Long-term predictors of dengue outbreaks in Bangladesh: A data mining approach

Abstract

The effects of weather variables on the transmission of vector-borne diseases are complex. Relationships can be non-linear, specific to particular geographic locations, and involve long lag times between predictors and outbreaks of disease. This study expands the geographical and temporal range of previous studies in Bangladesh of the mosquito-transmitted viral infection dengue, a major threat to human public health in tropical and subtropical regions worldwide. The analysis incorporates new compound variables such as anomalous events, running averages, consecutive days of particular weather characteristics, seasonal variables based on the traditional Bangla six-season annual calendar, and lag times of up to one year in predicting either the existence or the magnitude of each dengue epidemic. The study takes a novel, comprehensive data mining approach to show that different variables optimally predict the occurrence and extent of an outbreak. The best predictors of an outbreak are the number of rainy days in the preceding two months and the average daily minimum temperature one month prior to the outbreak, while the best predictor of the number of clinical cases is the average humidity six months prior to the month of outbreak. The magnitude of relationships between humidity 6, 7 and 8 months prior to the outbreak suggests the relationship is multifactorial, not due solely to the cyclical nature of prevailing weather conditions but likely due also to the immunocompetence of human hosts.

The ‘lifecycle’ of human beings: a call to explore vector-borne diseases from an ecosystem perspective

“…Further research is required to determine if the mediating factor between relative humidity 6 months before a dengue outbreak and its scale of incidence is valid or spurious, but clearly a simple vector-focused explanation is inadequate. Muurlink et al [9] demonstrate that this effect is not merely caused by climate predicting climate. We acknowledge that data mining analyses inherently generate a risk of the emergence of 'false negative' relationships, masked behind statistical significance.…”

“…Ourselves and colleagues recently conducted a nearexhaustive data mining analysis of relationships between climatic variables and dengue in Bangladesh [9]. The best predictors of an outbreak of dengue are not surprisingly assumed to be environmental conditions that benefit Aedes vector species, which have a short lifecycle of up to 3 weeks.…”

“…Conditions that cause the vector to thrive should in turn be associated with the threat of VBDs. We focused on the two hotspots of dengue infection within Bangladesh, Chittagong and Dhaka [9]. By holding constant the number of rainy days in the month prior to an outbreak for each degree Celsius increase in temperature, the risk of an outbreak (defined as at least one confirmed case of dengue at a local clinic) increased by 23%.…”

COVID-19 Pandemic Prediction for Hungary; a Hybrid Machine Learning Approach

“…Application of ML in outbreak prediction includes several algorithms, e.g., random forest for swine fever [39] [40], neural network for H1N1 flu, dengue fever, and Oyster norovirus [41] [11] [42], genetic programming for Oyster norovirus [43], classification and regression tree (CART) for Dengue [44], Bayesian Network for Dengue and Aedes [45], LogitBoost for Dengue [46], multi-regression and Naïve Bayes for Dengue outbreak prediction [47]. Although ML methods were used in modeling former pandemics (e.g., Ebola, Cholera, swine fever, H1N1 influenza, dengue fever, Zika, oyster norovirus [11,[39][40][41][42][43][44][45][46][47][48]), there is a gap in the literature for peer-reviewed papers dedicated to COVID-19. Nevertheless, machine learning has been strongly proposed as a great potential for the fight against COVID-19 [49,50].…”

COVID-19 Outbreak Prediction with Machine Learning

“…Although ML methods were used in modeling former pandemics (e.g., Ebola, Cholera, swine fever, H1N1 influenza, dengue fever, Zika, oyster norovirus [8,[34][35][36][37][38][39][40][41][42][43]), there is a gap in the literature for peer-reviewed papers dedicated to COVID-19. Table 1 represents notable ML methods used for outbreak prediction.…”