India’s disease surveillance capabilities have received a major boost with the deployment of an Artificial Intelligence–powered tool, which has issued more than 5,000 real-time alerts of infectious outbreaks since its rollout in 2022. The system, installed at the National Centre for Disease Control (NCDC), is designed to accelerate early warning signals and reduce delays in public health responses.
‘Health Sentinel’ Cuts 98% of Manual Workload
The study highlights that New Delhi–based Wadhwani AI has developed the ‘Health Sentinel’ platform, which has significantly cut down manual workload by as much as 98 per cent. According to the pre-print findings, the AI-driven mechanism enhances the speed and precision of outbreak detection, enabling faster interventions by health authorities.
Read More| PhonePe and OpenAI Join Forces to Transform User Experience
India’s Surveillance Framework Under IHR
Nearly 200 countries operate national disease surveillance systems under the legally binding International Health Regulations (IHR), working alongside the World Health Organization (WHO) to strengthen global health security. India, under its Integrated Disease Surveillance Programme (IDSP), traditionally relies on scanning print, electronic, and online news reports for signals of unusual health events before sending them for verification by authorities.
AI Scans Millions of Articles in 13 Languages
‘Health Sentinel’ automates this process by scanning media content daily in 13 languages. The authors of the study noted that the tool has processed more than 300 million news articles since April 2022, identifying over 95,000 unique health-related events across the country. Out of these, epidemiologists at the NCDC flagged more than 3,500 events—around four per cent—as potential outbreaks needing attention.
5,000+ Real-Time Alerts Issued Since 2022
Between April 2022 and April 2025 alone, the AI system generated over 5,000 real-time alerts for state and district health departments, Wadhwani AI researchers told PTI. Parag Govil, National Program Lead for Global Health Security at the organisation, explained that earlier, analysts relied entirely on manually reviewing newspapers, journals, and reports to identify potential disease events.
Also Read| Microsoft Unveils Its Most Ambitious AI Infrastructure Yet — the Planet-Scale Superfactory
Human-in-the-Loop Approach Strengthens Verification
He added that the introduction of the tool has replaced the manual screening step while maintaining a human-in-the-loop approach, ensuring that epidemiologists verify all information before it is shared with officials. This hybrid model supports traditional passive surveillance systems, which primarily depend on infection reports sent by physicians and healthcare facilities.
Growing Need for Automated Media Monitoring
The authors pointed out that monitoring informal sources, including digital media, has become increasingly crucial as the volume of published content grows daily. Manual screening, they said, is no longer practical. The Health Sentinel platform uses AI to extract information on unusual health events or potential outbreaks from news articles, addressing key gaps such as multilingual processing and faster alert generation.
AI Detected 150% More Events Than Manual Methods
Researchers observed a 150 per cent rise in detected health events since the system’s installation in 2022, compared to previous years of manual surveillance. In 2024, 96 per cent of events published by the national surveillance system were identified through the AI tool, while only four per cent came from manual screening.
Kerala Pilot Confirms Value of Event-Based Surveillance
Several studies have underscored the value of complementing traditional surveillance with online content, including news reports and social media posts, to improve outbreak detection. A pilot study published in the Indian Journal of Medical Research earlier this year tested an event-based surveillance system across six private hospitals in Kerala’s Kasaragod district. The system analysed case records of patients admitted with acute febrile illness (AFI), using algorithms to detect patterns such as rashes, haemorrhage, or unusual clustering of cases.
Also Read| Jaipur Installs India’s First Street Air Purifiers as Air Quality Drops
Clusters Reveal Early Signals of Dengue and COVID-19
Between May and December 2023, around three-fourths of the more than 4,500 AFI patients were evaluated using the algorithm. Of the 88 clusters identified, 76 per cent were linked to severe acute respiratory illness, followed by cases of acute encephalitis syndrome and AFI accompanied by rashes. Ten clusters were verified as events, nine of which were confirmed outbreaks, including dengue and COVID-19.
EBS Model Shows Expansion Potential
Researchers concluded that event-based surveillance in private health facilities helped detect outbreaks earlier and could be expanded to districts at higher risk of zoonotic spillover.
Global Studies Reinforce AI’s Role in Disease Tracking
Earlier reviews also highlight the growing use of online platforms for disease monitoring. A 2020 study published in the Journal of Biomedical Informatics examined 148 research articles on using social media—especially Twitter—for healthcare surveillance between 2010 and 2019. About one-fourth of the studies focused on flu surveillance, with machine learning tools widely applied to analyse real-time user-generated data.
Read More| Lava Makes Bold Europe Debut With UK Entry in 2026
Media-Based AI Surveillance Strengthens Public Health Response
Similarly, a 2017 study in the American Journal of Tropical Medicine and Hygiene showed that analysing news reports can help compensate for delays in obtaining official country-level case confirmations for infections like dengue. Together, the research reinforces that AI-enhanced media surveillance systems, such as ‘Health Sentinel’, can serve as powerful additions to India’s public health infrastructure.
