Date of Award
Master of Science
Electrical and Computer Engr
Bashir I. Morshed
Dr. Amy L de Jongh Curry
Asthma and Chronic Obstructive Pulmonary Disease are chronic and long-term lung diseases. Disease monitoring with minimal sensors with enough efficacy can make the disease management easier and efficacious for patients. Towards this goal, we propose a new model for the severity assessment of these diseases through wearables and compatible with mobile health applications, using only peripheral capillary oxygen saturation (SpO2) and heart rate (from pulse oximeter sensor). Patient data are obtained from the MIMIC-III Waveform Database Matched Subset. The dataset consists of 168 subjects. Both heart rate signal and SpO2 data of subjects are analyzed in retrospective via the proposed model to classify the severity of the diseases. Strategically, a rule-based threshold approach in real time evaluation is considered for the categorization scheme. Furthermore, a method is proposed to estimate severity as an Event of Interest (EOI) using the computed metrics from the datasets of the subjects with mathematical functions. Finally, four hyper-parameter models and K-Means Clustering algorithms are implemented for the distributions of severities of the diseases. For asthma, maximum accuracy is 60% and sensitivity is 78%, while the achieved maximum accuracy for COPD is 76% but the sensitivity is 45%. This type of autonomous system for real-time evaluation of patient’s condition has the potential to improve individual health through continual monitoring and self-management, as well as improve the health status of the overall Smart and Connected Community (SCC).
dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.
Siddiqui, Tasnuba, "Retrospective Analysis for Severity Classification of Chronic Obstructive Pulmonary Disease and Asthma with Heart Rate and SpO2" (2018). Electronic Theses and Dissertations. 1834.