An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms

• Published in: Computer methods and programs in biomedicine Vol. 112; no. 3; pp. 441 - 454
• Main Authors: Amaral, Jorge L.M., Lopes, Agnaldo J., Jansen, José M., Faria, Alvaro C.D., Melo, Pedro L.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.12.2013; Elsevier
• Subjects: Accuracy; Algorithms; Applied sciences; Artificial Intelligence; Biological and medical sciences; Chronic obstructive pulmonary disease; Chronic obstructive pulmonary disease, asthma; Classifiers; Clinical decision support; Computer science; control theory; systems; Computerized, statistical medical data processing and models in biomedicine; Data processing. List processing. Character string processing; Early Diagnosis; Exact sciences and technology; Forced oscillation technique; Genetic algorithms; Humans; Internal Medicine; Learning and adaptive systems; Machine learning; Medical management aid. Diagnosis aid; Medical sciences; Memory organisation. Data processing; Neural networks; Other; Pneumology; Respiratory System - physiopathology; ROC Curve; Searching; Smoking; Smoking - physiopathology; Software; Support vector machines; Forced oscillation technique; Early diagnosis; Chronic obstructive pulmonary disease; Clinical decision support; Artificial intelligence; Smoking; Consumption; Nearest neighbour; Automatic classification; Decision support system; Cross validation; Neural network; Experimental study; Biomedical data processing; Tobacco; Volunteering; Genetic algorithm; Supervised learning; Vector support machine; Receiver operating characteristic curves; Diagnosis; Pharmacokinetics; Learning algorithm; Logistics
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2013.08.004

The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers.