said co-corresponding author Aydogan Ozcan, the Volgenau Professor of Engineering Innovation at UCLA Samueli and CNSI’s associate director of entrepreneurship, industry and academic exchange.

“In Lyme disease, we look at a panel of immune factors that can be very different in different patients, depending on their history, their origin, etc. We needed AI to make sense of such a complex signal.”

The researchers trained their algorithm using multiple samples, including those from early-stage disease provided by the Bay Area Lyme Foundation’s Lyme Disease Biobank, and blindly analyzed the performance of their technology using new samples from the biobank.

They achieved a sensitivity of 95.5% in detecting Lyme disease and a specificity of 100%, excluding disease-free samples. Using additional samples from the CDC, they showed that their point-of-care test correlated very well with laboratory test results, correctly detecting Lyme disease and differentiating it from similar diseases.

“AI can only be effective if the data is good,” Ozcan said. “That’s why we worked with the Lyme Disease Biobank and the CDC to get well-characterized samples. Their involvement was very important so that our AI could learn the immune response patterns against the bacteria that cause Lyme disease.”

In addition to AI, synthetic peptides from Connecticut-based Biopeptides, Corp. have been a key component of the new testing technology. Compared to the whole proteins used in some lab tests for Lyme disease, peptides can be bound more specifically, are easier to produce and are more stable.

“Peptides are really critical,” Di Carlo said. “We want to focus on answers that are very specific to Lyme disease and not other related or similar diseases. At the same time, the tests can be cheaper, last longer and generate fewer diagnostic errors.”

If the test continues to be successful, it could be a few years before it becomes available in the clinic. The researchers are currently looking for partners to develop their technology to speed up that process. They are also working on adapting the test to use whole blood samples rather than serum, and plan to further simplify the test format and develop a dedicated AI sample reader that is independent of a given smartphone.