Abstract
Lyme disease is the most common tick-borne disease in the Northern Hemisphere. Existing estimates of Lyme disease spread are delayed a year or more. We introduce Lymelight—a new method for monitoring the incidence of Lyme disease in real-time. We use a machine-learned classifier of web search sessions to estimate the number of individuals who search for possible Lyme disease symptoms in a given geographical area for two years, 2014 and 2015. We evaluate Lymelight using the official case count data from CDC and find a 92% correlation (p < 0.001) at county level. Importantly, using web search data allows us not only to assess the incidence of the disease, but also to examine the appropriateness of treatments subsequently searched for by the users. Public health implications of our work include monitoring the spread of vector-borne diseases in a timely and scalable manner, complementing existing approaches through real-time detection, which can enable more timely interventions. Our analysis of treatment searches may also help reduce misdiagnosis of the disease.
Highlights
Lyme disease is a common tick-borne illness caused by the bacterium Borrelia burgdorferi
Even when controlling for demographic variables associated with greater Lyme disease risk, Lymelight estimates for 2014 was the only variable significantly associated with predicting the target searches to discover adverse drug reactions
We believe that the CDC is relatively stable from 2014 to 2015, which enables methods such as Lymelight, which assess the incidence of disease better future estimates with the use of historical case data. in near real time, can help target and evaluate public health in the second stage we fixed the learned feature interventions to alleviate the negative health effects of climate change.[23] weights, and plugged in the Lymelight estimates for 2015, to predict CDC incidence for 2015
Summary
Lyme disease (borreliosis) is a common tick-borne illness caused by the bacterium Borrelia burgdorferi. Our eventual goal is to advance the state of the art in epidemiology to a point where issues of public health significance can be quantified in a timely and actionable way using readily available online data We call this general approach “machinelearned epidemiology”,14 and in this paper we report the results of estimates for 2014 substantially increased the predictive ability of the model, allowing it to explain R2 = 78.6% of the variance, an absolute difference of 63.22%. For generalized to other vector-borne diseases, such as malaria, instance, previous case reports on Ebola were used to estimate the dengue fever, Zika fever, and Chikungunya This becomes future number of cases in the Ebola epidemic.[29] In the case of important as climate change has the potential to Lyme disease, the number of cases for each year available from affect the transmission of vector-borne diseases.[22] We believe that the CDC is relatively stable from 2014 to 2015, which enables methods such as Lymelight, which assess the incidence of disease better future estimates with the use of historical case data.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
