An AI-powered tool launched by the National Center for Disease Control (NCDC) in 2022 likely helped health authorities alert more than 5,000 infectious disease outbreaks in real time, a new study found.
Dubbed ‘Health Sentinel’, developed by New Delhi-based healthcare AI solutions provider Wadhwani AI, the tool is India’s latest weapon in digital surveillance.
The use of artificial intelligence could help reduce 98% of manual workload, facilitate much faster detection of outbreaks and proactive public health response, according to the paper, as reported by news agency PTI.
Almost 200 countries worldwide are legally bound by the International Health Regulations (IHR) to operate a national disease surveillance system. The IHR and the World Health Organization work together to protect global health security.
How does the AI tool work?
The ‘Health Sentinel’ works by scanning a huge volume of media reports and news articles in 13 languages every day to detect unusual health events, which are then shared with the authorities for further action if deemed necessary.
The authors wrote: “From April 2022 to date, Health Sentinel has processed more than 300 million news articles and identified more than 95,000 unique health events across India, of which more than 3,500 events (four percent) were selected by NCDC public health experts as potential outbreaks.”
According to Parag Govil, National Program Leader for Global Health Security at Wadhwani AI, this AI solution has replaced the tedious process of manually scanning newspapers, magazines and reports to identify relevant articles.
However, the system maintains a “human-in-the-loop” approach, which ensures that epidemiologists do the necessary verification before the information is disseminated to state and district officials, PTI reported.
A huge improvement in efficiency
Traditional approaches to disease surveillance rely heavily on “passive reporting,” which involves collecting reports of infections from physicians and health care providers.
Now that following informal sources such as online media for disease surveillance has become more popular, the volume of articles published each day has also increased, making manual screening impractical, said the study’s authors, including those from the National Centers for Disease Control (NCDC).
Read also | ByHeart Recall Amid Infant Botulism Outbreak – What Should Consumers Do?
The “Health Sentinel” tool solves this problem by using artificial intelligence to extract information about unusual health events or epidemics from news articles.
The implementation of the AI tool results in a significant increase in detected events. The research team observed a 150% increase in published health events from 2022 compared to previous years of tracking human-caused diseases.
Further, in 2024, the AI tool extracted 96% of health events published by the national surveillance system, with only 4% identified by manual media scanning, the report said.
Event tracking cases
The study, published in February in the Indian Journal of Medical Research: Official Journal of the Indian Council of Medical Research, demonstrated the value of an event-based surveillance system by looking at media and rumor registers at six private hospitals in Kerala’s Kasaragod district.
Researchers from the ICMR-National Institute of Epidemiology in Chennai and Kerala state and district health officials developed an algorithm that analyzed case records of patients with acute febrile illness (AFI) – a fever that can last up to two weeks.
Read also | Artificial intelligence has huge potential to transform healthcare delivery, says the CII Healthcare Council
The system identified 88 clusters of systems of interest, of which 10 were verified as events and nine were classified as outbreaks, including dengue and Covid-19, the study said.
“The inclusion of online data in surveillance systems has improved disease prediction ability over traditional syndromic surveillance systems,” said the authors from the Technological University of Delhi, as quoted by PTI.
