Exploratory Data Analysis and Artificial Neural Network for Prediction of Leptospirosis Occurrence in Seremban, Malaysia Based on Meteorological Data

Abstract

Leptospirosis outbreaks in various parts of the world have been linked to changes in the weather. Furthermore, the effects have been shown to occur at different lags of up to 10 months, affecting the performance of simulation models that predict leptospirosis occurrence. In Malaysia, the link between different weather parameters, at different time lags, has yet to be established despite an increasing number of cases in recent years. In this study, a combination of data mining and machine learning is used to analyze, capture, and predict the relation between leptospirosis occurrence and temperature, rainfall, and relative humidity using the Seremban district in Malaysia as a case study. First, the optimal time lags for rainfall were determined using graphical exploratory data analysis (EDA) while non-graphical EDA was used for temperature. Then, an artificial neural network (ANN) model is developed to classify the combination of selected features into disease occurrence and non-occurrence using back-propagation training, optimizing the number of hidden layers and hidden nodes. The success is measured using accuracy, sensitivity, and specificity of each model. EDA has shown that leptospirosis occurrence in Seremban is highly correlated with weekly average temperature at lag 16 weeks and weekly rainfall amount at lag 12-20 weeks. Using these selected features, the ANN model achieved the highest accuracy, sensitivity, and specificity at 84.00, 86.44, and 79.33%, respectively. Overall, the EDA approach has increased the accuracy of the predictive model by 13.30-31.26% from the baseline models.

Implementation of Exploratory Data Analysis and Artificial Neural Networks to Predict Student Graduation on-Time

“…What are the limitations that have an impact on the accuracy results, which only produce a figure of 69.84%, not above 90%? Previous research has proven that the exploratory data analysis method has succeeded in increasing the accuracy of the predictive model compared to the basic model (Rahmat et al, 2020). However, in this study, it has not been possible to prove the effect of exploratory data analysis on the level of prediction accuracy.…”

Spatio-Temporal Analysis of Leptospirosis Hotspot Areas and Its Association With Hydroclimatic Factors in Selangor, Malaysia: Protocol for an Ecological Cross-sectional Study

“…Studies in South America and East Asia ascertained the association of these factors to the disease, where heavy rainfall and flood events during the El Nino phenomenon and rainfall events that cause an increase in soil moisture impact regional leptospirosis [ 16 , 33 ]. A local study using weather data and artificial neuron network modeling to link leptospirosis occurrence in Seremban discovered their significant correlation with temperature and rainfall at a lag between 12 and 20 weeks [ 29 ].…”

“…Data on leptospirosis cases from 2011 to 2019 will be obtained from the Zoonosis Unit, Selangor State Health Department. A period of 9 years was taken to compare the results from other similar studies in Argentina and Malaysia [ 16 , 29 ]. The data obtained will be analyzed for the sociodemographic information of the cases and locations of possible sources of infection with their longitude and latitude coordinates.…”

Leptospirosis Relative Risk Estimates based on Continuous-Time, Discrete-Space Stochastic SIR-L-SI Transmission Model

“…Leptospires is also able to survive in organs and tissues of live or dead animals [45,1]. According to Rahmat et al [38], under favourable environmental factors, leptospires are able to survive longer and remain harmful up to 20 months at 30 degree Celsius, 10 months at higher temperature and at least 20 months in acidic environment. However, leptospires will be killed as the temperature increases 10.11113/mjfas.v20n1.3182 more than 50 degree with very low humidity.…”