Deep Learning Approach to Forecasting Dengue Cases in Davao City Using Long Short-term Memory (LSTM)

Abstract

Dengue is a mosquito-transmitted viral disease that causes mild to severe infection. In the tropics, the risk of high infection is driven by factors that influence its vector’s population density such as meteorological variables and unplanned rapid urbanization. In the Philippines, dengue remains endemic in all regions reporting hundreds of thousands of cases annually. The continuous development of data-based infectious disease prediction models plays a vital role in overcoming this persistent adversity. This study explored the application of artificial intelligence (AI) through a deep learning approach using the long short-term memory (LSTM) architecture in our prediction model. This is compared with the traditional feed-forward network approach using a multilayer perceptron (MLP) model and a statistical approach using non-seasonal and seasonal autoregressive integrated moving average (ARIMA). The forecasting models predicted the monthly number of reported dengue cases in Davao City using temperature, rainfall, relative humidity, and previous monthly cases. Model performance was evaluated using the root mean square error (RMSE). The LSTM model recorded the highest accuracy among the models, reporting two times lower RMSE than the MLP model and four times lower RMSE than the statistical models. This result demonstrated the feasibility of deep learning techniques to capture nonlinear characteristics of data and the ability of the LSTM to effectively incorporate information from longer past periods in its prediction.

Bridging the Gap or Widening the Divide: A Call for Capacity-Building in Artificial Intelligence for Healthcare in the Philippines

“…Among other projects is the CANDLE Study by the National Health Institute, which includes phenotypically scoring CT scans for early liver cancer detection [34]; the CHERISH2 App of the Department of Health in partnership with a tertiary hospital for screening COVID-Pneumonia [35]; and a Dengue prediction model using Long Short-term Memory (LSTM) made by researchers from the University of the Philippines [36].…”