Mollie Poynton

Classification of Smoking Cessation Status

Applying Machine Learning Methods to Health Survey Data

• Broschiertes Buch

Produktbeschreibung

This study examined the ability of a backpropagation neural network classifier to distinguish between current and former smokers in the 2000 National Health Interview Survey sample adult file. A multilayer artificial neural network was contructed to predict class membership, current or former smoker, using the attribute subset. Classifier performance exceeded that of random chance. However, separation of current and former smokers was imperfect. Additionally, performance did not exceed that of a comparison classifier created using logistic regression. Imprecise, but high quality health survey data provided sufficient information for prediction of smoking cessation status. Membership of specific survey items in the attribute subset was largely supported by the literature. However, the inability to interpret relationships among attribute values in the BPNN model hampers comparison with published literature. The study establishes the ability of a machine learning method, backpropagation neural networks, to classify a health-related behavior, smoking cessation.

Produktdetails

• Verlag: LAP Lambert Academic Publishing
• Seitenzahl: 144
• Erscheinungstermin: 17. Mai 2010
• Englisch
• Abmessung: 220mm x 150mm x 9mm
• Gewicht: 233g
• ISBN-13: 9783838306131
• ISBN-10: 3838306139
• Artikelnr.: 26890638

Autorenporträt

Mollie R. Poynton PhD, APRN, BC is a faculty member of the University of Utah College of Nursing and School of Medicine informatics programs. She studies applications of data mining methods to human behavior, primarily smoking cessation and patient adherence. Her work has been published in Clinical Toxicology and Journal of Biomedical Informatics.