Título del libro:
Título del capítulo: Performance of Machine Learning Models for OSA Detection Based on ECG Signal
VICENTE BORJA RAMIREZ; MARTHA GUADALUPE TORRES FRAGA;
Autores externos:
Idioma:
Año de publicación:
2025
Palabras clave:
Adversarial machine learning; Contrastive Learning; Diseases; Machine learning; Medical education; Patient treatment; Sleep research; ECG signals; Educational innovations; High educations; Machine learning models; Machine-learning; Obstructive sleep apnea; Performance; Sleep apnea detection; Sleep apnoea diagnosis; Sleep disorders; Electrocardiography
Resumen:
Obstructive Sleep Apnea (OSA) stands out as a prevalent sleep disorder typically identified through Polysomnography. While this study serves as the golden standard for its diagnosis, it is hindered by its time-consuming nature, high costs, and the limited availability of specialized centers, leading to a reduced number of diagnosed patients. Addressing this challenge necessitates the development of more costeffective and time-efficient solutions, facilitating broader and swifter diagnosis and treatment. Currently, there are methods that enable diagnosis and auto-diagnosis of the disease utilizing body signal monitoring; however, they often lack a focus on screening critical parameters with the most effective predictive models. For that reason, the proposed solution seeks to fill this gap, integrating seamlessly into current clinical practices to provide a rapid pre-diagnosis tool for a larger patient population. Implementation of this solution by healthcare providers could significantly reduce waiting lists for OSA diagnosis, ensuring timely interventions for affected individuals. Besides, for education purposes, it can be useful in the conceptualization of pre-diagnosis devices involving ML models and databases. Furthermore, by making OSA diagnosis research more accessible, this proposal lays the groundwork for future investigations and contributes to the overall advancement of knowledge in the field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Entidades citadas de la UNAM:
ISBN:
9783031824746
Editorial:
Springer Science and Business Media Deutschland GmbH
