LymeSentinel

Approved

LymeSentinel - DASHBOARD https://diseasemodeling.github.io/TopXHHSLymeInnovation_Dashboards/

TEAM: https://diseasemodeling.github.io/TopXHHSLymeInnovation_Dashboards/Team.html

LymeSentinel is a Forecasting System: 

The goal is to detect counties with risk of transition to a higher risk status for Lyme. It uses two types of signals to make that risk assessment. One detects potential for newly emergent Blacklegged ticks and Western Blacklegged ticks in counties that were previously not at risk. The second detects potential for temporal shifts in human Lyme cases over time. Both forecasting systems are intended for use by health officials involved in monitoring, surveillance, and preventive efforts. As the distribution of Lyme carrying ticks emerge across new geographies, detecting these signals ahead of time can help with timely action, including issuing clinician and public awareness.  LymeSentinel is Informed by Stakeholder Input: 

We conducted a stakeholder input call with a clinical epidemiologist who collaborates with clinicians and leads patient cohort and case-series research, and a public health data scientist who supports a Lyme dashboard. Both stakeholders use Lyme surveillance data to understand geographic trends, changing endemic areas, and disease burden.

They identified a central challenge motivating LymeSentinel --Lyme surveillance data are valuable, but are often released with a 1-to-2-year delay, limiting the ability of public health agencies, clinicians, researchers, and the public to understand current or emerging risk. They indicated that more timely data, ideally monthly during the seasonal Lyme period, could help identify when local risk is beginning, support clinical preparedness, and inform public awareness and prevention. This need is especially important in counties where tick populations and Lyme risk are newly emerging.

Stakeholders also emphasized that human surveillance data alone are incomplete. Lyme disease can be difficult to diagnose, early diagnostic tests may be unreliable, and reported cases depend on individuals seeking care and clinicians recognizing symptoms. Similarly, a county’s “No Records” tick classification may reflect limited surveillance rather than the absence of ticks. They highlighted the value of integrating complementary data sources, including tick surveillance, climate and environmental data, insurance claims, and electronic health records data. LymeSentinel directly addresses these needs by combining multiple data streams to forecast changes in tick establishment and Lyme risk ahead of delayed annual human case surveillance data.

LymeSentinel Provides Synthesized Analysis through an Interactive Dashboard:  

A GIS map that shows current tick-status at the county level, alongside risk of transition to a higher risk-status in the year ahead. It uses CDC defined classification of tick-status, ‘No Reports’, ‘Reported’, ‘Established’. It also shows reported human case rates in each county, over time, up to latest year, and forecasts for the year ahead. Consensus risk score uses predictions from each model and signal type (ticks and human cases in current version) to rank counties by risk of transition.

LymeSentinel is a Hub for Lyme Forecasting Models: 

The underlying methodologies informing the dashboard predictions will be an ensemble of models, each model built independently by different researchers using different methods, providing more confidence and stability in forecasts. We currently have 3 models for tick transition, and two models for human case shift. Our goal is for this to serve as a hub for scientific collaboration, where researchers can submit their models and forecasts. As Lyme cases are driven by interacting systems, including ecology, epidemiology, climate, and human behavior, forecasting Lyme involves a pipeline of models. We envision a future version where researchers can share stand-alone system modules (e.g., tick ecology, epidemiology of Lyme), for reuse by other researchers in their own modeling pipelines. A documentation page would document methodology, and data sources. The hub would also provide processed data files in a common format, for use by other models. For example, our compiled data was standardized with columns GEOID, Statename, County name, YEAR, Month, followed by columns specific to weather (temperature, precipitation,),  land cover (cultivated, developed, etc), socioeconomic (income, poverty, etc). Over time, we envision that this compiled data, including new data potentially generated from other teams in this challenge, will facilitate innovative research directions for forecasting of Lyme and also other vector-borne diseases. The hub is designed as a living dashboard and allows for updates as new data and models become available. The data-driven models are expected to improve in accuracy and precision as more data becomes available. As a future direction, we expect to ensemble the results from the different models contributed to the hub, providing more confidence and stability in forecasts.

LymeSentinel Estimates Transition Risk using Ensemble Machine Learning Methods from Multiple Signals:  

We use both tick status and human cases to asses risk, and an ensemble methods in each analysis. We use scientific machine learning that integrate robust math models with AI models, allowing to capture complex dynamics between climate and ecology, while accounting for data bias. We describe below the models driving the two complementary analysis. The first predicts tick-status and identifies counties with newly emergent risk. The second forecasts future cases of Lyme. The goal is for an ensemble analysis using multiple methods. We provide an overview of our current-status below, and hope to expand it in the future

 Forecast tick-status to detect counties with newly emergent risk

Methods: Neuro Symbolic regression to predict tick status and forecast change in tick-status

Background: CDC’s tick surveillance system tracks and classifies tick status into three classes: No Records (No ticks or not documented), Reported (<6 ticks in 12-month period), and Established (6+ ticks in 12-month period). Publicly available data are at the county level and limited to years 1996, 2016, 2018, 2019, 2020, 2023. The goal is to train a model to predict tick-status for each year each county, to track changes over time, and forecast tick status for the year ahead. We summarized the data sources used in these models at the end of this document.

 Methods: We trained three machine learning models, neural networks, random forests, and XGBoost, to predict tick status as the dependent variable using climate, land cover, terrain, and rural classification as independent variables. Surveillance data labels are incomplete, specifically, ‘No record’ could mean both ‘no-ticks’ or ‘no data’.

 Results and Validation: We used F1 score as the performance metric. The F1 score for predicting tick-status  was ~65%. Consensus transition risk score assigned to each county was based on each model's probability of transition and number of models agreeing with these results. Symbolic regression converted blackbox model into interpretable mathematical expressions, to understand what features influenced the model predictions.

Forecast future cases of Lyme, to detect changes in trend

We describe two models

Data:

We used climate, land cover, terrain, socio-economic factors, and tick-status as independent variables. Response as reported human case rate

Model 1: NeuralCDE (controlled differential equations). 

We used NeuralCDE to train the model. We chose this method as the data is irregularly sampled, e.g., tick-status were samples for only 5 years between 1996 and 2023, different time intervals, e.g., temperature and precipitation are available as monthly averages, while data such as land cover and forest cover are at annual intervals, and controlled signals, e.g., potential changes in case definition.  

 Model 2: Reduced order NeuralCDE

Background: High-fidelity AI-based methods are undoubtedly effective for many tasks, including forecasting. However, training time can be considerable. This introduces difficulty in Lyme disease surveillance, where data are regularly updated, as the incorporation of such data, in principle, can require full model retraining. Reduced-order NeuralCDE accelerates this process. Training costs are reduced to a few minutes on conventional  hardware, allowing for seamless integration of new/updated data, as well as enabling techniques like Monte Carlo analyses of the models themselves while remaining tractable computationally.

Concept: While relevant time series data across jurisdictions/variables are, in some sense independent, in practice we expect that processes underlying Lyme disease (for example, diffusion of tick and vector populations, precipitation/temperature, etc) to result in substantial correlation across indicators. Intuitively, this approach seeks to, rather than forecast for each quantity individually, to identify a small number of correlations underlying the outputs. Then, we learn and forecast just a handful of time series corresponding to each distinct correlation. For example, to forecast human case rates in 3,310 counties, instead of training on each county, we were able to extract 5 common correlation factors, and train/learn 5 time series rather than 3,310. This reduced training time to minutes. NeuralCDE allowed for accounting for missing and irregularly sampled data, and enable continuous projections.

Proof-of-concept/results: We used county-level annual data on human case rate, together with important indicators (temperature, participation, tick status, as well as changes in case definitions/reporting protocol). Training the model took approximately 4 minutes. Case rates per county for 2022-23 (not included in the training data) were predicted with an R-squared of .825 for 2022 and .757 for 2023.

Solution Overview (MVP Demonstration):

Data & AI Solution

Live demo, prototype, or working product

https://diseasemodeling.github.io/TopXHHSLymeInnovation_Dashboards/

Access instructions (if needed)

https://diseasemodeling.github.io/TopXHHSLymeInnovation_Dashboards/

Results for the American People:

Target user: Federal and local public health officials can use LymeSentinel to monitor and review forecasts alongside existing surveillance systems, to communicate future risk with healthcare systems and general public.  Public awareness will help prevention. Clinical awareness, especially in previously low risk counties, will help early diagnosis and surveillance reporting, which then feed into improved surveillance data and forecasts, creating a data feedback cycle for improved monitoring and prevention.

LymeSentinel fits into and leverages existing workflow: For example, currently the Centers for Disease Control and Prevention (CDC) monitors Lyme cases using national surveillance systems and four other data sources: insurance claims, SubLyme that integrates electronic health records, Tick Bite Data Tracker that shares emergency department data on visits for tick bites, Tick Surveillance Data Sets. These are all surveillance systems, tracking current and previous cases. LymeSentinel uses these datasets, and others (noted above) to forecast future risk.  LymeSentinel improves prevention and early diagnosis by creating a data sharing loop: Forecasted risk can be communicated back to healthcare systems for clinician and public awareness. Increased awareness can improve surveillance data, to consequently improve forecasting. This data sharing and feedback loop to improve surveillance data, and forecasting, in the long-term, can improve prevention and early diagnosis.

Data, Tech & Evidence Driven Approach

LymeSentinel uses open-access dataset: Our work used many publicly available data sources. The list of data sources are included  in a table above. 

LymeSentinel can be integrated into CDC workflow:  Our goal is to partner with federal partners and other modelers and datasources to 1) integrate surveillance data into our forecasting modeling workflow.2) integrate outcomes from our work into CDC systems workflow for both monitoring and disseminating risk assessment with healthcare systems and public awareness systems. Our group can also assist in updating model training with new data or modeling assistance to address data gaps.   

Execution, Efficiency & Delivery

LymeSentinel complements current surveillance systems by helping with preparedness: While Lyme disease surveillance systems serve to document actual cases, LymeSentinel projects future cases. As the distribution of Lyme carrying ticks emerge across new geographies, detecting these signals ahead of time can help with timely action, including issuing clinician and public awareness. 

 LymeSentinel improves prevention and early diagnosis by creating a data sharing feedback loop: Forecasted risk can be communicated back to healthcare systems for clinician and public awareness. Increased awareness can improve surveillance data, to consequently improve forecasting. This data sharing and feedback loop to improve surveillance data, and forecasting, in the long-run, will improve prevention and early diagnosis.  

Scalability, Reuse & Societal Impact:

LymeSentinel is a Hub for Forecasting Lyme Risk Transitions: It currently forecasts two signals, tick status transitions using three ML models, and temporal shifts in human cases using two scientific machine learning models. Our goal is for this to serve as a hub for scientific collaboration, where researchers can submit their models and forecasts to improve ensemble analysis. 

LymeSentinel is a Hub for System Modules: More intricate models of the interacting systems, such as ticks ecology, Lyme epidemiology, climate, and human behavior can help improve Lyme forecasting. We envision a future version where researchers contribute these independent system models, that can then be used as modules in the forecasting model pipeline to forecast Lyme and other vector-borne diseases. 

Partner with other Hubs/Systems: Our goal is to serve a hub for forecasting models. These models need regular data stream .Our goal is to reach out to partner with other modelers and data sources to use and link models on LymeSentinel to their compiled and processed data. As some of the data are not in a monthly resolution, our goal is to provide a curated monthly dataset, by using modeling where raw data are unavailable. Over time, we envision that this compiled data, including new data potentially generated from other teams in this challenge, will facilitate innovative directions to improve Lyme risk forecasting, prevention, and early diagnosis.  

edited on Oct 28, 2026 by Chaitra Gopalappa
Public (8)
You will need to login to post a comment
Uri Kartoun 3 weeks ago

LymeSentinel’s ensemble of independent models is a smart answer to the 1-to-2-year surveillance delay, and retraining in about four minutes is what makes a living dashboard realistic. I also appreciate how openly you describe the limits: your stakeholders’ point that “No Records” can mean “not looked at” is the right starting question for emerging counties.

That point connects to one finding in my entry (simulator 8). Kugeler et al. (Emerg Infect Dis 2021) estimated from insurance claims that about 476,000 people were diagnosed and treated for Lyme each year, against roughly 35,000 reported through surveillance. They also found that 19% of the claims-based diagnoses were in low-incidence states, against about 5% in surveillance (chart attached). The authors say this gap mixes under-reporting with possible overdiagnosis, so it is a signal to weigh, not proof. Still, it suggests the claims data you already list could add something in counties where Lyme is newly appearing, which is exactly where your forecasts are meant to help.

My entry takes papers like this one and turns each into a simulator you can change and check against federal data: https://invisibleillness.crowdicity.com/post/896844

Congratulations on a thoughtful, well-documented entry, and I wish you every success with the hub.

Users tagged:

Reply 1

Chaitra Gopalappa 3 weeks ago

Thank you for the thoughtful comments. Your compilation through simulation is a great idea, and could be a great resource. We indeed did find that including other signals to control for under-reporting improves model fit. We hope to continue this direction and hopefully be a publication that can add to your simulator data.

Reply 0

Uri Kartoun 3 weeks ago

Thank you, Chaitra. I’m glad the comments were useful, and it’s encouraging that adding other signals to control for under-reporting improved the model’s fit. I’d be glad to read your publication when it’s out, and to try it in the simulator if you’d like to share it. I wish you every success with the work.

Users tagged:

Reply 1

Chaitra Gopalappa 3 weeks ago

LymeSentinelTeam: Jessica Boakye, Diana Prieto, Diego Martinez, Hashir Tanveer, Alex Viguerie, Chaitra Gopalappa

Reply 0

Sulamit Berkovits 3 weeks ago

I wanted one more look at yours before tomorrow's final meeting, and your point about no records not meaning no ticks stopped me again. A forecast a year ahead is exciting, but I keep thinking about the clinician in a newly flagged county. How do you share that news without causing a panic, and what do you learn when a forecast misses? That loop back, from forecast to real reporting, feels like where the real value will show up.

Reply 0

Scott Savitt 3 weeks ago

Hi Chaitra, thanks for sharing your project. I'm curious: what's one thing you wish you'd known when you started, or something you'd have built in earlier if you could go back?

Reply 0

Pranisha Karki 2 weeks ago

Hi Chaitra, flagging counties a year before surveillance data catches up could really help health departments plan ahead. How have you tested the forecasts, for example by looking back at past years when ticks spread into new counties, and how well did the model do?

Reply 0

Pranisha Karki 2 weeks ago

Hi Chaitra, pairing one analysis for counties where ticks may be newly emerging with another that forecasts future Lyme cases gives health officials two useful views. Would you be open to us pointing people to LymeSentinel? We could add a "Where is risk rising?" button on our Lyme disease page that opens your dashboard. If a link back ever suits you, that would be lovely, but there's no expectation. How does that sound to you?

Reply 0

Pranisha Karki 2 weeks ago

Hi Chaitra, your stakeholders' point that surveillance data can arrive 1 to 2 years late explains the need well. Of your two signals, new tick emergence or shifts in human cases, which do health officials find more useful?

Reply 0

Pranisha Karki 1 week ago

Your consensus transition score already considers each model's probability and how many models agree. Showing that agreement count next to a county's flag, not only the combined score, would help an official see whether the alert is a close call or a finding several models share.

Reply 0