Lyme disease is now the most common tick-borne disease in the Northern Hemisphere, but estimates of the disease spread are delayed by a year or more, according to experts. However, investigators think they can monitor the incidence in real time.

Until recently, public health estimates of Lyme disease cases put the incidence at about 30,000 Americans each year, based on reports submitted by physicians. The Centers for Disease Control and Prevention (CDC) has conducted a more comprehensive case count, however, which found that close to 300,000 Americans are affected annually by the disease.

“These numbers [highlight] the need to develop more effective methods for monitoring the spread of the disease, which affects the health of millions of individuals in the US, since cases accumulate over time,” wrote Sadilek et al in an article published in npj Digital Medicine.

The investigators developed a new monitoring method called Lymelight. They used a machine-learned classifier of web search sessions to estimate the number of individuals searching for potential symptoms of Lyme disease in a particular geographical area.

Comparing Lymelight results with the CDC data, the authors found a high level of agreement.


Sadilek A, Hswen Y, Bavadekar S, Shekel T, Brownstein JS, Gabrilovich E. Lymelight: forecasting Lyme disease risk using web search data. NPJ Digit Med. 2020;3:16.