Chronic kidney disease prediction based on machine learning algorithms

Islam, Md. Ariful; Majumder, Md. Ziaul Hasan; Hussein, Md. Alomgeer

doi:10.1016/j.jpi.2023.100189

Cited by 71 publications

(27 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gradient boosting methods are among the most commonly used algorithms in the field of perioperative medicine and often show excellent performance [ 10 , 11 ]. However, there is evidence in the current literature that deep learning methods are superior to XGBoost with respect to AUROC [ 12 ] which made us use both methods.…”

Section: Discussionmentioning

confidence: 99%

Impact of the Covid-19 pandemic on the performance of machine learning algorithms for predicting perioperative mortality

Andonov

Ulm

Graeßner

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Machine-learning models are susceptible to external influences which can result in performance deterioration. The aim of our study was to elucidate the impact of a sudden shift in covariates, like the one caused by the Covid-19 pandemic, on model performance. Methods After ethical approval and registration in Clinical Trials (NCT04092933, initial release 17/09/2019), we developed different models for the prediction of perioperative mortality based on preoperative data: one for the pre-pandemic data period until March 2020, one including data before the pandemic and from the first wave until May 2020, and one that covers the complete period before and during the pandemic until October 2021. We applied XGBoost as well as a Deep Learning neural network (DL). Performance metrics of each model during the different pandemic phases were determined, and XGBoost models were analysed for changes in feature importance. Results XGBoost and DL provided similar performance on the pre-pandemic data with respect to area under receiver operating characteristic (AUROC, 0.951 vs. 0.942) and area under precision-recall curve (AUPR, 0.144 vs. 0.187). Validation in patient cohorts of the different pandemic waves showed high fluctuations in performance from both AUROC and AUPR for DL, whereas the XGBoost models seemed more stable. Change in variable frequencies with onset of the pandemic were visible in age, ASA score, and the higher proportion of emergency operations, among others. Age consistently showed the highest information gain. Models based on pre-pandemic data performed worse during the first pandemic wave (AUROC 0.914 for XGBoost and DL) whereas models augmented with data from the first wave lacked performance after the first wave (AUROC 0.907 for XGBoost and 0.747 for DL). The deterioration was also visible in AUPR, which worsened by over 50% in both XGBoost and DL in the first phase after re-training. Conclusions A sudden shift in data impacts model performance. Re-training the model with updated data may cause degradation in predictive accuracy if the changes are only transient. Too early re-training should therefore be avoided, and close model surveillance is necessary.

show abstract

Section: Discussionmentioning

confidence: 99%

Impact of the Covid-19 pandemic on the performance of machine learning algorithms for predicting perioperative mortality

Andonov

Ulm

Graeßner

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…The use of machine learning and predictive modeling is suggested as an approach for identifying chronic kidney disease and improving the accuracy of predictions [35]. However, machine learning algorithms require large amounts of data to be trained, and the quality of the data can affect the accuracy of the predictions.…”

Section: Discussion and Analysismentioning

confidence: 99%

“…The limitations of this study are that it used a preconstructed dataset and was conducted on a specific population, so the results may not be generalizable to other datasets or populations. 6 [35] Machine learning algorithms…”

Section: [34] Smote Rose and Adasynmentioning

confidence: 99%

An analysis and literature review of algorithms for frequent itemset mining

2023

IJACR

View full text Add to dashboard Cite

show abstract

“…M.A. Islam et al (2023) 8 conducted a study on the early detection of CKD using machine learning. They worked with a dataset of 400 cases, featuring 24 attributes—13 categorical and 11 numerical.…”

Section: Literature Reviewmentioning

confidence: 99%

“… Authors Limitations M.A. Islam et al (2023) 8 1. Limited exploration of alternative feature selection methods beyond PCA, impacting result robustness.…”

Section: Literature Reviewmentioning

confidence: 99%

ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

Halder,

Uddin,

Uddin

et al. 2024

Journal of Pathology Informatics

View full text Add to dashboard Cite

Chronic kidney disease prediction based on machine learning algorithms

Cited by 71 publications

References 25 publications

Impact of the Covid-19 pandemic on the performance of machine learning algorithms for predicting perioperative mortality

Impact of the Covid-19 pandemic on the performance of machine learning algorithms for predicting perioperative mortality

An analysis and literature review of algorithms for frequent itemset mining

ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

Contact Info

Product

Resources

About