Date of Award

2019-01-01

Degree Name

Doctor of Philosophy

Department

Engineering

Advisor(s)

Vladik Kreinovich

Abstract

Computer-aided classification of respiratory small airways dysfunction is not an easy task. There is a need to develop more robust classifiers, specifically for children as the classification studies performed to date have the following limitations: 1) they include features derived from tests that are not suitable for children and 2) they cannot distinguish between mild and severe small airway dysfunction.

This Dissertation describes the classification algorithms with high discriminative capacity to distinguish different levels of respiratory small airways function in children (Asthma, Small Airways Impairment, Possible Small Airways Impairment, and Normal lung function). This ability came from innovative feature selection, where features were derived from the child-friendly and reliable Impulse Oscillometry (IOS) technique. The feature selection process included deep statistical analyses and a proposed novel invariance-based pre-processing approach in the study of IOS features. The results are 100% accurate, sensitive and specific to classify normal lung function vs. small airways dysfunction; and 92%- 95% accurate, 73%-100% sensitive, and 80%-100% specific for classifying a specific type of small airways dysfunction. These results are better than any of the previous computer- aided classification of small airways dysfunction results.

Language

en

Provenance

Received from ProQuest

File Size

111 pages

File Format

application/pdf

Rights Holder

Nancy Selene Avila

Share

COinS