Remote Heart Monitoring: A Predictive Modeling Approach for Biomedical Signal Processing

Chen, Jiaming (2018) Remote Heart Monitoring: A Predictive Modeling Approach for Biomedical Signal Processing. Masters thesis, Northern Arizona University.

Text Chen_J_2018_Remote_heart_monitoring_predictive_approach.pdf - Published Version Download (1MB)

Abstract

Smart healthcare is an emerging field with the goal of harnessing technological advances to enhance healthcare quality. Several research projects in recent years are devoted to design of electronic devices and networking platforms to facilitate technology-based health service. One important paradigm in smart healthcare is developing tools for biomedical signal processing. Biomedical signals can directly reflect the information about patient health and therefore have been widely investigated by the research community. The essence of most signal analysis systems is to process a large training dataset and build a reference model to asses the health status of new patients. While the majority of these methods focus on improving classification performance on a collection of signals in large datasets, the predictive modeling of biomedical signals is rarely emphasized. In this work, we go one step beyond the conventional methods and intend to predict potential upcoming abnormalities before their occurrence. The approach is to build a patient-specific model and identify minor deviations from the normal signal, which can be indicative of potential upcoming significant deviations. To enable an accurate deviation analysis, a controlled nonlinear transformation is proposed to reshape the feature space into a more symmetric geometry. We applied the developed algorithms on Electrocardiogram (ECG) signals and the results confirm the effectiveness of the proposed method in predicting upcoming heart abnormalities before their occurrence. For instance, the probability of observing a specific abnormality class increases by 10% after triggering a yellow alarm of the same type. This approach is general and has the potential to be applied to a wide range of physiological signals.

Item Type:	Thesis (Masters)
Publisher’s Statement:	© Copyright is held by the author. Digital access to this material is made possible by the Cline Library, Northern Arizona University. Further transmission, reproduction or presentation of protected items is prohibited except with permission of the author.
Keywords:	biomedical signal processing; ECG signals; nonlinear transformation; Predictive modeling; smart health
Subjects:	Q Science > QM Human anatomy R Medicine > RB Pathology
MeSH Subjects:	E Analytical,Diagnostic and Therapeutic Techniques and Equipment > E01 Diagnosis E Analytical,Diagnostic and Therapeutic Techniques and Equipment > E05 Investigative Techniques
NAU Depositing Author Academic Status:	Student
Department/Unit:	Graduate College > Theses and Dissertations College of Engineering, Informatics, and Applied Sciences > School of Informatics, Computing, and Cyber Systems
Date Deposited:	22 Apr 2021 18:17
URI:	http://openknowledge.nau.edu/id/eprint/5273

Actions (login required)

IR Staff Record View

Downloads