Visceral leishmaniasis, a severe health disorder, is attributed to the microscopic parasite Leishmania. The parasitic illness possesses the capacity to pose a significant risk to human life and exhibits a variable prevalence across people worldwide. Using time series prediction techniques for VL might offer valuable insights to aid public health professionals in strategizing and implementing effective measures for VL prevention. This study presents a comparative analysis of time series forecasting techniques, specifically focusing on two methods: SARIMA and LSTM recurrent neural networks. Forecast performance evaluation involves utilizing monthly VL data acquired from district health offices from January 2000 to December 2021. An assessment of the model’s performance is conducted to ascertain its efficacy. According to the evaluation conducted using three metrics, namely mean average precision (MAP), root mean square (RMS), and mean absolute error (MA), the findings indicate that the LSTM model outperforms the SARIMA model in terms of forecasting monthly conditions. The discovery implies that the LSTM approach may be better suited for predicting VL incidents and has the potential to contribute to the formulation of efficient preventive measures. Furthermore, it is suggested that future studies should investigate the possibility of integrating SARIMA and LSTM techniques to improve VL forecasts’ precision.
Digital Object Identifier (DOI)
EL Guma, Fathelrhman
"Comparative analysis of time series prediction models for visceral leishmaniasis:based on SARIMA and LSTM,"
Applied Mathematics & Information Sciences: Vol. 18:
1, Article 12.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol18/iss1/12