Scientists at the Institute of Advanced Virology (IAV) in Keralam are developing a dengue forecasting system that integrates epidemiological and weather data on a machine-learning platform to predict dengue incidence trends in advance.
Thiruvananthapuram, for instance, has long been regarded as Keralam’s dengue hotspot, although public health experts have argued that its high reported burden also reflects stronger surveillance and testing. Variations in the reporting of confirmed dengue cases by the Health department could similarly influence observed disease patterns and the reliability of predictions, Dr. The aim is to help public health managers plan resource allocation and preventive measures proactively, rather than responding only after outbreaks occur. This has prompted considerable interest in developing forecasting models that combine meteorological and epidemiological data to enable disease surveillance to stay ahead of outbreaks. The model incorporates daily epidemiological and climatic parameters, including temperature, rainfall and humidity, allowing a more granular representation of disease dynamics. Each district is treated as an independent unit, taking into account district-specific geographical and environmental characteristics, including waterbodies and drainage systems. This enables the model to be trained and optimised for individual districts. Under-reporting is another major challenge. A large proportion of dengue infections are asymptomatic or mild and may be mistaken for other viral fevers. Differences in testing and reporting practices can also create geographical biases. The IAV acknowledges these limitations. Since DEWS is trained on historical data, sudden or substantial changes in climatic parameters could affect its accuracy.
Keralam, which remains warm and wet for much of the year, therefore has climatic conditions favourable to Aedes proliferation and dengue transmission.
Abhinand says.
For easier interpretation by public health managers, predicted disease burden is classified into four risk levels—very high, high, moderate and low, based on predefined prediction ranges. This provides a district-wise indication of the expected risk. “For the model to evolve from a research model to a routinely functioning public health forecasting system, DEWS will have to undergo yearly updation and further refinement, and perhaps be trained with more variables. Sreekumar. The platform could eventually be extended to other Aedes-borne diseases such as chikungunya and Zika, potentially strengthening Keralam’s disease surveillance capacity and enabling more timely, data-driven public health interventions.
DEWS is the first disease forecasting model of its kind to be developed for use by the State,” says IAV Director E.
