Nosotrack integrates clinical, genomic and mobility data to identify how infections spread and devise targeted interventions.
Every outbreak is different. Effective control requires rapidly identifying the specific drivers of transmission: who infected whom, who the superspreaders are, which cases are undetected or imported, where and how transmission occurred, and who is most at risk.
Healthcare facilities are among the highest-risk environments for infectious disease transmission, bringing together vulnerable populations, frequent close contact, and diverse pathogens. Healthcare-associated infections (HAIs) remain among the most common adverse events in healthcare delivery.
antibiotic-resistant HAIs / year
HAIs are a major driver of the antimicrobial resistance (AMR) crisis, one of the WHO's top global health threat.
annual deaths
The WHO's projected mortality from HAIs unless infection-prevention investment scales meaningfully in the next decade.
AMR's most underrated driver
Hospital outbreaks are the breeding ground for resistant strains. Stopping them earlier is the cheapest and most efficient solution.
Current outbreak surveillance tools work in silos. Nosotrack fuses their data streams into a unified outbreak analytics engine.
Nosotrack infers who-infected-whom in real-time, enabling infection prevention and control teams to identify how infections spread and design targeted interventions before outbreaks escalate
Nosotrack reconstructs transmission chains in near real-time by integrating epidemiological, genomic and contact data using the open-source Bayesian inference framework outbreaker2. It identifies the likely source of each infection and quantifies the uncertainty around it.
Designed to work across pathogens, healthcare settings and outbreak scenarios, Nosotrack enables response teams to understand how outbreaks spread, and determine when and where to intervene.
Nosotrack's vision is to become the operating system for infectious disease response.
We aim to build an integrated outbreak intelligence platform that brings together transmission analytics, contact tracing, rapid diagnostics, sequencing and field epidemiology to support outbreak response across settings and scales.
Built on over a decade of published methodological research by our team and peers. Its inference engine (outbreaker2) is grounded in scientifically validated methods that have become part of the standard toolkit for outbreak response worldwide.
These methods have supported real-world outbreak investigations by hospitals, research institutions and public health agencies, including SARS-CoV-2 nosocomial outbreaks in Switzerland and the UK, Klebsiella pneumoniae in a Nepali neonatal unit, vancomycin-resistant Enterococcus faecium in an Australian tertiary hospital, multidrug-resistant Acinetobacter baumannii at a burn centre in North Carolina, and Ebola in Guinea.
Founder
Johns Hopkins University
Research Fellow in epidemic forecasting at the Johns Hopkins Bloomberg School of Public Health, working with the US CDC Center for Forecasting and Outbreak Analytics. PhD in mathematical modelling of infectious diseases from Imperial College London, specialising in Bayesian reconstruction of transmission chains. Executive board member and developer for the R Epidemics Consortium.
Advisor
Imperial College London
Associate Professor specialising in real-time outbreak analysis and epidemiological modelling. Lead author of EpiEstim, widely used by public health agencies worldwide to monitor pathogen transmission, and co-author of outbreaker. A member of the Imperial College COVID-19 Response Team whose modelling informed the UK government's Scientific Advisory Group for Emergencies.
Advisor
Imperial College London
Associate Professor specialising in outbreak response analytics and infectious disease modelling. Lead author of outbreaker and founder of the R Epidemics Consortium. A World Health Organization (WHO) consultant and member of its COVID-19 analytics team, and a member of the UK Public Health Rapid Support Team, he has contributed to major field responses including Ebola in the Democratic Republic of the Congo.
Nosotrack is currently at the research and development stage.
A prototype, live at nosotrack.onrender.com, demonstrates the core outbreak-reconstruction engine (outbreaker2) with an integrated LLM interface. Additional modules, including contaminated-source (e.g. medical device) identification and an intervention simulator, are under development.
Conduct simulation studies under realistic operational constraints to determine the conditions under which Nosotrack improves outbreak control.
This phase will assess Nosotrack's effectiveness across pathogens, hospital settings, and levels of data availability.
Deploy the platform in real-time in a hospital environment.
This phase will generate real-world evidence on reduced infections, cost savings, and improved hospital capacity management.