Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan

Krishnamurthy, Surya; Ks, Kapeleshh; Dovgan, Erik; Luštrek, Mitja; Piletič, Barbara Gradišek; Srinivasan, Kathiravan; Li, Yu-Chuan; Gradišek, Anton; Syed-Abdul, Shabbir

doi:10.3390/healthcare9050546

Cited by 70 publications

(36 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chronic kidney diseases (CKDs) represent a heavy burden on the healthcare system because of the increasing number of patients, high risk of progression to end-stage renal disease, and poor prognosis with respect to morbidity and mortality ( 1 ). Sleep and smoking are two main modifiable factors of CKDs ( 2 ).…”

Section: Introductionmentioning

confidence: 99%

Sleeping, Smoking, and Kidney Diseases: Evidence From the NHANES 2017–2018

Wang

Liu

et al. 2021

Front. Med.

View full text Add to dashboard Cite

Study Objectives: Smoking and sleep are modifiable factors associated with the chronic kidney diseases. However, the interaction of smoking and sleep on the renal function are still unclear. Therefore, we aimed to evaluate the interactive impacts of smoking and sleep on the renal function.Methods: Data were obtained from the National Health and Nutrition Examination Survey. The study population were categorized into nine subgroups by smoking (smoking every day, sometimes, and non-smokers recently) and sleep duration (short duration ≤ 6 h, normal duration 6–9 h, and longer duration ≥ 9 h on the weekdays).Results: The study group with a short sleep duration had significantly higher serum cotinine and hydrocotinine levels compared with the other two sleep groups. After adjusting the demographic characteristics (age, race, body mass index, and marital status), sleep quality (snoring or breathing cessation), and comorbidities (diabetes mellitus, hypertension, high cholesterol, anemia, congestive heart failure, coronary heart disease, and stroke), non-smokers with short or long sleep duration had significant lower estimated glomerular filtration rate (eGFR) levels than the study group who smoked every day and slept ≤ 6 h. The effects of sleep duration on eGFR levels varied with smoking status. For the study group smoking every day, eGFR levels increased as sleep duration decreased, whereas for the study group smoking sometimes, eGFR levels increased as sleep duration increased. The U-shaped effects of eGFR levels were observed among non-smokers whose normal sleep duration was associated with better eGFR levels. Normal sleep duration was an important protective factor of the renal function for non-smokers than smokers.Conclusions: The effects of sleep duration on eGFR levels varied with smoking status. Normal sleep duration was a protective factor and more crucial for non-smokers than for smokers.

show abstract

Section: Introductionmentioning

confidence: 99%

Sleeping, Smoking, and Kidney Diseases: Evidence From the NHANES 2017–2018

Wang

Liu

et al. 2021

Front. Med.

View full text Add to dashboard Cite

show abstract

“…The performance of the proposed model compared with several recent scholarly studies, such as Ant Colony-based Optimization Classifier by Elhoseny et al [ 19 ], Neural network by Vasquez-Morales et al [ 27 ], K NN by M Senan et al [ 37 ], Convolutional Neural Networks by Krishnamurthy et al [ 38 ], SVM by Polat, H. et al [ 45 ], and SAE and Softmax Regression proposed by Sarah A. et al [ 46 ]. The exiting works obtained the accuracy from 85% to 98.5%, while the proposed model has obtained an accuracy of 100%.…”

Section: Discussionmentioning

confidence: 99%

“…Krishnamurthy S. et al [ 38 ] developed various artificial intelligence models to predict Chronic Kidney Disease. The LightGBM model selected the most important features for CKD prediction: age, gout, diabetes mellitus, use of sulfonamides, and angiotensins.…”

Section: Related Workmentioning

confidence: 99%

A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease

2022

View full text Add to dashboard Cite

Diabetes and high blood pressure are the primary causes of Chronic Kidney Disease (CKD). Glomerular Filtration Rate (GFR) and kidney damage markers are used by researchers around the world to identify CKD as a condition that leads to reduced renal function over time. A person with CKD has a higher chance of dying young. Doctors face a difficult task in diagnosing the different diseases linked to CKD at an early stage in order to prevent the disease. This research presents a novel deep learning model for the early detection and prediction of CKD. This research objectives to create a deep neural network and compare its performance to that of other contemporary machine learning techniques. In tests, the average of the associated features was used to replace all missing values in the database. After that, the neural network’s optimum parameters were fixed by establishing the parameters and running multiple trials. The foremost important features were selected by Recursive Feature Elimination (RFE). Hemoglobin, Specific Gravity, Serum Creatinine, Red Blood Cell Count, Albumin, Packed Cell Volume, and Hypertension were found as key features in the RFE. Selected features were passed to machine learning models for classification purposes. The proposed Deep neural model outperformed the other four classifiers (Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic regression, Random Forest, and Naive Bayes classifier) by achieving 100% accuracy. The proposed approach could be a useful tool for nephrologists in detecting CKD.

show abstract

“…The same goes for monitoring the elderly for heart diseases, which requires constant oversight and immediate response in case of any issues. Diabetes is one of the most common diseases in patients worldwide, ranging over a large age group [108][109][110][111].…”

Section: Discussionmentioning

confidence: 99%

Recent Advances on IoT-Assisted Wearable Sensor Systems for Healthcare Monitoring

et al. 2021

Self Cite

View full text Add to dashboard Cite

IoT has played an essential role in many industries over the last few decades. Recent advancements in the healthcare industry have made it possible to make healthcare accessible to more people and improve their overall health. The next step in healthcare is to integrate it with IoT-assisted wearable sensor systems seamlessly. This review rigorously discusses the various IoT architectures, different methods of data processing, transfer, and computing paradigms. It compiles various communication technologies and the devices commonly used in IoT-assisted wearable sensor systems and deals with its various applications in healthcare and their advantages to the world. A comparative analysis of all the wearable technology in healthcare is also discussed with tabulation of various research and technology. This review also analyses all the problems commonly faced in IoT-assisted wearable sensor systems and the specific issues that need to be tackled to optimize these systems in healthcare and describes the various future implementations that can be made to the architecture and the technology to improve the healthcare industry.

show abstract

Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan

Cited by 70 publications

References 21 publications

Sleeping, Smoking, and Kidney Diseases: Evidence From the NHANES 2017–2018

Sleeping, Smoking, and Kidney Diseases: Evidence From the NHANES 2017–2018

A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease

Recent Advances on IoT-Assisted Wearable Sensor Systems for Healthcare Monitoring

Contact Info

Product

Resources

About