Back to search

Georgia Institute of Technology

Advancing Pulmonary Monitoring Technologies in Acute Care Settings using Wearable Multimodal Sensing, Signal Processing, and Machine Learning

Abstract

dc:description.abstract

Millions of adults and children around the world experience respiratory distress as a result of pulmonary and extrapulmonary pathologies, such as asthma and heart failure (HF). A hallmark of these conditions is the acute worsening of respiratory symptoms, prompting admission to an acute care facility. Yet, existing pulmonary monitoring technologies in these settings remain limited. In particular, the lack of temporal resolution to capture the rapidly changing physiology is a critical limitation to improving titration of care. This dissertation describes wearable multimodal sensing hardware validation and biosignal processing efforts to enable continuous pulmonary monitoring in clinical and acute care settings. Toward this goal, we describe our efforts to evaluate the feasibility of wearable multimodal sensing in such settings. We then examine physiological markers derived from the combination of transthoracic electrical bioimpedance (BioZ) and respiratory sounds signals and elucidate their value for quantifying the physiologic manifestations of acute respiratory deterioration in a clinical setting. Through the research described, we make the following key contributions. First, we demonstrated the feasibility of obtaining simultaneous high-quality lung sounds (LS) and impedance pneumography (IP) data, and BioZ-derived fluid surrogates in patients hospitalized with acute decompensated HF via wearable multimodal sensing. We then validated transthoracic electrical BioZ analysis for continuous and simultaneous respiratory waveform estimation and fluid quantification during acute deterioration in a pig model of pleural effusion. Second, we designed and validated signal processing pipelines to derive multimodal physiological markers from the combination of IP and LS signals. Finally, we elucidated biomarkers derived thereof for quantifying the physiological manifestations of acute asthma in children admitted to the pediatric intensive care unit. This work presents a step towards continuous pulmonary monitoring in clinical and acute care settings, which can provide clinicians with real-time physiological information that may ultimately improve understanding of diseases and titration of care in the future.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Electrical and Computer Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Sanchez-Perez, Jesus Antonio
Advisor dc:contributor.advisor
  • Inan, Omer T.
Committee members dc:contributor.committeemember
  • Davenport, Mark
  • Kamaleswaran, Rishikesan
  • Hahn, Jin-Oh
  • Lin, Yingyan

Subjects

dc:subject × 13

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75707

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Sanchez-Perez, Jesus Antonio. Advancing Pulmonary Monitoring Technologies in Acute Care Settings using Wearable Multimodal Sensing, Signal Processing, and Machine Learning. Doctoral thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/75707