Lyme Disease

Leveraging machine learning approaches for predicting potential Lyme disease cases and incidence rates in the United States using Twitter

BACKGROUND

Lyme disease is one of the most commonly reported infectious diseases in the United States (US), accounting for more than [Formula: see text] of all vector-borne diseases in North America.

OBJECTIVE

In this paper, self-reported tweets on Twitter were analyzed in order to predict potential Lyme disease cases and accurately assess incidence rates in the US.

METHODS

The study was done in three stages: (1) Approximately 1.3 million tweets were collected and pre-processed to extract the most relevant Lyme disease tweets with geolocations. A subset of tweets were semi-automatically labelled as relevant or irrelevant to Lyme disease using a set of precise keywords, and the remaining portion were manually labelled, yielding a curated labelled dataset of 77, 500 tweets. (2) This labelled data set was used to train, validate, and test various combinations of NLP word embedding methods and prominent ML classification models, such as TF-IDF and logistic regression, Word2vec and XGboost, and BERTweet, among others, to identify potential Lyme disease tweets. (3) Lastly, the presence of spatio-temporal patterns in the US over a 10-year period were studied.

RESULTS

Preliminary results showed that BERTweet outperformed all tested NLP classifiers for identifying Lyme disease tweets, achieving the highest classification accuracy and F1-score of [Formula: see text]. There was also a consistent pattern indicating that the West and Northeast regions of the US had a higher tweet rate over time.

CONCLUSIONS

We focused on the less-studied problem of using Twitter data as a surveillance tool for Lyme disease in the US. Several crucial findings have emerged from the study. First, there is a fairly strong correlation between classified tweet counts and Lyme disease counts, with both following similar trends. Second, in 2015 and early 2016, the social media network like Twitter was essential in raising popular awareness of Lyme disease. Third, counties with a high incidence rate were not necessarily related with a high tweet rate, and vice versa. Fourth, BERTweet can be used as a reliable NLP classifier for detecting relevant Lyme disease tweets.

Seroexposure to Zoonotic Anaplasma and Borrelia in Dogs and Horses That Are in Contact with Vulnerable People in Italy

Equine and canine anaplasmosis and borreliosis are major tick-borne zoonotic diseases caused by Anaplasma phagocytophilum and various species of Borrelia (the most important being Borrelia burgdorferi s.l.), respectively. This study evaluated the seroexposure to Anaplasma and Borrelia in dogs and horses used in Animal-Assisted Interventions or living in contact with children, elderly people or immunocompromised persons. A total of 150 horses and 150 dogs living in Italy were equally divided into clinically healthy animals and animals with at least one clinical sign compatible with borreliosis and/or anaplasmosis (present at clinical examination or reported in the medical history). Serum samples were tested with ELISA and immunoblot for the presence of antibodies against A. phagocytophilum and B. burgdorferi s.l., and the association between seropositivity and possible risk factors was analyzed using multivariate and univariate tests. Overall, 13 dogs (8.7%) and 19 horses (12.7%) were positive for at least one of the two pathogens. In addition, 1 dog (0.7%) and 12 horses (8%) were positive for antibodies against A. phagocytophilum, while 12 dogs (8.0%) and 10 horses (6.7%) had antibodies against B. burgdorferi s.l. Tick infestation in the medical history of the dogs was significantly associated with seropositivity to at least one pathogen (p = 0.027; OR 7.398). These results indicate that, in Italy, ticks infected with A. phagocytophilum and/or B. burgdorferi circulate in places where horses and dogs are in contact with people at risk of developing severe diseases. Awareness should be increased, and adequate control plans need to be developed to protect human and animal health, especially where vulnerable, at-risk individuals are concerned.

Increased macrophage phagocytic activity with TLR9 agonist conjugation of an anti- Borrelia burgdorferi monoclonal antibody

Borrelia burgdorferi (Bb) infection causes Lyme disease, for which there is need for more effective therapies. Here, we sequenced the antibody repertoire of plasmablasts in Bb-infected humans. We expressed recombinant monoclonal antibodies (mAbs) representing the identified plasmablast clonal families, and identified their binding specificities. Our recombinant anti-Bb mAbs exhibit a range of activity in mediating macrophage phagocytosis of Bb. To determine if we could increase the macrophage phagocytosis-promoting activity of our anti-Bb mAbs, we generated a TLR9-agonist CpG-oligo-conjugated anti-BmpA mAb. We demonstrated that our CpG-conjugated anti-BmpA mAb exhibited increased peak Bb phagocytosis at 12-24 h, and sustained macrophage phagocytosis over 60+ hrs. Further, our CpG-conjugated anti-BmpA mAb induced macrophages to exhibit a sustained activation morphology. Our findings demonstrate the potential for TLR9-agonist CpG-oligo conjugates to enhance mAb-mediated clearance of Bb, and this approach might also enhance the activity of other anti-microbial mAbs.

Altered Spatial and Temporal Gait Parameters in Mice Infected with Ross River Virus

Infection with mosquito-borne arthritogenic alphaviruses, such as Ross River virus (RRV) and Barmah Forest virus (BFV), can lead to long-lasting rheumatic disease. Existing mouse models that recapitulate the disease signs and immunopathogenesis of acute RRV and BFV infection have consistently shown relevance to human disease. However, these mouse models, which chiefly model hindlimb dysfunction, may be prone to subjective interpretation when scoring disease. Assessment is therefore time-consuming and requires experienced users. The DigiGait system provides video-based measurements of movement, behavior, and gait dynamics in mice and small animals. Previous studies have shown DigiGait to be a reliable system to objectively quantify changes in gait in other models of pain and inflammation. Here, for the first time, we determine measurable differences in the gait of mice with infectious arthritis using the DigiGait system. Statistically significant differences in paw area and paw angle were detected during peak disease in RRV-infected mice. Significant differences in temporal gait parameters were also identified during the period of peak disease in RRV-infected mice. These trends were less obvious or absent in BFV-infected mice, which typically present with milder disease signs than RRV-infected mice. The DigiGait system therefore provides an objective model of variations in gait dynamics in mice acutely infected with RRV. DigiGait is likely to have further utility for murine models that develop severe forms of infectious arthritis resulting in hindlimb dysfunction like RRV.

IMPORTANCE Mouse models that accurately replicate the immunopathogenesis and clinical disease of alphavirus infection are vital to the preclinical development of therapeutic strategies that target alphavirus infection and disease. Current models rely on subjective scoring made through experienced observation of infected mice. Here, we demonstrate how the DigiGait system, and interventions on mice to use this system, can make an efficient objective assessment of acute disease progression and changes in gait in alphavirus-infected mice. Our study highlights the importance of measuring gait parameters in the assessment of models of infectious arthritis.

Prevalence of Borrelia burgdorferi and Anaplasma phagocytophilum in Ixodid Ticks from Southeastern Ukraine

Objectives: Tick-borne diseases have emerged as an increasing medical problem in the world. Being the most prevalent ixodid ticks in Europe, Ixodes ricinus and Dermacentor reticulatus are responsible for transmission of numerous zoonotic pathogens (e.g., human granulocytic anaplasmosis and Lyme borreliosis). Despite their public health significance, studies on the prevalence of tick-borne agents are scare for Eastern Europe. The objective of this study was to examine the prevalence of Anaplasma phagocytophilum, Ehrlichia chaffeensis, and Borrelia burgdorferi sensu lato (B. burgdorferi s. l.) in ixodid ticks from Southeastern Ukraine. Methods: Over a 5-year period (2014-2018), 358 questing and 389 engorged ixodid ticks were collected from Southeastern Ukraine (Zaporizhzhya region). The ticks were identified as Dermacentor marginatus, D. reticulatus, I. ricinus, and Rhipicephalus rossicus. Nucleic acid samples extracted from tick pools were subjected to RT-PCR analyses for A. phagocytophilum, E. chaffeensis, and B. burgdorferi s. l. Results: The examined ixodid ticks tested negative for the aforementioned pathogens with the exception of I. ricinus ticks. For questing I. ricinus ticks, minimum infection rates of A. phagocytophilum and B. burgdorferi s. l. were, respectively, 4.2-7.7% and 8.6-12.7%. Conclusions: These findings will be valuable for medical and veterinary practitioners when risks associated with tick-borne diseases are assessed for southeastern regions of Ukraine.