• Epworth questionnaire
• STOP-Bang questionnaire
• obstructive sleep apnea
• screening

• Obstructive sleep apnea
• Risk factors
• Sleep

• Sleep Apnea, Obstructive/diagnosis
• Sleep Apnea, Obstructive/pathology
• Oxygen Saturation
• Polysomnography
• Body Mass Index
• Risk
• Humans
• Male
• Female
• Adult
• Middle Aged
• Diagnostic Techniques and Procedures
• Neck/anatomy & histology
• Mouth/anatomy & histology

American Academy of Sleep Medicine guidelines suggest that clinical prediction algorithms can be used to screen patients with obstructive sleep apnea (OSA) without replacing polysomnography, the gold standard.

We aimed to identify, gather, and analyze existing machine learning approaches that are being used for disease screening in adult patients with suspected OSA.

We searched the MEDLINE, Scopus, and ISI Web of Knowledge databases to evaluate the validity of different machine learning techniques, with polysomnography as the gold standard outcome measure and used the Prediction Model Risk of Bias Assessment Tool (Kleijnen Systematic Reviews Ltd) to assess risk of bias and applicability of each included study.

Our search retrieved 5479 articles, of which 63 (1.15%) articles were included. We found 23 studies performing diagnostic model development alone, 26 with added internal validation, and 14 applying the clinical prediction algorithm to an independent sample (although not all reporting the most common discrimination metrics, sensitivity or specificity). Logistic regression was applied in 35 studies, linear regression in 16, support vector machine in 9, neural networks in 8, decision trees in 6, and Bayesian networks in 4. Random forest, discriminant analysis, classification and regression tree, and nomogram were each performed in 2 studies, whereas Pearson correlation, adaptive neuro-fuzzy inference system, artificial immune recognition system, genetic algorithm, supersparse linear integer models, and k-nearest neighbors algorithm were each performed in 1 study. The best area under the receiver operating curve was 0.98 (0.96-0.99) for age, waist circumference, Epworth Somnolence Scale score, and oxygen saturation as predictors in a logistic regression.

Although high values were obtained, they still lacked external validation results in large cohorts and a standard OSA criteria definition.

PROSPERO CRD42021221339; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=221339

• Adult
• Bayes Theorem
• Humans
• Machine Learning
• Neural Networks, Computer
• Polysomnography/methods
• Sleep Apnea, Obstructive/diagnosis

• body fat distribution
• body mass index
• obesity
• obstructive sleep apnea
• oximetry

• T32 HL007111 NHLBI NIH HHS
• Mayo Clinic
• National Institutes of Health

Background

The prevalence of obstructive sleep apnea (OSA) is high in the obese population. In this study, it was aimed to fulfill the STOP-Bang questionnaire which is a concise and easy-to-use questionnaire for OSA screening in obese patients.

Materials & methods

This is a retrospective study where the patients, who planned polysomnography, were referred to sleep clinic. Patients were screened for OSA by the STOP-Bang questionnaire. Laboratory polysomnography was performed in 275 patients. Patients with BMI ≥ 30 were taken into study. The screening test was evaluated by three different risk analysis such as, a STOP score, a STOP-Bang score and a modified STOP-Bang score. The predictive parameters (sensitivity, specificity, and positive and negative predictive values) for alternative scoring models in obese patients were analyzed.

Results

In 217 obese patients, a STOP score cutoff of 3 and a STOP-Bang score cutoff of 4 provides a better balance of sensitivity and specificity for all OSA (apnea-hypopnea index [AHI] ≥ 5). The STOP questionnaire revealed a sensitivity of 87.9% and a positive predictive value of 99.5% for patients with all OSA (p: 0.005). The STOP-Bang scoring model revealed a sensitivity of 95.3% and a positive predictive value of 99.5% for patients with all OSA (p < 0.001). The modified STOP-Bang scoring revealed a sensitivity of 95.8% and a positive predictive value of 99.5% for patients with all OSA (p < 0.001). The area under the curve of the STOP-Bang for identifying mild, moderate and severe OSA was 0.581, 0.652 and 0.675, respectively. Whereas according to the STOP-Bang, all morbid obese patients (obesity class III, n: 47) were at high risk of OSA.

Conclusion

This study suggests that the STOP-Bang questionnaire for obstructive sleep apnea screening in obese patients is a high sensitivity and appropriate screening test.

• : obstructive sleep apnea
• obesity
• sleep apnea screening
• stop-bang questionnaires

• Fatigue
• Hausarztmedizin
• Komorbiditäten
• Müdigkeit
• approche biopsychosociale
• biopsychosocial approach
• biopsychosozialer Zugang
• comorbidities
• comorbidités
• general practice
• médecine de famille

• Comorbidity
• Depression/complications
• Depression/diagnosis
• Family Practice
• Fatigue/diagnosis
• Fatigue/etiology
• General Practice
• Humans
• Sleep Apnea Syndromes/complications
• Sleep Apnea Syndromes/diagnosis
• Substance-Related Disorders/complications
• Substance-Related Disorders/diagnosis

• OSA screening
• obstructive sleep apnea/hypopnea syndrome
• snoring

Several clinical prediction rules (CPRs) are available for sleep apnoea-hypopnoea syndrome (OSAH), but they are difficult to apply in primary care (PC).

Derivation and validation of a CPR using simple measurements available in PC.

A prospective study conducted in health centres from the area of influence of three Spanish hospitals.

Patients (aged 18–70 years) who attended for any reason; who presented with at least one of the three key symptoms for OSAH (snoring, breathing pauses while sleeping, and daytime sleepiness); and who were not undergoing non-invasive ventilation or prior treatment with continuous positive airway pressure (CPAP) were included. Anthropometric data, smoking habit, comorbidities, and Epworth test were collected. Patients were subsequently referred to the sleep unit (SU), where the decision was taken whether or not to instigate treatment. A multivariate logistic model was constructed using a sub-sample and scores assigned based on the regression coefficients; the CPR was validated with the remaining sample. Both receiver operating characteristic (ROC) curves were plotted and the sensitivity, specificity, and predictive values calculated.

The derivation sample comprised 352 patients, with 260 in the validation sample. The final factors (arterial hypertension [AHT], age, body mass index [BMI], and sex) were used to develop a rule with scores ranging from 0.00–5.50. The cut-off point that optimises the area under the curve (AUC) is ≥2.50 points (AUC = 0.78; sensitivity = 86%; specificity = 54%; positive predictive value [PPV] = 45%; negative predictive value [NPV] = 90%; likelihood ratio [LR] = 0.26). The properties for the validation sample with this cut-off point are as follows: AUC = 0.68; sensitivity = 81%; specificity = 43%; PPV = 61%; NPV = 68%; LR = 0.44.

As in similar cases, the specificity is low, meaning that healthy people are referred to a specialist. A negative result rules out the disease in most cases.

• clinical predictive rule
• primary health care
• sleep apnea

To translate and perform a cross-cultural adaptation of the Snoring, Tiredness, Observed apnea, high blood Pressure, Body mass index, Age, Neck circumference, and Gender (STOP-Bang) questionnaire so that it can be used as a screening tool for the diagnosis of obstructive sleep apnea in Brazil.

Based on the principles of good practice for the translation and cross-cultural adaptation of such instruments, the protocol included the following steps: acquisition of authorization from the lead author of the original questionnaire; translation of the instrument to Brazilian Portuguese, carried out by two translators; reconciliation; back-translation to English, carried out by two English teachers who are fluent in Portuguese; review of the back-translation; harmonization; review and approval of the questionnaire by the original author; cognitive debriefing involving 14 patients who completed the questionnaire; analysis of the results; and review and preparation of the final version of the instrument approved by the review committee.

The final version of the STOP-Bang questionnaire for use in Brazil showed a clarity score > 9 (on a scale of 1-10) for all of the questions. The Cronbach's alpha coefficient was 0.62, demonstrating the internal consistency of the instrument. The means and standard deviations of the age, body mass index, and neck circumference of the patients studied were 46.8 ± 11.2 years, 43.7 ± 8.5 kg/m², and 41.3 ± 3.6 cm, respectively.

The STOP-Bang questionnaire proved to be understandable, clear, and applicable. The original instrument and the translated version, cross-culturally adapted for use in Brazil, were consistently equivalent. Therefore, it can become a widely used screening tool for patients with suspected obstructive sleep apnea.

• Diagnosis
• Pre-test probability
• Sleep apnea
• Sleep disordered breathing

• arousal threshold
• non benzodiazepine sedative hypnotics
• sleep apnea

• Apnea-hypopnea index
• Autonomic dysfunction
• Diving response
• Obstructive sleep apnea

According to recent epidemiologic studies, patients with sleep apnea/hypopnea syndrome (SAHS) are at increased risk of cardiovascular diseases, including stroke. However, the mechanisms are not well defined. Nocturnal apneas can trigger acute cerebral ischemia in predisposed patients and impaired vasodilatation is present in SAHS, but few studies have explored vascular cerebral dysfunction and often gave inconclusive results. The aims of our study were to assess whether patients with SAHS have impairment of cerebral hemodynamics with respect to controls, and to investigate a possible relationship with clinical data. We studied two groups, one of 76 SAHS patients and another one of 76 non-SAHS subjects matched for age, sex and main cardiovascular risk factors. All participants underwent a daytime transcranial Doppler study of right middle cerebral artery to record cerebral blood flow velocity and cerebrovascular reactivity by means of breath-holding test (BHT). SAHS patients have a reduction in mean cerebral blood flow velocity (MFV) (52 ± 9 vs 60 ± 12 cms/s, p < 0.001) and BHT (31 ± 12 vs 36 ± 11 %, p = 0.005) when compared to non-SAHS controls. Moreover, MFV correlated negatively with the presence of coronary disease, and BHT with female sex and arterial pressure. On the other hand, in the SAHS group, MFV correlated negatively with oxygen desaturation severity. Patients with SAHS have impaired MFV and cerebrovascular reactivity when compared to controls. Interestingly, poorly controlled or unknown hypertension and severe nocturnal hypoxemia caused additional cerebral hemodynamic disturbances to these patients.

• Cerebral blood flow
• Cerebrovascular reactivity
• Sleep apnea syndrome
• Transcranial Doppler

• Adult
• Anthropometry
• Blood Pressure Monitoring, Ambulatory/methods
• Body Mass Index
• Cross-Sectional Studies
• Female
• Humans
• Hypertension/diagnosis
• Hypertension/epidemiology
• Hypertension/physiopathology
• Male
• Middle Aged
• Prevalence
• Risk Factors
• Sleep Apnea, Obstructive/diagnosis
• Sleep Apnea, Obstructive/epidemiology
• Sleep Apnea, Obstructive/physiopathology
• Snoring/diagnosis
• Snoring/physiopathology
• Spain/epidemiology

• Burden of illness
• Economic analysis
• Microsimulation
• Obesity

• Absenteeism
• Adult
• Aged
• Aging
• Body Mass Index
• Body Weight
• Comorbidity
• Cost of Illness
• Costs and Cost Analysis
• Depressive Disorder, Major/economics
• Depressive Disorder, Major/etiology
• Employment/statistics & numerical data
• Female
• Health Services/economics
• Health Services/statistics & numerical data
• Humans
• Income/statistics & numerical data
• Male
• Markov Chains
• Middle Aged
• Obesity/complications
• Obesity/economics
• Obesity/mortality
• Quality of Life
• Sleep Apnea Syndromes/economics
• Sleep Apnea Syndromes/etiology
• Socioeconomic Factors

• Rehabilitation
• Sleep apnea syndromes
• Stroke

• Korea
• Military Personnel
• Prevalence
• Sleep Apnea Syndrome
• Sleep Apnea, Obstructive
• Snoring

• Asian People
• Body Mass Index
• Humans
• Logistic Models
• Male
• Military Personnel
• Odds Ratio
• Palate/anatomy & histology
• Palatine Tonsil/anatomy & histology
• Polysomnography
• Prevalence
• Republic of Korea
• Retrognathia/physiopathology
• Risk Factors
• Sleep Apnea, Obstructive/epidemiology
• Snoring/epidemiology
• Surveys and Questionnaires
• Uvula/anatomy & histology
• Young Adult

• Complications
• Conscious sedation
• Endoscopy
• Obstructive sleep apnea
• Safety

• Adult
• Case-Control Studies
• Chi-Square Distribution
• Deep Sedation/adverse effects
• Endoscopy, Digestive System/adverse effects
• Female
• Humans
• Hypnotics and Sedatives/administration & dosage
• Hypnotics and Sedatives/adverse effects
• Hypotension/etiology
• Hypoxia/etiology
• Logistic Models
• Male
• Midazolam/administration & dosage
• Midazolam/adverse effects
• Middle Aged
• Multivariate Analysis
• Odds Ratio
• Polysomnography
• Predictive Value of Tests
• Prospective Studies
• Respiratory Tract Diseases/etiology
• Risk Assessment
• Risk Factors
• Sleep Apnea, Obstructive/complications
• Sleep Apnea, Obstructive/diagnosis

• Obstructive
• Polysomnography
• Questionnaire
• STOP-BANG
• Screening tests
• Sleep apnea
• Sleep disordered breathing
• Sleepiness

• Berlin Questionnaire
• STOP-Bang model
• obstructive sleep apnea syndrome
• polysomnography
• proportional odds logistic regression
• screening questionnaire

• Adolescent
• Adult
• Aged
• Aged, 80 and over
• Body Mass Index
• Female
• Humans
• Linear Models
• Male
• Middle Aged
• Polysomnography/methods
• Polysomnography/statistics & numerical data
• Predictive Value of Tests
• Severity of Illness Index
• Sleep Apnea Syndromes/diagnosis
• Sleep Apnea Syndromes/physiopathology
• Sleep Apnea, Obstructive/diagnosis
• Sleep Apnea, Obstructive/physiopathology
• Surveys and Questionnaires
• Young Adult

• cardiovascular disease
• obstructive sleep apnea
• positive airway pressure

• K23 HL079114 NHLBI NIH HHS
• M01 RR000080 NCRR NIH HHS
• U54 CA116867 NCI NIH HHS
• UL1 RR024989 NCRR NIH HHS