Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms

• Published in: Computer methods and programs in biomedicine Vol. 104; no. 3; pp. 443 - 451
• Main Authors: Ozcift, Akin, Gulten, Arif
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.12.2011; Elsevier
• Subjects: Algorithms; Artificial Intelligence; Biological and medical sciences; Classifier performance; Cleveland heart; Computer aided diagnosis; Diabetes; Diagnosis; Ensemble learning; Humans; Internal Medicine; Medical sciences; Other; Parkinson's; Radiotherapy. Instrumental treatment. Physiotherapy. Reeducation. Rehabilitation, orthophony, crenotherapy. Diet therapy and various other treatments (general aspects); ROC Curve; Rotation forest; Sensitivity and Specificity; Technology. Biomaterials. Equipments. Material. Instrumentation; Parkinson's; Cleveland heart; Classifier performance; Rotation forest; Diabetes; Computer aided diagnosis; Ensemble learning; Biomedical engineering
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2011.03.018

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems.