Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Obstructive sleep apnea syndrome (OSA) is marked by repeated upper airway obstructions during sleep, affecting approximately 14% of men and 5% of women aged 30-70 years.
However, precise clinical prediction tools for selecting optimal treatment strategies are lacking. This study aims to develop an automated treatment clustering system using artificial intelligence to classify patients based on etiology into (i) anatomical factors, (ii) reduced muscle responsiveness, and (iii) other non-anatomical factors. This system will analyze physiological sleep assessments, such as electromyography (EMG) and pneumotachographs, from a retrospective polysomnography (PSG) database. Cross-validation will be conducted on new OSA patients undergoing various management strategies, including surgical intervention, CPAP therapy, and oropharyngeal training (delivered face-to-face or via telerehabilitation). This system aims to enhance clinicians' ability to predict treatment success rates and improve patient outcomes.
Backgrounds:
Obstructive sleep apnea syndrome (OSA) is marked by repeated upper airway obstructions during sleep, affecting about 14% of men and 5% of women aged 30-70 years. The etiology of OSA is divided into anatomical and non-anatomical factors. Anatomical factors include upper airway narrowing or collapse, while non-anatomical factors encompass reduced muscle responsiveness, low arousal threshold, and high loop gain. Anatomical issues can be managed using surgical interventions or dental appliances. Non-anatomical issues like low arousal threshold and high loop gain may require pharmacological treatment or oxygen therapy. The genioglossus (GG) muscle's activity, crucial during sleep, is insufficient in about 30% of OSA patients. Regular oropharyngeal muscle exercises can reduce OSA severity and related symptoms.
However, precise clinical prediction tools for selecting optimal treatment strategies are lacking, and research on telerehabilitation for OSA patients is insufficient. This study aims to develop an automated treatment clustering system using artificial intelligence to classify patients based on etiology into: (i) anatomical factors, (ii) reduced muscle responsiveness, and (iii) other non-anatomical factors. This system will analyze physiological sleep assessments from a retrospective polysomnography (PSG) database. Cross-validation will be conducted on new OSA patients undergoing various management strategies, including surgical intervention, CPAP therapy, and oropharyngeal training (delivered face-to-face or via telerehabilitation).
Methods:
The automated treatment clustering system employs artificial intelligence to classify patients into etiological groups: (i) anatomical factors like upper airway narrowing or collapse; (ii) non-anatomical factors such as reduced muscle responsiveness; and (iii) other non-anatomical factors. The classification relies on analyzing multiple physiological sleep assessments, including electromyography (EMG) and pneumotachographs, from a retrospective PSG database. The system will undergo cross-validation with novel OSA patients, who will be screened based on inclusion and exclusion criteria and provide consent.
During the cross-validation phase, the OSA patients will undergo various assessments, including polysomnography, sleep-related questionnaire, drug-induced sleep endoscopy (DISE), computed tomography (CT) scans, functional magnetic resonance imaging (fMRI), tongue muscle strength and endurance tests, and mental state evaluations. Pre- and post-treatment measurements will be conducted. CT scans and DISE will assess anatomical structures before and after treatment, while fMRI will examine brain activation status. Muscle strength and endurance tests will evaluate the responsiveness level of tongue muscle before and after intervention.
The automated treatment clustering system, utilizing machine learning, will determine the phenotype of each case based on PSG, CT, sleep endoscopy, fMRI, and tongue strength and endurance results. These results will aid clinicians in categorizing patients and predicting treatment success rates. Treatment decisions will involve collaboration between physicians and patients, considering clinical expertise and patient preferences.
Participants classified as upper airway narrowing or collapse due to anatomical factors by the phenotyping system will be recommended for surgical management. For patients with reduced muscle responsiveness, a 12-week program of oropharyngeal muscle training is recommended. This training will be administered in two modes: face-to-face sessions and telerehabilitation. Each session will last 45-60 minutes, with participants attending face-to-face sessions in the lab or online classes (telerehabilitation) 1-3 days per week. Both groups will be instructed to perform additional oropharyngeal exercises at home. Patients not fitting these groups will use CPAP therapy, the gold standard for OSA management. During the treatment period, participants from all groups will have regular follow-ups to assess potential risks. Each group is expected to include 50 cases. After six months of treatment, the apnea-hypopnea index will be collected based on polysomnography to evaluate the success rates, comparing them to the predicted value analyzed using the phenotyping system.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Control Group | Sham Comparator | Participants who are unwilling to undergo surgery, use a mandibular advancement device, utilize continuous positive airway pressure (CPAP) devices, or undergo oropharyngeal training. They will receive sleep hygiene education. |
|
| Surgical Intervention | Experimental | Remove excessive soft tissue from the base of the tongue, soft palate, and/or tonsil. |
|
| Oropharyngeal Training (face-to-face) | Experimental | Participants will attend face-to-face oropharyngeal training sessions with a therapist in the lab, each lasting 45-60 minutes, 1-2 times per week, over a 12-week intervention period. |
|
| Oropharyngeal Training (telerehabilitation ) | Experimental | Participants will attend online oropharyngeal training (telerehabilitation) sessions with a therapist, each lasting 45-60 minutes, 1-2 times per week, over a 12-week intervention period. |
|
| Continuous Positive Airway Pressure | Experimental | Participants will use Continuous Positive Airway Pressure (CPAP) throughout the intervention period. |
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Control Group | Other | sleep hygiene education |
| |
| Surgical Intervention |
| Measure | Description | Time Frame |
|---|---|---|
| Apnea-hypopnea -index | The apnea-hypopnea index will be obtained from the overnight Polysomnography (PSG) study. PSG will be performed in the sleep center of National Cheng Kung University Hospital. Less than 5 events/hour indicates normal; AHI between 5-14 events/hour indicates mild Obstructive Sleep Apnea(OSA); AHI between 15-30 events/hour indicates moderate OSA; and AHI more than 30 events/hour indicates severe OSA. | Baseline, 12 weeks, 24 weeks post intervention |
| Measure | Description | Time Frame |
|---|---|---|
| Tongue muscle strength | The maximal muscle strength of genioglossus muscles using The Iowa Oral Performance Instrument (IOPI) system, model 2.2 (Northwest, Co., LLC, Carnation, WA, USA) (kPa) | Baseline, 12 weeks, 24 weeks post intervention |
| Tongue muscle endurance |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Jun-Hui Ong, MS | Contact | +886-9-37839992 | junhui.ong611@gmail.com | |
| Ching-Hsia Hung, PhD | Contact | +886-6-2353535 | 5939 | chhung@mail.ncku.edu.tw |
| Name | Affiliation | Role |
|---|---|---|
| Ching-Hsia Hung, PhD | National Cheng Kung University | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| National Cheng Kung University Hospital | Recruiting | Tainan | 701 | Taiwan |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 41734638 | Derived | Ong JH, Liu CY, Chooi MH, Lin CY, Hung CH. Effectiveness of supervised multilevel oropharyngeal rehabilitation via videoconference on tongue function and apnea severity in obstructive sleep apnea: Quasi-experimental study. Rehabilitacion (Madr). 2026 Jan-Mar;60(1):100963. doi: 10.1016/j.rh.2026.100963. Epub 2026 Feb 23. |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
|
| Procedure |
Surgical Intervention includes uvulopalatopharyngoplasty (UPPP) and transoral robotic surgery (TORS). UPPP involves the removal of the uvula and tonsils, while TORS consists of the removal of the uvula, tonsils, and adipose tissue at the base of the tongue. |
|
| Oropharyngeal Training (face-to-face) | Other | Participants will attend face-to-face oropharyngeal training sessions with a therapist in the lab, each lasting 45-60 minutes, 1-2 times per week, over a 12-week intervention period. |
|
| Oropharyngeal Training (telerehabilitation) | Other | Participants will attend online oropharyngeal training (telerehabilitation) sessions with a therapist, each lasting 45-60 minutes, 1-2 times per week, over a 12-week intervention period. |
|
| Continuous Positive Airway Pressure | Device | Participants will use Continuous Positive Airway Pressure (CPAP) throughout the intervention period. |
|
The endurance of the genioglossus muscles using The Iowa Oral Performance Instrument (IOPI) system, model 2.2 (Northwest, Co., LLC, Carnation, WA, USA) (in seconds). |
| Baseline, 12 weeks, 24 weeks post intervention |
| Pharyngeal Airway Volume | Computer Tomography (CT) will be performed. The pharyngeal airway volume will be calculated from the hard palate to the epiglottis and the data will be presented in cm^3. The minimum score is 0 and a higher score indicates greater in pharyngeal airway volume. | Baseline, 12 weeks, 24 weeks post intervention |
| Cross Section Area on the Tip of Epiglottis | Computer Tomography (CT) will be performed. Cross section area on the tip of the epiglottis was measured and the data will be presented in cm^2. The minimum score is 0 and a higher score indicates greater in the cross-sectional area of the region. | Baseline, 12 weeks, 24 weeks post intervention |
| Anterior to Posterior Distance on the Tip of the Epiglottis | The distance between the anterior and posterior pharyngeal wall on the tip of the epiglottis will be measured and presented in cm. The minimal value will be 0 and the greater value indicates a greater distance between the anterior to posterior in this area. | Baseline, 12 weeks, 24 weeks post intervention |
| Lateral Distance on the Tip of Epiglottis | The distance between the lateral distance on the tip of the epiglottis will be measured and presented in cm. The minimal value will be 0 and the greater value indicates a greater distance between the lateral wall. | Baseline, 12 weeks, 24 weeks post intervention |
| Drug-induced Sleep Endoscopy (DISE) | The level of obstruction, the degree of obstruction, and the configuration of the obstructive will be identified through the drug-induced sleep endoscopy. The degree of obstruction ranged from 0 to 2. 0: no obstruction; 1: partial obstruction; 2: complete obstruction. | Baseline, 12 weeks, 24 weeks post intervention |
| Sleep Quality | Sleep quality will be measured using Pittsburgh Sleep Quality Index (PSQI).The total score ranges from 0 to 21 with a higher total score equal to or more than 5 indicating worse sleep quality. | Baseline, 12 weeks, 24 weeks post intervention |
| Daytime sleepiness level | Epworth Sleepiness Score(ESS) will be used to measure the daytime sleepiness of OSA patients. The total score of ESS range from 0-24. A score greater than 10 indicates greater daytime sleepiness. | Baseline, 12 weeks, 24 weeks post intervention |
| Activation of brain | Functional MRI (fMRI) will be conducted by psychiatrists to evaluate the activation of brain areas in a relaxed state, including the amygdala, hippocampus, insula, locus coeruleus, ventromedial prefrontal cortex, mammillary bodies, and lateral hypothalamus. | Baseline, 12 weeks, 24 weeks post intervention |
| Mental State Assessment | Using the Hospital Anxiety and Depression Scale (HADS) to assess subjects' mood over the past week. HADS. Each subscale has a maximum score of 21, with higher scores indicating greater anxiety or depression. | Baseline, 12 weeks, 24 weeks post intervention |
| ID | Term |
|---|---|
| D020181 | Sleep Apnea, Obstructive |
| ID | Term |
|---|---|
| D012891 | Sleep Apnea Syndromes |
| D001049 | Apnea |
| D012120 | Respiration Disorders |
| D012140 | Respiratory Tract Diseases |
| D020919 | Sleep Disorders, Intrinsic |
| D020920 | Dyssomnias |
| D012893 | Sleep Wake Disorders |
| D009422 | Nervous System Diseases |
Not provided
Not provided
| ID | Term |
|---|---|
| D035061 | Control Groups |
| D013514 | Surgical Procedures, Operative |
| D000069350 | Telerehabilitation |
| D045422 | Continuous Positive Airway Pressure |
| ID | Term |
|---|---|
| D015340 | Epidemiologic Research Design |
| D004812 | Epidemiologic Methods |
| D008919 | Investigative Techniques |
| D012107 | Research Design |
| D008722 | Methods |
| D012046 | Rehabilitation |
| D000359 | Aftercare |
| D003266 | Continuity of Patient Care |
| D005791 | Patient Care |
| D013812 | Therapeutics |
| D006296 | Health Services |
| D005159 | Health Care Facilities Workforce and Services |
| D017216 | Telemedicine |
| D003695 | Delivery of Health Care |
| D010346 | Patient Care Management |
| D006298 | Health Services Administration |
| D011175 | Positive-Pressure Respiration |
| D012121 | Respiration, Artificial |
| D058109 | Airway Management |
| D012138 | Respiratory Therapy |
Not provided
Not provided