Validation of Belun Ring Gen3 Deep Learning Algorithms With Subxiphoid Body Sensor

Belun Ring Gen3 Deep Learning Algorithms With Subxiphoid Body Sensor: Exploring Its Diagnostic Capabilities for Sleep Disordered Breathing With Analysis of Biomarker Dynamics

Hypothesis: BR's Gen3 DL algorithms, combined with its subxiphoid body sensor, can accurately diagnose OSA, categorize its severity, identify REM OSA and supine OSA, and detect central sleep apnea (CSA).

Primary Objective:

To rigorously evaluate the overall performance of the BR with Gen3 DL Algorithms and Subxiphoid Body Sensor in assessing SDB in individuals referred to the sleep labs with clinical suspicion of sleep apnea and a STOP-Bang score > 3, by comparing to the attended in-lab PSG, the gold standard.

Secondary Objectives:

To determine the accuracy of BR sleep stage parameters using the Gen3 DL algorithms by comparing to the in-lab PSG;

To assess the accuracy of the BR arrhythmia detection algorithm;

To assess the impact of CPAP on HRV (both time- and frequency-domain), delta HR, hypoxic burden, and PWADI during split night studies;

To assess if any of the baseline HRV parameters (both time- and frequency-domain), delta heart rate (referred to as Delta HR), hypoxic burden, and pulse wave amplitude drop index (PWADI) or the change of these parameters may predict CPAP compliance;

To evaluate the minimum duration of quality data necessary for BR to achieve OSA diagnosis;

To examine the performance of OSA screening tools using OSA predictive AI models formulated by National Taiwan University Hospital (NTUH) and Northeast Ohio Medical University (NEOMED).

Study Overview

• Status: Not yet recruiting
• Conditions: Arrhythmia; Sleep-Disordered Breathing; Sleep Architecture
• Intervention / Treatment: Device: Belun Ring; Device: Belun Cor

• Study Type: Interventional
• Enrollment (Estimated): 79
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Tiffany Tsai; Phone Number: 216-844-3201; Email: tiffany.tsai2@va.gov

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Provision of signed informed consent form.
• Clinically assessed and suspicious for OSA with a STOP-Bang score ≥ 3.

Exclusion Criteria:

• Full night PAP titration study.
• On home O2, noninvasive ventilator, diaphragmatic pacing, or any form of a nerve stimulator.
• Having atrial fibrillation-flutter, pacemaker/defibrillator, left ventricular assist device (LVAD), or status post cardiac transplantation.
• Recent hospitalization or recent surgery in the past 30 days.
• Unstable cardiopulmonary status on the night of the study judged to be unsafe for sleep study by the sleep tech and/or the on-call sleep physician.

If a participant did not sleep for at least 4 hours of technically valid sleep based on the Belun Ring method for diagnostic assessments, or a minimum of 3 hours of technically valid sleep during the diagnostic phase of a split-night study, the patient will be excluded from statistical analysis.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: UH-Participant; Potential participants will be identified from patients scheduled for in-lab PSG at the two medical centers of University Hospitals

Device: Belun Ring; The Belun Ring sensor should be placed on the palmar side of the proximal phalanx of the index finger and the sensor should be placed along the radial artery such that the accuracy of the device will be minimally affected by skin color. The Ring has 7 adjustable arms for different finger sizes. Each device is reusable after thorough cleaning with an alcohol swab.; Device: Belun Cor; The "Belun Cor" body sensor accessory is composed of an accelerometer, a temperature sensor, and a lithium battery. It will be placed immediately below the xiphoid process in the upper abdomen with a medical adhesive to detect the body temperature, body posture, respiratory rate, and respiratory efforts.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Performance of diagnosing sleep disordered breathing by BR's Gen3 DL algorithms	To establish mean, standard deviation, and target clinical agreement limit values for the differences in sleep-disordered breathing parameters (including AHI3%, AHI4%, REM AHI 3%, REM AHI4%, Supine AHI3%, Supine AHI4%, and CAI) from the BR against PSG. To calculate the sensitivity and specificity values, along with 95% confidence intervals (CIs), for sleep-disordered breathing parameters from the BR against PSG at PSG cutoffs of 5, 15, and 30 events/h. Pearson correlation and regression analysis will be employed to assess the association between sleep-disordered breathing parameters obtained from the BR and PSG.	2 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of the BR arrhythmia-detecting algorithm	To calculate the performance metrics, including sensitivity and specificity, along with 95% CIs, for the detection of arrhythmias by BR device in comparison to assessments made by a board-certified sleep physician. The physician will review the PSG ECG signals of the subjects suspected of having significant arrhythmias during the sleep study.	3 years
Biomarker relationship analysis	Pearson correlation and regression analysis will be employed: (1) to explore the relationships between autonomic nervous system (ANS) metrics and delta HR, hypoxic burden, and pulse wave amplitude drop index (PWADI); (2) to evaluate the association between HRV, Delta HR, hypoxic burden, PWADI, CPAP adherence, sleep-disordered breathing parameters, and demographic data (including age, gender, and BMI). If data distribution assumptions are violated, the Spearman correlation will be used instead of the Pearson correlation.	3 years
Accuracy of the NTUH and NEOMED models	The investigators will compute sensitivity and specificity values, accompanied by their respective 95% CIs, for AHI3% and AHI4% from the NTUH/NEOMED models in comparison to PSG. Furthermore, the investigators will determine the ROC curve at PSG-defined cutoffs of 5, 15, and 30 events/h for both AHI3% and AHI4%.	3 years
Performance of sleep stage classification by BR's Gen3 DL algorithms	Sensitivity and specificity of the Epoch-by-Epoch (EBE) 4-stage classification (wake, deep sleep, light sleep, REM) of the BR will be compared to EBE PSG data for each stage against the combination of the other three classifications. For instance, sensitivity for detecting wake will measure the proportion of correctly classified wake epochs against the combined classifications of deep sleep, light sleep, and REM sleep. Sensitivity and specificity values, accompanied by 95% CIs, of EBE body position (supine vs. non-supine) against PSG will also be computed.	2 years
To evaluate the minimum duration of quality data necessary for OSA diagnosis	To explore the minimum number of hours needed by the BR for an accurate OSA diagnosis, sensitivity, specificity, and Matthews Correlation Coefficient (MCC) values, along with 95% CIs, will be computed for sleep-disordered breathing parameters of Belun total record time (bTRT) and belun total sleep time (bTST) with different numbers of hours (e.g., 2, 3, 4, 5, 6, 7, and 8 hours) against PSG data. In cases where varying numbers of subjects meet different bTRT and bTST criteria at different durations, resampling methods like oversampling, undersampling, bootstrapping, etc., will be employed to address data imbalances.	2 years

Collaborators and Investigators

• Sponsor: Belun Technology Company Limited
• Collaborators: University Hospitals Cleveland Medical Center
• Investigators: Principal Investigator: Ambrose A. Chiang, MD, University Hospitals Cleveland Medical Center; Principal Investigator: Susheel P. Patil, MD, University Hospitals Cleveland Medical Center; Principal Investigator: Kingman P. Strohl, MD, University Hospitals Cleveland Medical Center

Study record dates

Study Major Dates

• Study Start (Estimated): April 1, 2024
• Primary Completion (Estimated): March 31, 2026
• Study Completion (Estimated): September 30, 2027

Study Registration Dates

• First Submitted: January 15, 2024
• First Submitted That Met QC Criteria: February 2, 2024
• First Posted (Actual): February 13, 2024

Study Record Updates

• Last Update Posted (Actual): March 6, 2024
• Last Update Submitted That Met QC Criteria: March 4, 2024
• Last Verified: March 1, 2024

More Information

Terms related to this study

• Keywords: Obstructive Sleep Apnea; Photoplethysmography; Deep Learning; Wearable; Home Sleep Test; Predictive AI models
• Additional Relevant MeSH Terms: Pathologic Processes; Nervous System Diseases; Respiratory Tract Diseases; Apnea; Respiration Disorders; Sleep Disorders, Intrinsic; Dyssomnias; Sleep Wake Disorders; Sleep Apnea Syndromes; Respiratory Aspiration
• Other Study ID Numbers: STUDY20231436

Plan for Individual participant data (IPD)

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

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No