Obstructive Sleep Apnea, Obstructive Sleep Apnea-hypopnea
Conditions
Brief summary
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.
Detailed description
Patients undergoing Level 1 polysomnography are equipped with the CART-I PLUS device, for collecting polysomnography data alongside concurrent photoplethysmography (PPG) signals. The collected data is categorized into apnea, hypopnea, and normal segments based on the polysomnography results. Utilizing the PPG and accelerometer (ACC) signals from the CART-I PLUS, metrics such as SaO2 (oxygen saturation), respiratory rate, heart rate (HR), heart rate variability (HRV), and body movement are calculated for each segment. These metrics, along with the PPG and ACC signals, are then used to develop a deep learning model that classifies the segments into apnea, hypopnea, or normal. Participants are divided into training and validation sets. The deep learning model is trained on data from the participants in the training set, and its performance is evaluated using the validation set. The algorithm is constructed using convolutional neural networks (CNN), recurrent neural networks (RNN), attention mechanisms, and other advanced techniques recognized for their efficacy in classification tasks, specifically for identifying apnea, hypopnea, and normal segments.
Interventions
DEVICECART-I plus
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.
DEVICEPolysomnography
In polysomnography, the following data are collected: Electrocardiogram (ECG), Electroencephalogram (EEG), Electromyogram (EMG), Electrooculogram (EOG), Oxygen Saturation (SpO2) Respiratory Analysis, Body Position Monitoring
Sponsors
Gangnam Severance Hospital
Sky Labs
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DIAGNOSTIC
Masking
NONE
Eligibility
Sex/Gender
FEMALE
Age
19 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
Patients scheduled for Level 1 polysomnography at a sleep center who meet all of the following criteria: * Aged 19 years or older * Have listened to and understood a thorough explanation of the clinical study and voluntarily agreed to participate
Exclusion criteria
* 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)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of the algorithm and the 95% confidence interval | 11 hours | 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. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy and 95% confidence intervals for each interval | 11 hours | 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. |
Countries
South Korea
Contacts
Primary ContactGerrard Kim
Backup ContactYujung Kang
Outcome results
None listed