A Comparative Study, Prediction and Development of Chronic Kidney Disease Using Machine Learning on Patients Clinical Records

Abstract

Chronic Kidney Disease (CKD) has become a major problem in modern times, and it is dubbed the silent assassin due to its delayed signs. To overcome these critical issues, early identification may minimize the prevalence of chronic diseases, though it is quite difficult because of different kinds of limitations in the dataset. The novelty of our study is that we extracted the best features from the dataset in order to provide the best classification models for diagnosing patients with chronic kidney disease. In our study, we used CKD patients’ clinical datasets to predict CKD using some popular machine learning algorithms. After handling missing values, K-means clustering has been performed. Then feature selection was done by applying the XGBoost feature selection algorithm. After selecting features from our dataset, we have used a variety of machine learning models to determine the best classification models, including Neural Network (NN), Random Forest (RF), Support Vector Machine (SVM), Random Tree (RT), and Bagging Tree Model (BTM). Accuracy, Sensitivity, Specificity, and Kappa values were used to evaluate model performance.

Adversarial transfer learning based hybrid recurrent network for air quality prediction

“…Li et al formulated an innovative air quality prediction approach based on spatial-temporal deep learning (STDL), which inherently takes into account spatial and temporal associations [25]. Yasmin et al proposed an efficient hybrid MLP-LSTM model to forecast the air quality index based on the cluster analysis [37]. Zhang et al put forward a new deep residuals network for collectively predicting two kinds of crowd flows in a city's every zone affected by temporal dependencies (period, trend, closeness) and spatial dependencies (adjacent and distant) [39].…”

Development of mathematical methods for diagnosing kidney diseases using fuzzy set tools

“…In the next stage, we obtain the corresponding analytical expressions using Figures 4-8. For example, we provide analytical calculations of membership functions in selected class states based on characteristics x1 and x2, given by expressions ( 12)- (17). Below are the analytical expressions for the membership functions of the classes ω PL , ω CKD , and ω AKI based on the levels of bilirubin (factor x 1 ) and urea (factor x2):…”

“…In diagnosing kidney diseases, an important tool is the analysis of functional kidney tests, which provide information about the functional state of the kidneys [16]. Significant risk factors for kidney dysfunction include clinical signs indicating a high or moderate risk of developing kidney disease [17]. Identifying these risk factors helps determine the appropriate approach to management and treatment for individuals at risk.…”

“…This necessitates rapid decision-making to prioritize patients based on the severity of their condition, determining who requires immediate care, urgent consultation, or can afford a more delayed evaluation. Complicating matters further, clinicians' judgments are inherently subjective and can be influenced by personal biases or external factors like fatigue, potentially leading to inconsistencies in diagnosis and treatment [17].…”

Chronic Kidney Diseases Prediction Using Machine Learning Algorithms

“…[M.M. Hassan, 2023] [4] showcased that in order to predict CKD using certain well-known machine learning methods, we analysed clinical information from CKD patients. K-means clustering has been done after addressing missing values.…”