PreprintArticleVersion 2Preserved in Portico This version is not peer-reviewed
Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors
Version 1
: Received: 12 February 2024 / Approved: 21 February 2024 / Online: 21 February 2024 (10:19:00 CET)
Version 2
: Received: 19 March 2024 / Approved: 19 March 2024 / Online: 20 March 2024 (13:13:29 CET)
How to cite:
El-Sunais, Y.; Eberemu, N.C. Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors. Preprints2024, 2024021217. https://doi.org/10.20944/preprints202402.1217.v2
El-Sunais, Y.; Eberemu, N.C. Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors. Preprints 2024, 2024021217. https://doi.org/10.20944/preprints202402.1217.v2
El-Sunais, Y.; Eberemu, N.C. Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors. Preprints2024, 2024021217. https://doi.org/10.20944/preprints202402.1217.v2
APA Style
El-Sunais, Y., & Eberemu, N.C. (2024). Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors. Preprints. https://doi.org/10.20944/preprints202402.1217.v2
Chicago/Turabian Style
El-Sunais, Y. and Nkiru Charity Eberemu. 2024 "Revolutionizing Parasitic Infection Diagnosis in Northern Nigeria: An Integrated Machine Learning Approach for the Identification of Intestinal Parasites and Associated Risk Factors" Preprints. https://doi.org/10.20944/preprints202402.1217.v2
Abstract
Intestinal parasitic infections pose a significant public health challenge in Northern Nigeria, with prevalence rates ranging from 20% to 70%. Traditional diagnostic methods, primarily microscopic examination of stool samples, face limitations such as low sensitivity and high costs. This research addresses these challenges by proposing an Artificial Intelligence (AI)-based platform for the identification and counting of intestinal parasites. A total of 651 samples were collected from the 7 Northern State of Nigeria along with questionnaire collecting data on demographic, socio-economic, hygiene habits and environmental factors. Leveraging the You Only Look Once (YOLO) V8 model, trained on a dataset of 360 pre-processed and 467 annotated images, the AI model demonstrated promising performance metrics. Information-Theory-Based approaches including (CIFE, CMIM, DISR and ICAP) were used on various machine learning models (Naïve Bayes, Random Forest, Support Vector Machine and Decision Tree) to analyse the risk factors associated with the parasitic disease. The precision-recall curve, average precision, mean average precision, and F1 score indicated reliable detection and classification across various parasite classes. The accuracy (97%) and AUC (99%) scores shows that CIFE with Random Forest has the best performance indicating the significant risk factors associated with the parasitic diseases. The model exhibited a well-balanced trade-off between precision and recall, showcasing its potential as a cost-effective and accessible tool for improving the diagnosis and treatment of intestinal parasitic infections in resource-limited settings.
Keywords
Intestinal parasitic infections, Artificial Intelligence (AI), Machine Learning, You Only Look Once (YOLO) V8, CIFE, CMIM, DIRS, ICAP
Subject
Biology and Life Sciences, Other
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
