LSTM-based Forecasting of Dengue Cases in Gujarat: A Machine Learning Approach

Abstract

Objectives: Dengue fever, a mosquito-borne viral disease, is particularly prevalent in tropical regions like India. Gujarat State is also one of them. Forecasting outbreaks of diseases such as dengue can prove important for public health management. The purpose of this study is to predict dengue cases in ten districts of Gujarat using the LSTM machine learning model. And if people are aware of this from the beginning, the spread of dengue can be prevented. Methods: This approach uses LSTM models to predict dengue cases using a total of 10 years (2010 to 2019) of data. From this data, data from 2010 to 2016 is used for training and data from 2017 to 2019 is used for testing. To predict dengue cases, population density, average temperature, average humidity, monthly rainfall, dengue cases with lag of one, two and twelve months. Findings: The LSTM model was applied with different parameter configurations, showing the following results: The root mean square error value is 0.04, and the R-squared (R2) score is 0.84. Many machine learning methods, like ANN, linear regression, random forest, etc., have been used to predict dengue cases in different states and countries. LSTM model gives the best results in terms of accuracy. Previously reported dengue cases, population density, and total monthly rainfall proved to be the most effective predictors of dengue in the state of Gujarat. Novelty: Models have been developed to predict dengue outbreaks in many other countries and states. The LSTM model is developed for the first time in this study for the state of Gujarat. 84% accuracy is obtained from the model. This model has been prepared by collecting environmental data and registered dengue cases in Gujarat state. Keywords: Dengue Cases Predictions, Artificial Intelligence in Healthcare, LSTM Algorithm, Disease Outbreaks, Public Health Management