Kyasanur Forest Disease, is our surveillance system healthy to prevent a larger outbreak? A mixed-method study, Shivamogga, Karnataka, India: 2019

Sociodemographic factors associated with Kyasanur forest disease in India - a retrospective study

Objectives

Kyasanur forest disease (KFD) is a tick-borne disease in India affecting humans and two local non-human primate species. A critical knowledge gap in the scientific literature is the lack of information on how people's sociodemographic factors influence KFD occurrence.

Methods

We analyzed available data on KFD from three data sources: (a) 104 peer-reviewed articles using keyword searches on PubMed Central and Google Scholar, (b) 116 Program for Monitoring Emerging Diseases reports, and (c) an acute febrile illness surveillance data set on KFD from a report by the government of India. We performed statistical analyses to calculate the prevalence of KFD by state and differences in KFD cases by sex and age group.

Results

All three data sets used indicate that KFD cases and deaths have occurred predominantly in the 15-64 years age group (literature: 87% cases and 95% deaths, Program for Monitoring Emerging Diseases: 78% cases and 78% deaths, acute febrile illness: 96% cases [no breakdown for acute febrile illness death data]). Data reporting varies across states and is non-standardized.

Conclusions

The inconsistent reporting of sociodemographic data on KFD in India has created a gap in our understanding of its impact on different social groups. Collecting and reporting data on sociodemographic factors is critical to understanding the epidemiology of KFD and designing effective public health interventions.

Predicting Kyasanur forest disease in resource-limited settings using event-based surveillance and transfer learning

In recent years, the reports of Kyasanur forest disease (KFD) breaking endemic barriers by spreading to new regions and crossing state boundaries is alarming. Effective disease surveillance and reporting systems are lacking for this emerging zoonosis, hence hindering control and prevention efforts. We compared time-series models using weather data with and without Event-Based Surveillance (EBS) information, i.e., news media reports and internet search trends, to predict monthly KFD cases in humans. We fitted Extreme Gradient Boosting (XGB) and Long Short Term Memory models at the national and regional levels. We utilized the rich epidemiological data from endemic regions by applying Transfer Learning (TL) techniques to predict KFD cases in new outbreak regions where disease surveillance information was scarce. Overall, the inclusion of EBS data, in addition to the weather data, substantially increased the prediction performance across all models. The XGB method produced the best predictions at the national and regional levels. The TL techniques outperformed baseline models in predicting KFD in new outbreak regions. Novel sources of data and advanced machine-learning approaches, e.g., EBS and TL, show great potential towards increasing disease prediction capabilities in data-scarce scenarios and/or resource-limited settings, for better-informed decisions in the face of emerging zoonotic threats.