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.
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.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DIAGNOSTIC
Masking
NONE
Enrollment
107
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.
In polysomnography, the following data are collected: Electrocardiogram (ECG), Electroencephalogram (EEG), Electromyogram (EMG), Electrooculogram (EOG), Oxygen Saturation (SpO2) Respiratory Analysis, Body Position Monitoring
Gangnam Severance Hospital
Seoul, South Korea
RECRUITINGAccuracy 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
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
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.