Weather integrated multiple machine learning models for prediction of dengue prevalence in India.

Dengue is a rapidly spreading viral disease transmitted to humans by Aedes mosquitoes. Due to global urbanization and climate change, the number of dengue cases are gradually increasing in recent decades. Hence, an early prediction of dengue continues to be a major concern for public health in countries with high prevalence of dengue. Creating a robust forecast model for the accurate prediction of dengue is a complex task and can be done through various data modelling approaches. In the present study, we have applied vector auto regression, generalized boosted models, support vector regression, and long short-term memory (LSTM) to predict the dengue prevalence in Kerala state of the Indian subcontinent. We consider the number of dengue cases as the target variable and weather variables viz., relative humidity, soil moisture, mean temperature, precipitation, and NINO3.4 as independent variables. Various analytical models have been applied on both datasets and predicted the dengue cases. Among all the models, the LSTM model was outperformed with superior prediction capability (RMSE: 0.345 and R2:0.86) than the other models. However, other models are able to capture the trend of dengue cases but failed in predicting the outbreak periods when compared to LSTM. The findings of this study will be helpful for public health agencies and policymakers to draw appropriate control measures before the onset of dengue. The proposed LSTM model for dengue prediction can be followed by other states of India as well.

Climate based malaria forecasting system for Andhra Pradesh, India.

Malaria is a major public health problem in tropical and subtropical countries of the World. During the year 1999, Visakhapatnam district of Andhra Pradesh, India experienced a major epidemic of malaria, and nearly 41,805 cases were reported. Hence, a retrospective malaria surveillance study was conducted from 2001 to 2016 and reported nearly a total of 149,317 malaria cases during the study period. Of which, Plasmodium vivax contributes 32%, and Plasmodium falciparum contributes 68% of the total cases. Malaria cases follow a strong seasonal variation and 70% of cases are reported during the monsoon periods. In the present study, we exploited multi step polynomial regression and seasonal autoregressive integrated moving average (SARIMA) models to forecast the malaria cases in the study area. The polynomial model predicted malaria cases with high predictive power and found that malaria cases at lag one, and population played a vital role in malaria transmission. Similarly, mean temperature, rainfall and Normalized Difference Vegetation Index build a significant impact on malaria cases. The best fit model was SARIMA (1, 1, 2) (2, 1, 1)12 which was used for forecasting monthly malaria incidence for the period of January 2015 to December 2016. The performance accuracy of both models are similar, however lowest Akaike information criterion score was observed by the polynomial model, and this approach can be helpful further for forecasting malaria incidence to implement effective control measures in advance for combating malaria in India.

Dengue situation in India: Suitability and transmission potential model for present and projected climate change scenarios.

Dengue fever is mosquito borne viral disease caused by dengue virus and transmitted by Aedes mosquitoes. In recent years the dengue has spread rapidly to several regions and it becomes a major public health menace globally. Dengue transmission is strongly influenced by environmental factors such as temperature and rainfall. In the present study, a climate driven dengue model was developed and predicted areas vulnerable for dengue transmission under the present and future climate change scenarios in India. The study also projected the dengue distribution risk map using representative concentration pathways (RCP4.5 and RCP8.5) in India in 2018-2030 (forthcoming period), 2031-2050 (intermediate period) and 2051-2080 (long period). The dengue cases assessed in India from 1998 to 2018 and found that the dengue transmission is gradually increasing year over year. The temperature data from 1980 to 2017 shows that, the mean temperatures are raising in the Southern region of India. During 2000-2017 periods the dengue transmission is steadily increasing across the India in compare with 1980-1999 periods. The dengue distribution risk is predicted and it is revealed that the coastal states have yearlong transmission possibility, but the high transmission potential is observed throughout the monsoon period. Due to the climate change, the expansion two more months of dengue transmission risk occurs in many regions of India. Both RCP4.5 and RCP8.5 scenarios revealed that dengue outbreaks might occur at larger volume in Southern, Eastern, and Central regions of India. Furthermore a sensitivity analysis was performed to explore the impact of climate change on dengue transmission. These results helps to suggest appropriate control measures should be implemented to limit the spread in future warmer climates. Besides these, a proper plan is required to mitigate greenhouse gas emissions to reduce the epidemic potential of dengue in India.

Lag effect of climatic variables on dengue burden in India.

Dengue is a widespread vector-borne disease believed to affect between 100 and 390 million people every year. The interaction between vector, host and pathogen is influenced by various climatic factors and the relationship between dengue and climatic conditions has been poorly explored in India. This study explores the relationship between El Niño Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD) and dengue cases in India. Additionally, distributed lag non-linear model was used to assess the delayed effects of climatic factors on dengue cases. The weekly dengue cases reported by the Integrated Disease Surveillance Program (IDSP) over India during the period 2010-2017 were analysed. The study shows that dengue cases usually follow a seasonal pattern, with most cases reported in August and September. Both temperature and rainfall were positively associated with the number of dengue cases. The precipitation shows the higher transmission risk of dengue was observed between 8 and 15 weeks of lag. The highest relative risk (RR) of dengue was observed at 60 mm rainfall with a 12-week lag period when compared with 40 and 80 mm rainfall. The RR of dengue tends to increase with increasing mean temperature above 24 °C. The largest transmission risk of dengue was observed at 30 °C with a 0-3 weeks of lag. Similarly, the transmission risk increases more than twofold when the minimum temperature reaches 26 °C with a 2-week lag period. The dengue cases and El Niño were positively correlated with a 3-6 months lag period. The significant correlation observed between the IOD and dengue cases was shown for a 0-2 months lag period.

Temperature dependent transmission potential model for chikungunya in India.

Chikungunya is a major public health problem in tropical and subtropical countries of the world. During 2016, the National Capital Territory of Delhi experienced an epidemic caused by chikungunya virus with >12,000 cases. Similarly, other parts of India also reported a large number of chikungunya cases, highest incidence rate was observed during 2016 in comparison with last 10 years of epidemiological data. In the present study we exploited R0 mathematical model to understand the transmission risk of chikungunya virus which is transmitted by Aedes vectors. This mechanistic transmission model is climate driven and it predicts how the probability and transmission risk of chikungunya occurs in India. The gridded temperature data from 1948 to 2016 shows that the mean temperatures are gradually increasing in South India from 1982 to 2016 when compared with data of 1948-1981 time scale. During 1982-2016 period many states have reported gradual increase in risk of chikungunya transmission when compared with the 1948-1981 period. The highest transmission risk of chikungunya in India due to favourable ecoclimatic conditions, increasing temperature leads to low extrinsic incubation period, mortality rates and high biting rate were predicted for the year 2016. The epidemics in 2010 and 2016 are also strongly connected to El Nino conditions which favours transmission of chikungunya in India. The study shows that transmission of chikungunya occurs between 20 and 34 °C but the peak transmission occurs at 29 °C. The infections of chikungunya in India are due to availability of vectors and optimum temperature conditions influence chikungunya transmission faster in India. This climate based empirical model helps the public health authorities to assess the risk of chikungunya and one can implement necessary control measures before onset of disease outbreak.