Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements

Abstract Chronic kidney disease (CKD) is a global health concern with early detection playing a pivotal role in effective management. Machine learning models demonstrate promise in CKD detection, yet the impact on detection and classification using different sets of clinical features remains under-e...

Full description

Saved in:
Bibliographic Details
Main Authors: Brady Metherall, Anna K. Berryman, Georgia S. Brennan
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-88631-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1823862167741399040
author Brady Metherall
Anna K. Berryman
Georgia S. Brennan
author_facet Brady Metherall
Anna K. Berryman
Georgia S. Brennan
author_sort Brady Metherall
collection DOAJ
description Abstract Chronic kidney disease (CKD) is a global health concern with early detection playing a pivotal role in effective management. Machine learning models demonstrate promise in CKD detection, yet the impact on detection and classification using different sets of clinical features remains under-explored. In this study, we focus on CKD classification and creatinine prediction using three sets of features: at-home, monitoring, and laboratory. We employ artificial neural networks (ANNs) and random forests (RFs) on a dataset of 400 patients with 25 input features, which we divide into three feature sets. Using 10-fold cross-validation, we calculate metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), and mean squared error. Our results reveal RF achieves superior accuracy (92.5%) in at-home CKD classification over ANNs (82.9%). ANNs achieve a higher TPR (92.0%), but a lower TNR (67.9%) compared with RFs (90.0% and 95.8%, respectively). For monitoring and laboratory features, both methods achieve accuracies exceeding 98%. The R2 score for creatinine regression is approximately 0.3 higher with laboratory features than at-home features. Feature importance analysis identifies the key clinical variables hemoglobin and blood urea, and key comorbidities hypertension and diabetes mellitus, in agreement with previous studies. Machine learning models, particularly RFs, exhibit promise in CKD diagnosis and highlight significant features in CKD detection. Moreover, such models may assist in screening a general population using at-home features—potentially increasing early detection of CKD, thus improving patient care and offering hope for a more effective approach to managing this prevalent health condition.
format Article
id doaj-art-5bedb55fd01f4b2b9a7b0a6ad0626101
institution Kabale University
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5bedb55fd01f4b2b9a7b0a6ad06261012025-02-09T12:37:20ZengNature PortfolioScientific Reports2045-23222025-02-0115111110.1038/s41598-025-88631-yMachine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurementsBrady Metherall0Anna K. Berryman1Georgia S. Brennan2Mathematical Institute, University of OxfordMathematical Institute, University of OxfordMathematical Institute, University of OxfordAbstract Chronic kidney disease (CKD) is a global health concern with early detection playing a pivotal role in effective management. Machine learning models demonstrate promise in CKD detection, yet the impact on detection and classification using different sets of clinical features remains under-explored. In this study, we focus on CKD classification and creatinine prediction using three sets of features: at-home, monitoring, and laboratory. We employ artificial neural networks (ANNs) and random forests (RFs) on a dataset of 400 patients with 25 input features, which we divide into three feature sets. Using 10-fold cross-validation, we calculate metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), and mean squared error. Our results reveal RF achieves superior accuracy (92.5%) in at-home CKD classification over ANNs (82.9%). ANNs achieve a higher TPR (92.0%), but a lower TNR (67.9%) compared with RFs (90.0% and 95.8%, respectively). For monitoring and laboratory features, both methods achieve accuracies exceeding 98%. The R2 score for creatinine regression is approximately 0.3 higher with laboratory features than at-home features. Feature importance analysis identifies the key clinical variables hemoglobin and blood urea, and key comorbidities hypertension and diabetes mellitus, in agreement with previous studies. Machine learning models, particularly RFs, exhibit promise in CKD diagnosis and highlight significant features in CKD detection. Moreover, such models may assist in screening a general population using at-home features—potentially increasing early detection of CKD, thus improving patient care and offering hope for a more effective approach to managing this prevalent health condition.https://doi.org/10.1038/s41598-025-88631-yChronic kidney disease classificationCreatinine predictionMachine learningAt-home detection
spellingShingle Brady Metherall
Anna K. Berryman
Georgia S. Brennan
Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
Scientific Reports
Chronic kidney disease classification
Creatinine prediction
Machine learning
At-home detection
title Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
title_full Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
title_fullStr Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
title_full_unstemmed Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
title_short Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements
title_sort machine learning for classifying chronic kidney disease and predicting creatinine levels using at home measurements
topic Chronic kidney disease classification
Creatinine prediction
Machine learning
At-home detection
url https://doi.org/10.1038/s41598-025-88631-y
work_keys_str_mv AT bradymetherall machinelearningforclassifyingchronickidneydiseaseandpredictingcreatininelevelsusingathomemeasurements
AT annakberryman machinelearningforclassifyingchronickidneydiseaseandpredictingcreatininelevelsusingathomemeasurements
AT georgiasbrennan machinelearningforclassifyingchronickidneydiseaseandpredictingcreatininelevelsusingathomemeasurements