Hybrid diabetes disease prediction framework based on data imputation and outlier detection techniques

Abstract

In the field of medical science, accurate prediction is a difficult and challenging task. But, the presence of missing values and outliers can make the prediction task more complicated. Many researchers address the issue of missing value in medical data, either detect the missing value and delete the respective data instances from the dataset or adopt some default methods such as mean, median, neighbour etc., for filling the missing value. However, both methods are lacking to produce optimal results. Furthermore, outliers are also presented in data and degraded the performance of classifier. Few researchers also focus on the outlier detection in medical dataset, but it is not fully explored till date. This work considers the two well‐known problems of data that is, (i) missing value imputation, and (ii) outlier. The missing value imputation issue is addressed through K‐Mean++ based data imputation technique. This technique also validates the data through clustering and also compute the values for missing data. The outlier can be detected through an ABC based outlier detection technique. Further, the final outcome is determined using LS‐SVM classifiers. Hence, this work presents a hybrid disease diagnosis framework for diabetes prediction, called hybrid diabetes prediction framework. The reason behind to choose the diabetes dataset for implementation as it contains 763 missing values and several outliers. The simulation results showed that proposed hybrid framework effectively determines the missing values and outliers in diabetes dataset. Further, the performance of proposed hybrid diabetes prediction framework is evaluated using accuracy, sensitivity, specificity, kappa and AUC parameters and compared with 34 state of art techniques. Results confirmed that proposed hybrid framework obtains 96.57%, 93.37%, 98.12%, 98.17%, and 95.43% accuracy, sensitivity, specificity, kappa and AUC rate respectively.

Comprehensive analysis of Classical Machine Learning models and Ensemble methods for predicting Crime in urban society

“…The first one is to remove those rows with the outliers altogether because the outlier's percentage is less. The second method is data imputation by random sampling from a normal distribution with the standard deviation from the mean (Srivastava et al, 2022).…”

Deep Forest Based Internet of Medical Things System for Diagnosis of Heart Disease

“…1 illustrates the few applications of IoT devices. It is analyzed that collected data are in huge amount and existing tools are not capable to process and interpret such massive data (Srivastava, Kumar and Singh, 2022). IoT with data analytics, edge computing and fog computing are capable to provide state of art solutions for many healthcare applications such as health monitoring, diagnosis and prediction of diseases, emergence services, resource allocation, and elderly care.…”

A Novel Data Imputation Method (M-CBRI) for Industrial Analytic Applications

“…[2] However, not always these data resources yield complete datasets. Even though the majority of missing values are caused by manual data entry, missing data might have occurred due to several factors such as human error, noise generation during transformation, equipment and measurement error, lack of response [3,4,5,6]. The first approach is eliminating missing values and using the rest of the data as a complete dataset [7].…”