Myoung Su Choi

assistant professor

Eulji University Hospital
Country flagSouth Korea

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (14)

Year:

2026

Year:

2026

Background and Objectives The aim of this study was to investigate the prevalence, risk factors, and possible causes of residual excessive daytime sleepiness (EDS) in patients with obstructive sleep apnea (OSA) who were treated with positive airway pressure (PAP) machines.Subjects and Method We retrospectively analyzed medical records of 108 patients diagnosed with OSA from July 2021 to July 2023. PAP compliance, the presence of EDS, and EDS risk factors were assessed using the Epworth Sleepiness Scale and telephone interviews with patients who had received PAP treatment for more than 6 months.Results The overall prevalence of residual EDS was 17.6% (19/108 patients). Among them, 8 cases (42.1%) had explainable causes such as lack of sleep, depression, and chronic diseases, while 11 cases (57.9%) had idiopathic EDS. A high depression score (odds ratio [OR]=1.159, p=0.010) and the use of PAP for less than 4 hours (OR=4.554, p=0.018) significantly increased the risk of residual EDS.Conclusion Through this study, we found that the risk factors for residual EDS in OSA patients were high depression scores and insufficient PAP usage time.

Year:

2025

Background and Objectives The purpose of this study was to determine whether smartwatch (SW) data measured over several nights at home could effectively predict obstructive sleep apnea (OSA).Subjects and Method Patients suspected of having OSA and scheduled for polysomnography (PSG) were asked to wear a SW at home for 7 nights before undergoing PSG. After obtaining the SW data, it was compared and analyzed with the PSG.Results A total 59 people including 42 OSA patients and 17 normal control were included in the study. The sensitivity and specificity for predicting apnea-hypopnea index (AHI) ≥5/h using the SW lowest oxygen saturation of 85% were 85.7% and 70.6%. The area under curve (AUC) for the receiver operating characteristic (ROC) curve was 0.901 (p<0.001). The sensitivity and specificity for predicting AHI ≥15/h using the SW lowest oxygen saturation of 82% were 80.6% and 67.9%. The AUC for the ROC curve was 0.866 (p<0.001).Conclusion This study showed that the OSA can be predicted fairly accurately using data obtained from wearing a SW for several nights in an environment similar to daily life rather than a hospital laboratory.

Year:

2025

Background and Objectives The aim of this study was to investigate the compliance and treatment effects of both rapid eye movement sleep related obstructive sleep apnea (REM_ OSA) and non-stage specific OSA (NS_OSA) patients prescribed with positive airway pressure (PAP) therapy.Subjects and Method Medical records of 223 patients diagnosed with OSA from July 2021 to March 2023 were retrospectively analyzed. Six-month PAP compliance, symptoms questionnaires were compared for 60 patients in the REM_OSA group and 163 in the NS_OSA group.Results For patients in mild NS_OSA, mild REM_OSA, moderate NS_OSA, moderate REM_ OSA, severe NS_OSA, and severe REM_OSA groups, the compliance of six-month PAP was 50.0%, 33.3% ( p =0.467), 69.6%, 58.3% ( p >0.999), 70.7%, and 0% ( p =0.023), respectively. In the NS_OSA group, PAP led to significant daytime sleepiness score improvement (7.3±3.4 to 5.7±3.6, p =0.022). In contrast, the scores for the REM_OSA group changed insignificantly (8.4±4.7 to 6.8±2.9, p =0.332).Conclusion This study revealed that PAP therapy compliance of the REM_OSA group was not lower than that of the NS_OSA group, except for the severe subgroup. However, REM_OSA was found to be less effective in improving daytime sleepiness symptoms than NS_OSA after PAP therapy.

Year:

2024

Sleep apnea has emerged as a significant health issue in modern society, with self-diagnosis and effective management becoming increasingly important. Among the most renowned methods for self-diagnosis, the STOP-BANG questionnaire is widely recognized as a simple yet effective tool for diagnosing and assessing the risk of sleep apnea. However, its sensitivity and specificity have limitations, necessitating the need for tools with higher performance. Consequently, this study aimed to enhance the accuracy of sleep apnea diagnoses by integrating machine learning with the STOP-BANG questionnaire. Research through actual cases was conducted based on the data of 262 patients undergoing polysomnography, confirming sleep apnea with a STOP-BANG score of ≥3 and an Apnea–Hypopnea Index (AHI) of ≥5. The accuracy, sensitivity, and specificity were derived by comparing Apnea–Hypopnea Index scores with STOP-BANG scores. When applying machine learning models, four hyperparameter-tuned models were utilized: K-Nearest Neighbor (K-NN), Logistic Regression, Random Forest, and Support Vector Machine (SVM). Among them, the K-NN model with a K value of 11 demonstrated superior performance, achieving a sensitivity of 0.94, specificity of 0.85, and overall accuracy of 0.92. These results highlight the potential of combining traditional STOP-BANG diagnostic tools with machine learning technology, offering new directions for future research in self-diagnosis and the preliminary diagnosis of sleep-related disorders in clinical settings.

Year:

2024

Year:

2023

Year:

2023

Year:

2023

Year:

2022

Year:

2022

Year:

2022

Year:

2021

Year:

2021

Collaborators (1)

Minsoo Kang

Professor

Eulji University

SOUTH KOREA
View details