Investigating sensor-based interventions to support patient adherence to inhalation therapy

Abstract

Patient adherence to inhalation therapy for chronic respiratory conditions, specifically asthma and Chronic Obstructive Pulmonary Disease (COPD) remains a persistent challenge in healthcare, undermining treatment efficacy and leading to worsened health outcomes and increased costs. This thesis investigates the potential of sensor-based interventions, guided by Human Factors Engineering (HFE) principles, to improve patient adherence in these specific chronic respiratory conditions. By integrating real-time monitoring technologies and personalized feedback mechanisms, the research aims to design and evaluate systems that better support asthma and COPD patients in managing their inhalation therapy.
The thesis begins by establishing the theoretical foundations of patient adherence, sensor technologies, and the HFE framework (Chapter 2). It also outlines the research methodologies, with an emphasis on user-centered design approaches tailored to inhalation therapy for asthma and COPD (Chapter 3). As part of this structured, multi-phase approach, key factors influencing adherence—such as emotional experiences, environmental conditions, and cultural beliefs—are identified through semi-structured interviews within the HFE framework (Chapter 4). These insights inform the design of the XIAOXI system through participatory workshops (Chapter 5), and its development, which integrates multiple sensors to monitor patients' physiological conditions, inhaler usage, and environmental factors in real time (Chapter 6). The system’s usability and effectiveness are evaluated, and machine learning models are applied to classify adherence behaviors based on the collected data (Chapter 7).
A comprehensive discussion of the key findings (Chapter 8) showcases the successful application and validation of the Patient Adherence to Inhalation Therapy Work System Model, demonstrating how the integration of HFE principles into the design significantly enhanced patient adherence in asthma and COPD. The research highlights the XIAOXI system as an innovative, sensor-based intervention that effectively combined user-centric design with personalized feedback, improving patient adherence and management of inhalation therapy in these patients. The assessment of data-driven approaches revealed that machine learning models were highly effective in classifying adherence behaviors, with emotional and environmental factors playing a crucial role. The final chapter (Chapter 9) concludes by summarizing the thesis' primary contributions and identifying avenues for future research to further improve patient adherence and outcomes in inhalation therapy for asthma and COPD.

Date of Award	15 Jul 2025
Original language	English
Awarding Institution	University of Nottingham
Supervisor	Xu Sun (Supervisor), Xinwei Wang (Supervisor), Bingjian Liu (Supervisor) & Qingfeng Wang (Supervisor)