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

Abstract

Accuracy plays a vital role in the medical field as it concerns with the life of an individual. Extensive research has been conducted on disease classification and prediction using machine learning techniques. However, there is no agreement on which classifier produces the best results. A specific classifier may be better than others for a specific dataset, but another classifier could perform better for some other dataset. Ensemble of classifiers has been proved to be an effective way to improve classification accuracy. In this research we present an ensemble framework with multi-layer classification using enhanced bagging and optimized weighting. The proposed model called "HM-BagMoov" overcomes the limitations of conventional performance bottlenecks by utilizing an ensemble of seven heterogeneous classifiers. The framework is evaluated on five different heart disease datasets, four breast cancer datasets, two diabetes datasets, two liver disease datasets and one hepatitis dataset obtained from public repositories. The analysis of the results show that ensemble framework achieved the highest accuracy, sensitivity and F-Measure when compared with individual classifiers for all the diseases. In addition to this, the ensemble framework also achieved the highest accuracy when compared with the state of the art techniques. An application named "IntelliHealth" is also developed based on proposed model that may be used by hospitals/doctors for diagnostic advice.

Machine Learning and Data Mining Methods in Diabetes Research

“…The second category deals with disease prediction and diagnosis [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72], [73], [74], [75], [76]. Numerous algorithms and different approaches have been applied, such as traditional machine learning algorithms, ensemble learning approaches and association rule learning in order to achieve the best classification accuracy.…”

“…The specific approaches have also been used in DM prediction [50], [52], [53], [69]. Anderson et al used a Bayesian scoring algorithm to explore the model space [50].…”

“…Anderson et al used a Bayesian scoring algorithm to explore the model space [50]. In [52], authors proposed an ensemble framework with multi-layer classification, using enhanced bagging and optimized weighting, combining seven heterogeneous classifiers. In [53], authors used Rotation Forest (RF), a newly proposed ensemble algorithm, to combine 30 machine learning algorithms.…”

Hybrid Disease Diagnosis Using Multiobjective Optimization with Evolutionary Parameter Optimization

“…Bashir et al [45] presented an ensemble framework for predicting people with diabetes with multilayer classification using enhanced bagging and optimized weighting. The proposed HM-BagMOOV method used KNN approach for missing data imputation and had three layers, namely, layer 1 containing naive Bayes (NB), quadratic discriminant analysis (QDA), linear regression (LR), instance-based learning (IBL), and SVM; layer 2 included ANN and RF; and layer 3 used multilayer weighted bagging prediction.…”

Performance Analysis of Classification Algorithms on a Novel Unified Clinical Decision Support Model for Predicting Coronary Heart Disease Risks

“…The main drawback in using neural network is the time to converge and getting into local optimum value, so the neural networks are not used for analysis in our work and we have tried only with the rich set of data mining algorithms. Research works [8,10] uses Bagging ensemble classifier in medical decision support system. In our proposed methods boosting ensemble method too is tried along with bagging.…”