BlueDot’s intelligence platform empowers public and private sector organizations to rapidly identify, understand, and effectively respond to global infectious disease threats. Combining human and artificial intelligence to track the activity of hundreds of infectious diseases and syndromes worldwide, it applies academic data science and deep subject matter expertise to anticipate global spread and impact. Founded in 2013 and used by the City of Chicago, Taiwan CDC, Air Canada, and more, BlueDot helps clients make critical decisions with clarity and confidence.
Infectious diseases pose a growing global threat, as evidenced by recent outbreaks like the COVID-19 pandemic, the mpox global public health emergency, and an expanding number of avian influenza outbreaks. To prevent health, economic, and social disruption from outbreaks, public and private sector organizations need access to unbiased, accurate, real-time, and global intelligence about disease threats. For more than a decade, BlueDot has generated and disseminated such intelligence through its technology platform. However, until now, it was only accessible via complex API calls tailored to data engineers and data scientists.
BlueDot sought to make its insights more accessible and timely while ensuring the highest level of accuracy. Using the fine-tuned Cohere Classify and Cohere Rerank solutions, BlueDot created an interactive platform that makes infectious disease intelligence available to users through natural language.
Previously, tapping into BlueDot’s real-time, infectious disease surveillance data and intelligence required significant technical expertise. Users had to understand which of BlueDot’s many API endpoints – including real-time reports of disease cases, disease spread forecasts, and more – to leverage and structure programmatic calls to the API. This limited adoption to skilled data scientists, engineers, and epidemiologists, creating delays in insight generation and ultimately, real-world action. Dr. Kamran Khan, CEO of BlueDot, explains, “By reducing the technical barriers to interact with a diverse array of complex global data, almost anyone can now generate powerful insights in just a matter of seconds.”
BlueDot’s vision was to create a highly accesible solution that empowers users to ask questions in plain language and receive accurate responses instantly. However, translating intricate data queries into precise API calls presented a significant challenge. Initial trials with embedding techniques proved inadequate, failing to discern the subtleties between queries, such as “COVID cases in Italy” and “disease outbreaks in Italy.” To preserve the integrity of insights and client trust, BlueDot needed a system that consistently and reliably identified the most appropriate API endpoint for every user query made in natural language.
BlueDot first experimented with embedding-based techniques, but this failed to achieve the necessary level of accuracy, delivering less than a 50% match rate. Then, the BlueDot team found their answer with Cohere, using a fine-tuned Cohere Classify and Cohere Rerank. In production, these endpoints to the Cohere API work in tandem with impressive, low-latency query processing in milliseconds.
A fine-tuned Classify first retrieves a list of candidate API endpoints based on the query, then Rerank reorders the candidates to prioritize the most relevant ones. According to BlueDot’s Machine Learning Engineer Nick Gibb, “The integration of Cohere’s technology marked a significant leap in performance. The right endpoint now appears more than 97% of the time.”
This level of accuracy was unachievable with other approaches. This new system captures subtle linguistic nuances that were overlooked by basic embedding techniques, with fast and affordable implementation compared to developing a similar in-house solution. Nick Gibb explains, “Cohere's fine-tuned models were easy to test, going live in less than an hour.”
Efforts are ongoing to further refine the system, targeting perfect 100% accuracy. BlueDot employs an evaluation protocol that rigorously assesses the accuracy of fine-tuned Classify and Rerank solutions. This protocol makes sure that the system consistently interprets user queries correctly and reliably directs them to the right data source for accurate responses. It confirms that the system understands user questions well enough to connect them to the data that is needed.
A dedicated team handled the Cohere integration, including four software engineers, one product owner, and one product designer. The new system uses BlueDot's data assets, curated and maintained by infectious disease epidemiologists, clinicians, veterinarians, and data scientists.
With Cohere’s custom models in place, BlueDot launched its initial beta trial with its public and private sector clients. BlueDot’s CEO, Dr. Khan noted, “BlueDot’s intelligence informs decisions that impact millions of lives worldwide. This is why our approach to AI development is so rigorous. Cohere is a key partner in helping us make our intelligence more accessible through natural language, while ensuring users are empowered with the specific data they need."
By removing technical barriers, BlueDot now enables faster, more effective, and better coordinated organizational responses to global infectious disease threats. Public health agencies, life sciences companies, multinational enterprises, and more can now monitor global threats, understand them faster, and take appropriate actions sooner. What once took days to generate actionable insights now takes minutes, thanks to the broader access to BlueDot’s global intelligence through natural language.
Cohere remains a valued partner as BlueDot advances the natural language interface to handle multi-turn conversations and queries requiring orchestration across multiple endpoints. Together, BlueDot and Cohere are driving transformational change in how organizations combat, prepare for, and respond to infectious disease outbreaks worldwide.
"Cohere is a key partner in helping us make our intelligence more accessible through natural language, while ensuring users are empowered with the specific data they need."