Development and Validation of a Multimodal Deep Learning Model Using Peripheral Oxygen Saturation and Ballistocardiography Signals for Predicting Apnea-Hypopnea Index in Obstructive Sleep Apnea

A Prospective Observational Study to Develop and Validate a Multimodal Deep Learning Model Integrating Peripheral Oxygen Saturation and Ballistocardiography Signals for the Prediction of Apnea-Hypopnea Index in Patients With Suspected Obstructive Sleep Apnea

Obstructive sleep apnea (OSA) is a common sleep disorder associated with cardiovascular, metabolic, and neurocognitive complications. The standard diagnostic test for OSA is in-laboratory polysomnography (PSG), which can be costly, labor-intensive, and inconvenient for repeated or large-scale screening. Therefore, there is a need for a convenient and non-invasive method to help identify individuals who may be at risk for OSA.

This prospective observational study aims to develop and clinically validate a multimodal deep learning model that integrates peripheral oxygen saturation (SpO₂) signals and ballistocardiography (BCG) data collected using a smart mattress system to estimate the apnea-hypopnea index (AHI). Adult participants undergoing routine overnight PSG for suspected OSA will be enrolled. During sleep, synchronized SpO₂ and BCG signals will be recorded non-invasively.

The performance of the deep learning model will be evaluated by comparing the predicted AHI values with AHI values derived from PSG. This study seeks to evaluate whether this practical, non-invasive, and scalable approach may support early identification of OSA risk and improve access to sleep disorder assessment in both clinical and home-based settings.

Study Overview

• Status: Recruiting
• Conditions: Obstructive Sleep Apnea

Detailed Description

This is a prospective observational cohort study designed to develop and validate a multimodal deep learning-based model for estimating obstructive sleep apnea (OSA) severity. Adult participants with suspected OSA who are scheduled to undergo overnight in-laboratory polysomnography (PSG) will be recruited at Fu Jen Catholic University Hospital.

During the PSG examination, participants will simultaneously undergo non-invasive physiological signal acquisition using a smart mattress system equipped with ballistocardiography (BCG) sensors, along with continuous peripheral oxygen saturation (SpO₂) monitoring. These signals will be time-synchronized with PSG recordings. No experimental intervention or alteration to standard clinical care will be performed.

Multimodal deep learning algorithms incorporating convolutional neural networks and sequence-based architectures will be developed to analyze SpO₂ and BCG signals and to estimate the apnea-hypopnea index (AHI). Model performance will be assessed by comparing predicted AHI values with PSG-derived AHI using predefined statistical metrics.

The primary objective is to evaluate the accuracy of AHI prediction using the proposed multimodal model. Secondary objectives include assessment of model discrimination for OSA severity classification and exploratory analyses of physiological signal features associated with sleep-disordered breathing. All analyses will be conducted using de-identified data. This study does not involve U.S. FDA-regulated drugs or devices and is not conducted under an investigational new drug application or investigational device exemption.

• Study Type: Observational
• Enrollment (Estimated): 100

Contacts and Locations

• Study Contact: Name: Ke-Yun Chao Principal Investigator; Phone Number: +886-905-301-879; Email: C00152@mail.fjuh.fju.edu.tw

Study Locations

• Taiwan
  • New Taipei City
    • New Taipei City, New Taipei City, Taiwan, 24352
      • Recruiting
      • Fu Jen Catholic University Hospital
      • Contact: Clinical Research Coordinator; Phone Number: +886-2-2905-2000; Email: Ck_qq@hotmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 20 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Adult individuals aged 20 years or older who are referred to Fu Jen Catholic University Hospital for in-laboratory polysomnography due to suspected obstructive sleep apnea will be invited to participate. The study population includes participants with a wide range of apnea-hypopnea index values, including individuals without obstructive sleep apnea based on polysomnography results.

Description

Inclusion Criteria:

• Adults aged 20 years or older.
• Individuals referred for in-laboratory polysomnography due to suspected obstructive sleep apnea.
• Able and willing to provide informed consent.

Exclusion Criteria:

• Inability to provide informed consent.
• Presence of conditions that may interfere with sleep signal acquisition, as determined by the investigator.
• Prior diagnosis of sleep disorders other than obstructive sleep apnea that could confound study results.

Study Plan

How is the study designed?

Design Details

• Observational Models: COHORT
• Time Perspectives: PROSPECTIVE

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Adults With Suspected Obstructive Sleep Apnea; This cohort includes adult participants with suspected obstructive sleep apnea who are scheduled to undergo overnight in-laboratory polysomnography. All participants will receive standard clinical polysomnography while simultaneously undergoing non-invasive physiological signal acquisition using a smart mattress system and peripheral oxygen saturation monitoring. No experimental intervention or treatment assignment is performed.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Mean absolute error of apnea-hypopnea index estimation	Mean absolute error (MAE) will be calculated as the average absolute difference between the apnea-hypopnea index (AHI) predicted by the multimodal deep learning model using peripheral oxygen saturation (SpO2) and ballistocardiography (BCG) signals collected during home sleep monitoring and the AHI measured by in-laboratory polysomnography (PSG). The analysis will include participants with evaluable paired PSG and home monitoring data. MAE will be reported in events per hour, with lower values indicating better predictive performance.	Two overnight assessments per participant: one in-laboratory polysomnography night and one subsequent home sleep monitoring night.

Collaborators and Investigators

• Sponsor: Fu Jen Catholic University
• Collaborators: Fu Jen Catholic University Hospital

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2026
• Primary Completion (Estimated): June 30, 2028
• Study Completion (Estimated): June 30, 2028

Study Registration Dates

• First Submitted: February 9, 2026
• First Submitted That Met QC Criteria: November 3, 2026
• First Posted (Actual): November 6, 2026

Study Record Updates

• Last Update Posted (Actual): November 6, 2026
• Last Update Submitted That Met QC Criteria: November 3, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Obstructive Sleep Apnea; Peripheral Oxygen Saturation; Deep Learning; Apnea-Hypopnea Index; Ballistocardiography; Home Sleep Monitoring
• Additional Relevant MeSH Terms: Nervous System Diseases; Respiratory Tract Diseases; Respiration Disorders; Sleep Wake Disorders; Apnea; Sleep Disorders, Intrinsic; Dyssomnias; Sleep Apnea Syndromes; Sleep Apnea, Obstructive
• Other Study ID Numbers: FJUH115580

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

IPD Plan Description

Individual participant data will not be shared publicly.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No