Perspectivas actuales sobre el Síndrome de Apnea Obstructiva Del Sueño Revisión sistemática
Abstract
El Síndrome de apnea obstructiva del sueño (SAOS) plantea graves riesgos para la salud, motivo por el cual su detección precoz es crucial para un tratamiento eficaz. Objetivo: Este trabajo pretende analizar el potencial de la inteligencia artificial (IA) en la detección del SAOS, utilizando específicamente los datos de polisomnografía. Método: Para tal fin, se llevó a cabo una revisión bibliográfica mediante una búsqueda exhaustiva de la literatura científica relacionada con el SAOS y su diagnóstico. Resultados: De acuerdo a los estudios analizados, los modelos de IA predicen con precisión el riesgo de SAOS. Los métodos de aprendizaje automático resultan prometedores en la revisión de sonidos de ronquidos e imágenes faciales para el diagnóstico del SAOS. Conclusión: La tecnología basada en IA mejora el proceso de detección del SAOS mediante métodos no invasivos y eficientes. La incorporación de la IA a múltiples enfoques diagnósticos proporciona una estrategia integral para el diagnóstico precoz del SAOS. Sin embargo, aún es necesaria una mayor validación en diversas poblaciones.
Obstructive sleep apnea syndrome (OSAS) poses serious health risks, which is why its early detection is crucial for effective treatment. Objective: This work aims to analyze the potential of artificial intelligence (AI) in the detection of OSAS, specifically using polysomnography data. Method: For this purpose, a bibliographic review was carried out through an exhaustive search of the scientific literature related to OSAS and its diagnosis. Results: According to the studies analyzed, AI models accurately predict the risk of OSA. Machine learning methods show promise in reviewing snoring sounds and facial images for OSA diagnosis. Conclusion: AI-based technology improves the OSAS detection process through non-invasive and efficient methods. Incorporating AI into multiple diagnostic approaches provides a comprehensive strategy for early diagnosis of OSAS. However, further validation in various populations is still necessary.
Obstructive sleep apnea syndrome (OSAS) poses serious health risks, which is why its early detection is crucial for effective treatment. Objective: This work aims to analyze the potential of artificial intelligence (AI) in the detection of OSAS, specifically using polysomnography data. Method: For this purpose, a bibliographic review was carried out through an exhaustive search of the scientific literature related to OSAS and its diagnosis. Results: According to the studies analyzed, AI models accurately predict the risk of OSA. Machine learning methods show promise in reviewing snoring sounds and facial images for OSA diagnosis. Conclusion: AI-based technology improves the OSAS detection process through non-invasive and efficient methods. Incorporating AI into multiple diagnostic approaches provides a comprehensive strategy for early diagnosis of OSAS. However, further validation in various populations is still necessary.
Description
Vol. 47, No. 2