Clinical Research Directory
Browse clinical research sites, groups, and studies.
Multimodal Deep Learning Model for Predicting the Apnea-Hypopnea Index in Obstructive Sleep
Sponsor: Fu Jen Catholic University
Summary
This study aims to develop a multimodal deep learning model that integrates noninvasive signals to predict the severity of obstructive sleep apnea. By establishing a clinically viable and user-friendly monitoring tool, the study seeks to enhance early screening accessibility and support the development of home-based sleep care systems.
Official title: A Multisensor Deep Neural Framework Combining Digital Auscultation, Oxygen Saturation, and Motion Data to Estimate the Apnea-Hypopnea Index in Obstructive Sleep Apnea
Key Details
Gender
All
Age Range
30 Years - 75 Years
Study Type
OBSERVATIONAL
Enrollment
150
Start Date
2025-09-05
Completion Date
2026-07-31
Last Updated
2026-03-05
Healthy Volunteers
No
Interventions
electronic stethoscope
digital device amplifying and recording cardiopulmonary sounds
fingertip pulse oximeter
a small device placed on the finger to measure blood oxygen saturation (SpO₂) and pulse rate noninvasively.
pressure-sensing mattresses
using ballistocardiography (BCG) for monitoring respiration and heart rate
Locations (1)
Fu Jen Catholic University Hospital, Fu Jen Catholic University
New Taipei City, Taiwan