AI in Public Health Surveillance

This new paper by Sergio Consoli et al explores how generative AI can transform unstructured outbreak data into structured, searchable knowledge. The team developed an epidemiological knowledge graph (eKG) using WHO Disease Outbreak News (DONs), applying an ensemble of large language models to extract details such as disease name, country, date, and number of cases or deaths. The researchers used open-source models including Mistral, Zephyr, and Meta-Llama to extract information from over 3,000 outbreak reports. They structured this data into a FAIR-compliant knowledge graph, linking it with biomedical and geographic ontologies. The resulting resource—comprising nearly 3,000 outbreak events—is now publicly accessible via SPARQL endpoints and visualization tools. This matters because many official outbreak reports remain locked in prose, making them difficult to analyze at scale. With eKG, public health professionals can conduct detailed, structured queries across decades of global outbreak data. This significantly improves our ability to track, analyze, and respond to emerging health threats. The big takeaway: AI can unlock the full value of legacy outbreak data by transforming it into structured, interoperable formats that support real-time analysis and response. This approach opens new possibilities for integrating informal sources like news and social media into formal disease surveillance systems, advancing global preparedness and early warning capabilities. https://lnkd.in/ePc54yvQ #GlobalHealth #PathogenSurveillance #HealthInnovation #PublicHealth

THE ROLE OF ARTIFICIAL INTELLIGENCE IN PANDEMIC RESPONSES: FROM EPIDEMIOLOGICAL MODELLING TO VACCINE DEVELOPMENT. This compelling review delves into the multifaceted role of artificial intelligence (AI) in addressing pandemics as global health crises. It explores AI's contributions to preparedness and response efforts, including advanced epidemiological modeling, accelerated vaccine development, and improved methods for screening, forecasting, contact tracing, and virus monitoring. The article also emphasizes the importance of sustained research, real-world applications, ethical use, and the strategic integration of AI technologies to enhance our collective capacity to tackle and mitigate the impacts of global health challenges. A must-read for those interested in the intersection of technology and public health. Molecular Biomedicine 2025; 6:1. https://lnkd.in/gM4V34py.

WHO upgrades its public health intelligence system to boost #globalhealth security The World Health Organization (WHO), in collaboration with key partners and supporters, launched version 2.0 of the Epidemic Intelligence from Open Sources (EIOS) system, used globally for the early detection of #publichealth threats. Since its development in 2017, the initiative has grown steadily and is now being used by more than 110 Member States and around 30 organizations and networks around the world The update incorporates new #data sources and improved functionalities, including the use of #artificial #intelligence #AI Hosted at the WHO Hub for #Pandemic and #Epidemic #Intelligence in Berlin, EIOS is the world’s leading initiative for open-source intelligence for public health decision-making. It helps public #health teams detect and respond to potential #threats daily by analyzing large volumes of publicly available information in near real time. Recent health #emergencies, such as the #COVID‑19 pandemic, and the #mpox and #avian #influenza #outbreaks, have demonstrated how critical early detection is to prevent outbreaks from escalating into global #crises. With version 2.0, public health experts around the globe are now better equipped to quickly identify new health threats and monitor ongoing events, whether they are linked to #conflict, #climate change, or new and re-emerging #pathogens. Version 2.0 is the most significant upgrade to the custom-built technology and includes several new features: Built for growth: The system has been rebuilt to process more sources, accommodate more users and allow new features to be added more quickly. AI integration: Implementation of latest AI-powered tools enhancing automated analysis and signal detection Variety of sources: The tool can now process additional sources, such as radio channels, which are automatically transcribed and translated Simpler and multilingual interface: The new interface can be translated in multiple languages, making it more accessible for non-English speakers, and a new dashboard view helps users find and share the most relevant reports more quickly Better collaboration: Users across countries and organizations can now track and monitor events jointly more easily WHO offers the EIOS system as a public good, free of charge to its Member States and eligible organizations and supports them with #training and #communities of practice. Ministries of Health and public health agencies use the EIOS system to complement information they receive through formal channels, such as #laboratories and #hospitals The EIOS system enables them to identify relevant content from #websites, #social #media and other public sources to identify important health events, which authorities can then verify and assess European Commission https://lnkd.in/eHJ_dCQi

Sharing our new peer reviewed article:  https://lnkd.in/ggtCnExS At Waymark, we have developed and deployed custom AI solutions that provide continuous population health surveillance, proactively monitoring for clinical red flags and clinical optimization opportunities between healthcare encounters when physicians aren't present to identify high risk situations. This augments the ability of our teams to prevent poor patient outcomes between clinic visits, enabling 24/7 detection of concerning health trends before costly emergency department visits or hospitalizations. This work was co authored by Pablo Bermudez-Canete (Stanford / Paratus), Tannen Hall (Stanford / Paratus) & Pranav Rajpurkar (Harvard / a2z), contributing to the development of AI-driven population health monitoring.

🎙️We dive into the fascinating world of wastewater-based epidemiology and AI with Dr Mariana Matus, co-founder and CEO of Biobot Analytics. We explore how AI is revolutionizing public health by analyzing wastewater to predict population health threats. Here are three key takeaways: 🌟 Harnessing Wastewater for Public Health Insights: Dr. Mattis shared how BioBot is transforming wastewater infrastructure into public health observatories. By analyzing wastewater samples from various communities, they can identify disease indicators and track outbreaks before they escalate. This proactive approach allows health officials to prepare and allocate resources effectively, potentially saving lives and minimizing the impact of diseases like COVID-19 and influenza. 🌟 The Power of AI in Data Analysis: One of the most exciting aspects of BioBot's work is the integration of AI in their data analysis processes. AI helps model regions where primary data collection is challenging, ensuring that the insights generated are representative of entire populations. This capability not only enhances the accuracy of predictions but also allows for a more comprehensive understanding of public health trends across different locations. 🌟 Ethical Considerations and Community Trust: As pioneers in this innovative field, Dr. Mattis emphasized the importance of ethical considerations in their work. BioBot has established a code of conduct to ensure that the data collected is always anonymized and aggregated, protecting individual privacy. By prioritizing transparency and scientific rigor, they aim to build trust with the communities they serve, which is crucial for the success of their initiatives. This episode is a must-listen for anyone interested in the intersection of technology, public health, and data science. Join us as we uncover how wastewater analysis can lead to groundbreaking advancements in disease prevention and health management. 🎧 Tune in now to hear more about this revolutionary approach which is a lot more accurate than many other data approach for this kind of prediction (including other wastewater analysis approaches) and the future of public health! https://lnkd.in/deB6e8SF #PublicHealth #AI #WastewaterEpidemiology #BioBot #Podcast #Innovation #HealthTech