Diagnosis of Cardiac Disease and Panic Attacks : Through Wearable ECG Monitoring (Preprint)

BACKGROUND Wearable devices are increasingly important in mental health, monitoring physiological signals like ECG and HRV that reflect autonomic nervous system activity. While extensively researched for heart disease prediction, studies on predicting panic attacks are in early stages. Challenges include data collection difficulties, quantifying psychological factors, and analyzing different panic attack patterns. OBJECTIVE To propose strategies for improving panic attack prediction using wearable devices, review methods that precedent studies accomplished in heart disease prediction, and addressing challenges in data collection, model development, and ethical considerations. METHODS We propose a robust data collection and preprocessing protocol using wearable devices for long-term ECG and HRV monitoring. Also, we propose a comprehensive prediction model integrating both physiological signals and psychological factors (stress, anxiety, sleep patterns). Finally, we propose strict data privacy measures and ethical guidelines for handling sensitive personal information. RESULTS In this paper, we propose an integration of psychological factors with physiological data for a more holistic prediction model. Implementation of ethical data collection practices, including explicit user consent and anonymized data management. CONCLUSIONS This approach offers a practical and scalable strategy for predicting panic attacks using wearable devices. It has the potential to improve the quality of life for individuals with panic disorders and introduce a new paradigm for preventive mental health management. The proposed service is expected to contribute significantly to the field of mental health care.