Diabetes Prediction Using Ensembling of Different Machine Learning Classifiers (2020-04-23T00:00:00.000000Z)

TL;DR

A robust framework for diabetes prediction is proposed where the outlier rejection, filling the missing values, data standardization, feature selection, K-fold cross-validation, and different Machine Learning (ML) classifiers were employed and the weighted ensembling of different ML models were employed to improve the prediction of diabetes.

Abstract

Diabetes, also known as chronic illness, is a group of metabolic diseases due to a high level of sugar in the blood over a long period. The risk factor and severity of diabetes can be reduced significantly if the precise early prediction is possible. The robust and accurate prediction of diabetes is highly challenging due to the limited number of labeled data and also the presence of outliers (or missing values) in the diabetes datasets. In this literature, we are proposing a robust framework for diabetes prediction where the outlier rejection, filling the missing values, data standardization, feature selection, K-fold cross-validation, and different Machine Learning (ML) classifiers (k-nearest Neighbour, Decision Trees, Random Forest, AdaBoost, Naive Bayes, and XGBoost) and Multilayer Perceptron (MLP) were employed. The weighted ensembling of different ML models is also proposed, in this literature, to improve the prediction of diabetes where the weights are estimated from the corresponding Area Under ROC Curve (AUC) of the ML model. AUC is chosen as the performance metric, which is then maximized during hyperparameter tuning using the grid search technique. All the experiments, in this literature, were conducted under the same experimental conditions using the Pima Indian Diabetes Dataset. From all the extensive experiments, our proposed ensembling classifier is the best performing classifier with the sensitivity, specificity, false omission rate, diagnostic odds ratio, and AUC as 0.789, 0.934, 0.092, 66.234, and 0.950 respectively which outperforms the state-of-the-art results by 2.00 % in AUC. Our proposed framework for the diabetes prediction outperforms the other methods discussed in the article. It can also provide better results on the same dataset which can lead to better performance in diabetes prediction. Our source code for diabetes prediction is made publicly available.

References49 items

Smart home health monitoring system for predicting type 2 diabetes and hypertension

Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the International Diabetes Federation Diabetes Atlas, 9th edition.

DMP_MI: An Effective Diabetes Mellitus Classification Algorithm on Imbalanced Data With Missing Values

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

IDF Diabetes Atlas: Global estimates of diabetes prevalence for 2017 and projections for 2045.

Comparative approaches for classification of diabetes mellitus data: Machine learning paradigm

Genetic algorithm based feature selection and MOE Fuzzy classification algorithm on Pima Indians Diabetes dataset

Skin lesion detection based on an ensemble of deep convolutional neural network

XGBoost: A Scalable Tree Boosting System

IntelliHealth: A medical decision support application using a novel weighted multi-layer classifier ensemble framework

Classification of Diabetes Mellitus Using Machine Learning Techniques

Diagnosis of Diabetes Using a Weight-Adjusted Voting Approach

Cross-validation pitfalls when selecting and assessing regression and classification models

The return of AdaBoost.MH: multi-class Hamming trees

Learning the naive Bayes classifier with optimization models

Statistical analysis of latent generalized correlation matrix estimation in transelliptical distribution.

Design Ensemble Machine Learning Model for Breast Cancer Diagnosis

Outliers detection and treatment: a review

A survey of cross-validation procedures for model selection

Decision trees as possibilistic classifiers

Survey of Improving K-Nearest-Neighbor for Classification

Gaussian process for nonstationary time series prediction

The diagnostic odds ratio: a single indicator of test performance.

A multivariate logistic regression equation to screen for diabetes: development and validation.

Systematic reviews of evaluations of diagnostic and screening tests

Independent component analysis: algorithms and applications

Distribution-balanced stratified cross-validation for accuracy estimation

Using neural networks for prediction of the subcellular location of proteins.

Support-Vector Networks

Review of neural network applications in medical imaging and signal processing

Discriminant Analysis and Statistical Pattern Recognition

Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus

Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition

Predictive modelling and analytics for diabetes using a machine learning approach

Searching for Activation Functions

Prediction of Diabetes using Classification Algorithms

Outlier Detection: Applications and techniques in Data Mining

Comparison of Classifiers for the Risk of Diabetes Prediction

Dropout: a simple way to prevent neural networks from overfitting

Design of Classifier for Detection of Diabetes Mellitus Using Genetic Programming