EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cholera_Microscope: An intelligent mapping and predictive analysis of cholera disease in Ogun State

Adesina Simon Sodiya, Olorunjube James Falana, Abdullahi Ahmed, Dada Olaniyi Aborisade, Gloria Bosede Imhonopi, Oludele Awodele, Saheed Olalekan Akinbowale

Oxford Open Digital Health · 02.11.2026

DOI: 10.1093/oodh/oqag029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Oxford Open Digital Health, online erschienen am 02.11.2026. Verfasst von Adesina Simon Sodiya und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cholera remains a primary epidemic-prone disease in Nigeria, with Ogun State identified as a high-burden region. National surveillance data from the Nigeria Centre for Disease Control and Prevention (NCDC) reported 10 353 suspected cases and 244 associated fatalities between January 1 and September 14, 2025, representing a significant public health challenge. Some of the factors that mitigate against effective control of cholera in Nigeria are poor hygiene, lack of basic infrastructure, inadequate surveillance structure and ineffective preparedness plan. This research work presents Cholera Microscope, an intelligent geospatial surveillance system for visualising and predicting cholera outbreaks. Variogram, a geospatial mapping technique, was used to generate insights into cholera outbreak dynamics. A hybridised model, which combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), was developed for effective prediction of cholera outbreaks. The hybrid model was based on the strength of CNN in efficient extraction of salient features and the capability of LSTM in capturing long-term sequential dependencies for training and prediction. The implementation was done on a Flutter-based platform integrated with geocoding and polygon mapping. The pre-processed data were also visualised using heat circle mapping, spatial pictograms, colour gradient and variogram analysis to dynamically identify outbreak hotspots and spatial dependencies. Experimental results show that the hybrid CNN-LSTM model outperformed individual CNN, LSTM, and traditional machine-learning classifiers. The model obtained 94.7% accuracy in hotspot detection and outbreak trend prediction, demonstrating its high reliability. These findings show that the cholera microscope is a very reliable hotspot detection and outbreak trend prediction.

Zitieren

APA

Sodiya, A. S., Falana, O. J., Ahmed, A., Aborisade, D. O., Imhonopi, G. B., Awodele, O., & Akinbowale, S. O. (2026). Cholera_Microscope: An intelligent mapping and predictive analysis of cholera disease in Ogun State. Oxford Open Digital Health. https://doi.org/10.1093/oodh/oqag029

Vancouver

Sodiya AS, Falana OJ, Ahmed A, Aborisade DO, Imhonopi GB, Awodele O, et al. Cholera_Microscope: An intelligent mapping and predictive analysis of cholera disease in Ogun State. Oxford Open Digital Health. 2026. doi:10.1093/oodh/oqag029

BibTeX
@article{Sodiya2026,
  author = {Sodiya, Adesina Simon and Falana, Olorunjube James and Ahmed, Abdullahi and Aborisade, Dada Olaniyi and Imhonopi, Gloria Bosede and Awodele, Oludele and Akinbowale, Saheed Olalekan},
  title = {Cholera_Microscope: An intelligent mapping and predictive analysis of cholera disease in Ogun State},
  journal = {Oxford Open Digital Health},
  year = {2026},
  doi = {10.1093/oodh/oqag029}
}
Kostenlos starten →