Abstract

The development of an integrated emergency alert system for asthmatic patients hinges upon overcoming critical data quality challenges inherent in consumer-grade wearable technology. This report surveys the foundational science and engineering required, synthesizing methodologies from cardiovascular monitoring (Atrial Fibrillation (AF) and Out-of-Hospital Cardiac Arrest (OHCA) detection) to address the unique difficulties posed by respiratory signal acquisition. The ubiquitous Photoplethysmography (PPG) technology, while reliable for heart rate (HR) estimation (yielding 99.2% usable data during monitoring), fails critically when tasked with continuous respiratory rate (RR) extraction, offering only 17.6% usable data in ambulatory settings. This technical limitation mandates a paradigm shift: predictive models must pivot from direct RR measurement to highly reliable surrogate markers, primarily Heart Rate Variability (HRV), which captures stress and autonomic imbalance, correlated precursors to exacerbation. Advanced signal processing frameworks, such as TROIKA, demonstrate the ability to achieve high HR fidelity (2.34 beats per minute average absolute error) even during intensive motion, setting a benchmark for required robustness. Architecturally, the system must employ a tiered alert model, incorporating machine learning prediction, immediate physiological crisis detection, a user-cancellation mechanism derived from OHCA systems, and integration with telehealth services, which have proven critical for maintaining patient adherence and improving asthma outcomes. Success requires resolving the technical disparity in sensor quality and establishing a user-centric design that mitigates anxiety and ensures long-term engagement.

References

• Global Asthma Network, "The Global Asthma Report 2014," Auckland, New Zealand, 2014.
• World Health Organization (WHO), "Asthma: Key facts," 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/asthma.
• F. E. Ozoh et al., "The Prevalence of Asthma and Allergic Rhinitis in Nigeria: A Nationwide Survey Among Children, Adolescents and Adults," PLoS ONE, vol. 14, no. 9, p. e0222281, Sep. 2019.
• Institute for Health Metrics and Evaluation (IHME), "Global Burden of Disease Study 2019 (GBD 2019) Results," Seattle, WA, 2020.
• R. Dhruve and T. Jackson, "Assessing Adherence to Inhaled Therapies in Asthma and Electronic Monitoring Devices," Journal of Asthma and Allergy, vol. 15, pp. 1133–1145, 2022.
• M. Kumar et al., "Asthma Prediction Using Machine Learning," International Journal of Computer Applications, vol. 183, no. 43, pp. 24–30, 2021.
• S. Bhat et al., "Machine Learning-Based Asthma Risk Prediction Using IoT and Smartphone Applications," IEEE Access, vol. 9, pp. 113115–113126, 2021.
• L. Lin et al., "Telehealth Delivery of Adherence and Medication Management System Improves Outcomes in Inner-City Children with Asthma," Pediatric Pulmonology, vol. 55, no. 6, pp. 1362–1370, 2020.
• E. Indriani et al., "Design of Asthma Detection Devices Through Heart Rate and Oxygen Saturation," in Proc. International Conference on Computer Science and Information Technology (ICoSNIKOM), 2020.
• S. Hakizimana et al., "Current Technological Advancement in Asthma Care," Journal of Personalized Medicine, vol. 14, no. 2, p. 158, 2024.
• O. Cevhertas et al., "Advances and Recent Developments in Asthma in 2020," Allergy, vol. 75, no. 12, pp. 3124–3146, 2020.
• H. Sridharan, "Sensor Data Streams Correlation Platform for Asthma Management," M.S. thesis, Dept. Comput. Sci., Univ. Maryland, College Park, MD, 2018.
• S. Joo et al., "Increasing the Accuracy of the Asthma Diagnosis Using an Operational Definition for Asthma and a Machine Learning Method," Scientific Reports, vol. 13, no. 1, p. 10452, 2023.
• K. Tsang et al., "Home Monitoring with Connected Mobile Devices for Asthma Attack Prediction with Machine Learning," ERJ Open Research, vol. 9, no. 3, 2023.
• A. Venkataramanan et al., "Determination of Personalized Asthma Triggers from Multimodal Sensing and a Mobile App: Observational Study," JMIR mHealth and uHealth, vol. 6, no. 11, p. e11073, 2018.
• S. Lee et al., "A Wearable Stethoscope for Accurate Real-Time Lung Sound Monitoring and Automatic Wheezing Detection Based on an AI Algorithm," Sensors, vol. 23, no. 4, p. 1956, 2023.
• S. Aulia et al., "Optimization of the Electronic Nose Sensor Array for Asthma Detection Based on Genetic Algorithm," Diagnostics, vol. 13, no. 5, p. 864, 2023.
• T. Zhang et al., "Diagnosis of Asthma Based on Routine Blood Biomarkers Using Machine Learning," Computational Intelligence and Neuroscience, vol. 2020, Art. no. 8841002, May 2020.
• Z. Zhang, Z. Pi, and B. Liu, "TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise," IEEE Transactions on Biomedical Engineering, vol. 62, no. 2, pp. 522–531, Feb. 2015.