Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers

Abstract

Diabetes mellitus is a group of metabolic diseases in which blood sugar levels are too high. About 8.8% of the world was diabetic in 2017. It is projected that this will reach nearly 10% by 2045. The major challenge is that when machine learning-based classifiers are applied to such data sets for risk stratification, leads to lower performance. Thus, our objective is to develop an optimized and robust machine learning (ML) system under the assumption that missing values or outliers if replaced by a median configuration will yield higher risk stratification accuracy. This ML-based risk stratification is designed, optimized and evaluated, where: (i) the features are extracted and optimized from the six feature selection techniques (random forest, logistic regression, mutual information, principal component analysis, analysis of variance, and Fisher discriminant ratio) and combined with ten different types of classifiers (linear discriminant analysis, quadratic discriminant analysis, naïve Bayes, Gaussian process classification, support vector machine, artificial neural network, Adaboost, logistic regression, decision tree, and random forest) under the hypothesis that both missing values and outliers when replaced by computed medians will improve the risk stratification accuracy. Pima Indian diabetic dataset (768 patients: 268 diabetic and 500 controls) was used. Our results demonstrate that on replacing the missing values and outliers by group median and median values, respectively and further using the combination of random forest feature selection and random forest classification technique yields an accuracy, sensitivity, specificity, positive predictive value, negative predictive value and area under the curve as: 92.26%, 95.96%, 79.72%, 91.14%, 91.20%, and 0.93, respectively. This is an improvement of 10% over previously developed techniques published in literature. The system was validated for its stability and reliability. RF-based model showed the best performance when outliers are replaced by median values.Electronic supplementary materialThe online version of this article (10.1007/s10916-018-0940-7) contains supplementary material, which is available to authorized users.

MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model

“…V 6 } with 6 measurements per 24-h sampling window for each feature. Missing values were imputed by using the median value of the variable over the entire cohort at the sampling time point [23]. each as a true positive, false positive, true negative or false negative.…”

“…The result was a time series V = {V1, V2, … V6} with 6 measurements per 24-h sampling window for each feature. Missing values were imputed by using the median value of the variable over the entire cohort at the sampling time point [23]. Performance of the models were compared, and an optimal prediction time of 6 h was chosen based on clinical and operational considerations such as anticipated impact on nursing and clinician workload.…”

Beyond the Horizon: A Meticulous Analysis of Clinical Decision-Making Practices

“…However, for feature subset selection, ECAs lack in reducing residual features from final selection and they are costly too. In [28] development of a robust optimized machine learning -ML system is presented. The aim is to improve risk stratification accuracy by replacing outliers with median configuration, which is based on assumption.…”

Advanced Data Imputation Techniques for Predicting Type 2 Diabetes using Machine Learning

“…Type 2 diabetes is a metabolic disease that causes glucose to accumulate in the blood. When a person eats food it gets broken down into glucose which enters into cells for the functioning of the body [6]. A hormone called insulin is secreted by the pancreas, which is a chemical messenger that allows glucose to enter into cells.…”

“…The majority of studies shows that diabetes mellitus has proven to affect the growth in the health department over the last few years [6]. It has been observed that in 2013, normal Indian suffering from diabetes mellitus was estimated to have spent Rs 4,493 (US$95) a yearly treatment cost.…”