Intelligent Machine Learning Approach for Effective Recognition of Diabetes in E-Healthcare Using Clinical Data

Abstract

Significant attention has been paid to the accurate detection of diabetes. It is a big challenge for the research community to develop a diagnosis system to detect diabetes in a successful way in the e-healthcare environment. Machine learning techniques have an emerging role in healthcare services by delivering a system to analyze the medical data for diagnosis of diseases. The existing diagnosis systems have some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we have proposed a diagnosis system using machine learning methods for the detection of diabetes. The proposed method has been tested on the diabetes data set which is a clinical dataset designed from patient’s clinical history. Further, model validation methods, such as hold out, K-fold, leave one subject out and performance evaluation metrics, includes accuracy, specificity, sensitivity, F1-score, receiver operating characteristic curve, and execution time have been used to check the validity of the proposed system. We have proposed a filter method based on the Decision Tree (Iterative Dichotomiser 3) algorithm for highly important feature selection. Two ensemble learning algorithms, Ada Boost and Random Forest, are also used for feature selection and we also compared the classifier performance with wrapper based feature selection algorithms. Classifier Decision Tree has been used for the classification of healthy and diabetic subjects. The experimental results show that the proposed feature selection algorithm selected features improve the classification performance of the predictive model and achieved optimal accuracy. Additionally, the proposed system performance is high compared to the previous state-of-the-art methods. High performance of the proposed method is due to the different combinations of selected features set and Plasma glucose concentrations, Diabetes pedigree function, and Blood mass index are more significantly important features in the dataset for prediction of diabetes. Furthermore, the experimental results statistical analysis demonstrated that the proposed method would effectively detect diabetes and can be deployed in an e-healthcare environment.

Analysis and Testing of a Suitable Compatible Electrode’s Material for Continuous Measurement of Glucose Concentration

“…The method was designed on a filtering method based on a decision tree algorithm. Experimental results have shown that the proposed performance of the system is comparable to previous state-of-the-art methods [21].…”

An Intelligent Decision-Making Support System for the Detection and Staging of Prostate Cancer in Developing Countries

“…As shown in Table 6 and Figure 12 , the receiver operating curve (ROC), the ROC is thetrue positive rate–false positive rate curve: the x -axis represents true; positive rate, the y -axis represents the false positive rate. From Figure 12 , we can see that the curve is very close to (0, 1) point [ 22 – 24 ]. Therefore, the classification accuracy of the prostate cancer machine-assisted diagnosis system is still very high.…”

Prediction of Chronic Kidney Disease - A Machine Learning Perspective

“…Amin UI Haq et al [34] proposed the machine learning model to predict the diabetes disease at early stage. They concluded that machine learning can play vital role in the healthcare.…”