Comparison of Different Machine Learning Techniques to Predict Diabetic Kidney Disease

Abstract

Background. Diabetic kidney disease (DKD), one of the complications of diabetes in patients, leads to progressive loss of kidney function. Timely intervention is known to improve outcomes. Therefore, screening patients to identify high-risk populations is important. Machine learning classification techniques can be applied to patient datasets to identify high-risk patients by building a predictive model. Objective. This study aims to identify a suitable classification technique for predicting DKD by applying different classification techniques to a DKD dataset and comparing their performance using WEKA machine learning software. Methods. The performance of nine different classification techniques was analyzed on a DKD dataset with 410 instances and 18 attributes. Data preprocessing was carried out using the PartitionMembershipFilter. A 10-fold cross validation was performed on the dataset. The performance was assessed on the basis of the execution time, accuracy, correctly and incorrectly classified instances, kappa statistics (K), mean absolute error, root mean squared error, and true values of the confusion matrix. Results. With an accuracy of 93.6585% and a higher K value (0.8731), IBK and random tree classification techniques were found to be the best performing techniques. Moreover, they also exhibited the lowest root mean squared error rate (0.2496). There were 15 false-positive instances and 11 false-negative instances with these prediction models. Conclusions. This study identified IBK and random tree classification techniques as the best performing classifiers and accurate prediction methods for DKD.

The automatic detection of diabetic kidney disease from retinal vascular parameters combined with clinical variables using artificial intelligence in type-2 diabetes patients

“…DKD is the main cause of ESRD worldwide, accounting for approximately 20–40% of patients with diabetes [ 19 , 20 ]. Early and accurate detection and intervention contributing to a better outcome is beneficial for the patients [ 13 , 19 ].…”

“…DKD is the main cause of ESRD worldwide, accounting for approximately 20–40% of patients with diabetes [ 19 , 20 ]. Early and accurate detection and intervention contributing to a better outcome is beneficial for the patients [ 13 , 19 ]. The present detection of DKD depends on the measurement of albuminuria or the eGFR, which are invasive and not optimal.…”

“…Maniruzzaman et al developed a model with superior performance to detect DN using SVM-RBF (support vector machine-radial basis function) with 13 parameters (sex, age, BMI, DM duration, FBS, HbA1c, LDL, HDL, TGs, SBP, DBP, DM treatment, use of statins), and the accuracy and AUC were 88.7% and 0.9, respectively, when validated [ 22 ]. Satish Kumar David et al developed a detection model for DKD with an accuracy of 93.7% using IBK and random tree classification techniques through 18 parameters (age, sex, serum albumin, sodium, potassium, urea, glucose, creatinine, HbA1c, hemoglobin, white blood cell counts, red blood cell counts, hemoglobin (%), platelet counts, SBP, DBP, hypertension, and retinopathy) [ 19 ]. However, most biochemical parameters are not convenient enough, and retinal vascular parameters have not been used in formal models, although a large number of studies have indicated that retinal changes are related to DKD [ 1 , 9 ].…”

Multi-classifier models to improve the accuracy of fish landing application

“…The network architecture, which includes multiple layers of nodes (neurons) and non-linear activation functions, enables MLPs to capture intricate patterns and representations in the data. IBK stands out as one of the simplest and earliest classification algorithms [10]. Finally, RF stemming from the decision tree, facilitates the aggregation of numerous weak or weakly-correlated classifiers into a robust classifier [11].…”

Artificial Intelligence for Predicting and Diagnosing Complications of Diabetes

“…AI has been applied to ten populations of patients with type 2 diabetes to predict development of DN using various combinations of demographics, vital signs, and laboratory tests. [83][84][85][86][87][88][89][90][91][92] The predictions were compared with modified databases in a sensitivity analysis comparison in two of these reports 84,87 and outperformed algorithms derived exclusively from clinical data in four of these reports. 83,85,86,91 In addition to standard data extraction, one study used natural language processing to identify data from the EHR.…”