Updating Deep Learning Algorithms for OSA Monitoring

ConditionsObstructive Sleep Apnea Obstructive Sleep Apnea-hypopnea

Trial statusRecruiting

Trial phaseNot applicable

Trial typeInterventional

Biological sexFemale

Age19+

SponsorSky Labs

About this trial

The objective is to enhance the reliability of the algorithm to match that of Level 1 polysomnography by leveraging the diverse data obtained from Level 1 polysomnography to refine the deep learning algorithm.

Eligibility criteria

This trial accepts healthy volunteers

Qualifiers

Aged 19 years or older

Have listened to and understood a thorough explanation of the clinical study and voluntarily agreed to participate

Disqualifiers

Under 19 years of age

Unable to collect normal signals during the pre-test or wearing of the CART-I PLUS device

Refuse to participate in the clinical study

Have cognitive impairments to the extent that they cannot understand the explanation of the clinical study and therefore cannot make a voluntary decision to participate (e.g., legally incompetent individuals)

Trial design

Design model

Single group

Treatments tested in this trial

CART-I plus
Device
CART-I PLUS collects signals in two ways: ECG: Utilizes the metal on the inner and outer sides as electrodes to detect subtle electrical changes resulting from the contraction and relaxation of the heart muscle. PPG: Emits LED light into the blood vessels inside the finger and collects the signal reflected by the blood flow, thereby gathering data on the pulse and functional oxygen saturation (SpO2) of arterial hemoglobin. In this clinical trial, PPG signals will be continuously collected during the polysomnography using the PPG method.
Polysomnography
Device
In polysomnography, the following data are collected: Electrocardiogram (ECG), Electroencephalogram (EEG), Electromyogram (EMG), Electrooculogram (EOG), Oxygen Saturation (SpO2) Respiratory Analysis, Body Position Monitoring

Treatment groups

107 Participants

are divided into 1 treatment group

Group A: Level 1 polysomnography patientExperimental treatment 2 interventions

Trial outcomes

Primary outcomes

Accuracy of the algorithm and the 95% confidence interval

Present the accuracy of the algorithm and the 95% confidence interval. If the lower bound of the 95% confidence interval exceeds a minimum accuracy of 0.85, it is considered clinically significant.

Time frame

11 hours

Secondary outcomes

Accuracy and 95% confidence intervals for each interval

Present the accuracy and 95% confidence intervals for each interval. Additionally, precision, recall, ROC curve, and AUC may be presented. The performance comparison between algorithms will use the bootstrap method, and a p-value less than 0.05 will be considered statistically significant.

Time frame

11 hours

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

Sky Labs

Lead sponsor

Gangnam Severance Hospital

Collaborator

Source ClinicalTrials.gov

Apply now