A Hybrid Approach Based on Seasonal Autoregressive Integrated Moving Average and Neural Network Autoregressive Models to Predict Scorpion Sting Incidence in El Oued Province, Algeria, From 2005 to 2020
Journal of Research in Health Sciences · 2023
DOI: 10.34172/jrhs.2023.121 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Research in Health Sciences, 2023. Verfasst von Safia Zenia und 2 weiteren Autor:innen. Beteiligte Einrichtung: L'IFORCE, SPA, Higher National Veterinary School of Algiers, Algeria. Hauptthemen laut MEDLINE: Models, Statistical, Scorpion Stings. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
This study was designed to find the best statistical approach to scorpion sting predictions. Study Design: A retrospective study.
Methods
Multiple regression, seasonal autoregressive integrated moving average (SARIMA), neural network autoregressive (NNAR), and hybrid SARIMA-NNAR models were developed to predict monthly scorpion sting cases in El Oued province. The root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were used to quantitatively compare different models.
Results
In general, 96909 scorpion stings were recorded in El Oued province from 2005-2020. The incidence rate experienced a gradual decrease until 2012 and since then slight fluctuations have been noted. Scorpion stings occurred throughout the year with peaks in September followed by July and August and troughs in December and January. Sting cases were not evenly distributed across demographic groups; the most affected age group was 15-49 years, and males were more likely to be stung. Of the reported deaths, more than half were in children 15 and younger. Scorpion’s activity was conditioned by climate factors, and temperature had the highest effect. The SARIMA(2,0,2)(1,1,1)12, NNAR(1,1,2)12, and SARIMA(2,0,2)(1,1,1)12-NNAR(1,1,2)12 were selected as the best-fitting models. The RMSE, MAE, and MAPE of the SARIMA and SARIMA-NNAR models were lower than those of the NNAR model in fitting and forecasting; however, the NNAR model could produce better predictive accuracy.
Conclusion
The NNAR model is preferred for short-term monthly scorpion sting predictions. An in-depth understanding of the epidemiologic triad of scorpionism and the development of predictive models ought to establish enlightened, informed, better-targeted, and more effective policies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- L'IFORCE, SPA, Higher National Veterinary School of Algiers, Algeria.
- Scorp2, BeniMessous University Hospital Centre, Ministry of Health, Algeria.
- L'IFORCE, Scorp2, Faculty of Mathematics, University of Sciences and Technology Houari Boumediene, Algeria.
ORCID-Profile: Safia Zenia, Schehrazad Selmane
Zitieren
APA
Zenia, S., L'Hadj, M., & Selmane, S. (2023). A Hybrid Approach Based on Seasonal Autoregressive Integrated Moving Average and Neural Network Autoregressive Models to Predict Scorpion Sting Incidence in El Oued Province, Algeria, From 2005 to 2020. Journal of Research in Health Sciences. https://doi.org/10.34172/jrhs.2023.121
Vancouver
Zenia S, L'Hadj M, Selmane S. A Hybrid Approach Based on Seasonal Autoregressive Integrated Moving Average and Neural Network Autoregressive Models to Predict Scorpion Sting Incidence in El Oued Province, Algeria, From 2005 to 2020. Journal of Research in Health Sciences. 2023. doi:10.34172/jrhs.2023.121
BibTeX
@article{Zenia2023,
author = {Zenia, Safia and L'Hadj, Mohamed and Selmane, Schehrazad},
title = {A Hybrid Approach Based on Seasonal Autoregressive Integrated Moving Average and Neural Network Autoregressive Models to Predict Scorpion Sting Incidence in El Oued Province, Algeria, From 2005 to 2020},
journal = {Journal of Research in Health Sciences},
year = {2023},
doi = {10.34172/jrhs.2023.121}
}
EUVIMED