Machine Learning Based Detection of Chronic Kidney Disease using Full Blood Count from a Ghanaian Hospital Population with an Integrated Web Application
- 1Ho Technical University
Abstract
Chronic kidney disease (CKD) is usually silent until advanced, and the tests confirming it are frequently unaffordable in sub-Saharan Africa, whereas the full blood count (FBC) is inexpensive and widely performed. We assessed whether machine learning applied to the FBC can detect CKD, and how far its reported performance depends on where synthetic minority oversampling (SMOTE) is applied. Records of 155 patients at the Ho Technical University Hospital, Ghana, 43 (27.7%) with CKD, yielded ten features: age, cardiovascular disease and eight raw FBC parameters. Eleven algorithms, six resampling strategies and thirteen ensembles were compared under repeated stratified cross-validation. With SMOTE applied before the train-test split, the protocol under which the deployed models were fitted, Random Forest and Extra Trees both reached an accuracy of 83.9%, with sensitivities of 0.893 and 0.857 and areas under the curve (AUC) of 0.925 and 0.939; repeated cross-validation gave an accuracy of 0.809 {+/-} 0.051 and an AUC of 0.897. With resampling confined to the training folds, the same features gave a held-out accuracy of 61.5% and an AUC of 0.604 in 39 unseen patients. Age was the only variable separating the groups after correction for multiple testing (median 64 versus 47 years, adjusted p = 0.0026). The models are deployed as NephroScan GH (https://nephroscangh.com), which explains every prediction. The FBC carries a real but moderate signal for CKD, and the 22.4 point gap between the two protocols quantifies how far a single preprocessing decision can move a reported accuracy.
Related
- Exploring the Application of Machine Learning for Daily‐Life Near‐Fall Detection in Older Adults
- Food insecurity and its related indicators in an Iranian population: An application of machine learning methods in data from Golestan Province
- Application of a Quantitative POCT-FIT Based on Near-Infrared Fluorescence Immunochromatography in Population-Based Colorectal Cancer Screening: A Comparative Evaluation with a Centralized Testing System
- An Arduino-Based Butane Leak Detection System With Automated Ventilation and Internet of Things (IoT) Mobile Application
- Perinatal maternal infections among mothers attending an urban Ghanaian hospital: clinical characteristics and predictors of infections
BibTeX
@misc{akwetey2026machine,
title = {{Machine Learning Based Detection of Chronic Kidney Disease using Full Blood Count from a Ghanaian Hospital Population with an Integrated Web Application}},
author = {B. Y. Akwetey and E. Y. Lawluvi and T. T. Equagoo and S. Kumako and E. A. Tsinyo and R. T. Kumi and I. R. Mensah and F. S. Amedume and E. Avuetor and C. E. Adikah and W. Mensah and J. N.-D. Botuo},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.27.26366677},
url = {https://www.medrxiv.org/content/10.64898/2026.10.27.26366677v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Machine Learning Based Detection of Chronic Kidney Disease using Full Blood Count from a Ghanaian Hospital Population with an Integrated Web Application
AU - B. Y. Akwetey
AU - E. Y. Lawluvi
AU - T. T. Equagoo
AU - S. Kumako
AU - E. A. Tsinyo
AU - R. T. Kumi
AU - I. R. Mensah
AU - F. S. Amedume
AU - E. Avuetor
AU - C. E. Adikah
AU - W. Mensah
AU - J. N.-D. Botuo
PY - 2026
DA - 2026/10/27
PB - medRxiv
DO - 10.64898/2026.10.27.26366677
UR - https://www.medrxiv.org/content/10.64898/2026.10.27.26366677v1
AB - Chronic kidney disease (CKD) is usually silent until advanced, and the tests confirming it are frequently unaffordable in sub-Saharan Africa, whereas the full blood count (FBC) is inexpensive and widely performed. We assessed whether machine learning applied to the FBC can detect CKD, and how far its reported performance depends on where synthetic minority oversampling (SMOTE) is applied. Records of 155 patients at the Ho Technical University Hospital, Ghana, 43 (27.7%) with CKD, yielded ten features: age, cardiovascular disease and eight raw FBC parameters. Eleven algorithms, six resampling strategies and thirteen ensembles were compared under repeated stratified cross-validation. With SMOTE applied before the train-test split, the protocol under which the deployed models were fitted, Random Forest and Extra Trees both reached an accuracy of 83.9%, with sensitivities of 0.893 and 0.857 and areas under the curve (AUC) of 0.925 and 0.939; repeated cross-validation gave an accuracy of 0.809 {+/-} 0.051 and an AUC of 0.897. With resampling confined to the training folds, the same features gave a held-out accuracy of 61.5% and an AUC of 0.604 in 39 unseen patients. Age was the only variable separating the groups after correction for multiple testing (median 64 versus 47 years, adjusted p = 0.0026). The models are deployed as NephroScan GH (https://nephroscangh.com), which explains every prediction. The FBC carries a real but moderate signal for CKD, and the 22.4 point gap between the two protocols quantifies how far a single preprocessing decision can move a reported accuracy.
ER -