A Mixed-Methods Study on Self-Management Support: Exploring Patient and Healthcare Professional Perspectives Alongside a Health Condition Recommender System

Enabling individuals with asthma to proactively identify signs of worsening condition and respond promptly is pivotal in mitigating the risk of asthma attacks. The fusion of smartphones, intelligent monitoring tools, and machine learning holds the potential to amplify self-management capabilities by anticipatively predicting asthma attacks and delivering personalized guidance. In this pursuit, our objective is to conceptualize and evaluate the viability of an asthma attack prediction system rooted in data harnessed from diverse smart devices. This approach presents a comprehensive mixed-methods study that investigates patient self-management support by integrating insights from patients and healthcare professionals, alongside the implementation of an IoT device, cloud infrastructure, and deep learning techniques.The study aims to understand the challenges and needs of patient self-management while leveraging contemporary technological advancements. Through qualitative interviews, focus groups, surveys, and experiments, the study captures diverse perspectives and evaluates the effectiveness of a health condition recommender system. The integration of an IoT device enables real-time data collection, which is processed using cloud infrastructure and deep learning models to provide personalized recommendations for self-management. The study's findings shed light on enhancing patient self-management through a multidimensional approach that combines human insights with cutting-edge technology.