Prediction of obstructive sleep apnea using visual photographic analysis

Cheung, Kristin; Ishman, Stacey L.; Benke, James R.; Collop, Nancy A.; Tron, Lia; Moy, Nicole; Stierer, Tracey L.

doi:10.1016/j.jclinane.2015.12.020

Cited by 13 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assessment of facial morphology by craniofacial photography did not improve the ability of clinical assessments and the nasal flow monitor to identify disease in this primary care context. Previous research found that visual assessment of photographs was not useful in the diagnosis of OSA, 34 but did not use the validated photographic assessment technique as used in our study. 20 There is evidence to show that craniofacial measurements relate to OSA differently across different ethnic groups, 35 and this adds complexity as a screening tool.…”

Section: Discussionmentioning

confidence: 85%

Development and validation of a model for diagnosis of obstructive sleep apnoea in primary care

et al. 2021

View full text Add to dashboard Cite

Background and objective: Use of in-laboratory polysomnography (PSG) to diagnose obstructive sleep apnoea (OSA) is cost and resource intensive. Questionnaires, physical measurements and home monitors have been studied as potential simpler alternatives. This study aimed to develop a diagnostic model for OSA for use in primary care. Methods: Primary care practitioners were trained to recognize symptoms of sleep apnoea and recruited patients based on the clinical need to investigate OSA. Assessment was by symptom questionnaires, anthropomorphic measurements, digital facial photography, and a single-channel nasal flow monitor (Flow Wiz-ard©, DiagnoseIT, Sydney, Australia) worn at home for 3 nights. The in-laboratory PSG was the reference test, with OSA defined as apnoea-hypopnoea index (AHI) ≥10 events/h. Results: In the model development phase, 25 primary care practitioners studied 315 patients in whom they suspected OSA, of which 57% had AHI≥10 and 22% had AHI≥30. Published OSA questionnaires provided low to moderate prediction of OSA (area under the curve [AUC] 0.53-0.73). The nasal flow monitor alone yielded high accuracy for predicting OSA with AUC of 0.87. Sensitivity was 0.87 and specificity 0.77 at a threshold respiratory event index (REI) of 18 events/h. A model adding age, gender, symptoms and BMI to the nasal flow monitor REI only modestly improved OSA prediction (AUC 0.89), with similar AUC (0.88) confirmed in the validation population of 114 patients. Conclusion: Sleep apnoea can be diagnosed in the primary care setting with a combination of clinical judgement and portable monitor test outcomes. K E Y W O R D S development and validation, diagnostic model, obstructive sleep apnoea, predictive value, primary care † List of collaborator names are given in the Acknowledgements.

show abstract

Section: Discussionmentioning

confidence: 85%

Development and validation of a model for diagnosis of obstructive sleep apnoea in primary care

et al. 2021

View full text Add to dashboard Cite

show abstract

“… 58 Cheung also found that visual assessments based on front and side photographs were poor at predicting OSA. 59 Yuen found significant differences in the maxillary-mandibular relationship angle and the ratio of mandibular height to the entire length of the face in prepubertal children as the severity of OSA increased. 33 The model established by Masoud through three-dimensional airway analysis shows remarkable predictive value.…”

Section: Discussionmentioning

confidence: 99%

Development and Validation of a Nomogram for Predicting Obstructive Sleep Apnea Severity in Children

Liu,

Xie,

Yang

et al. 2024

NSS

View full text Add to dashboard Cite

Purpose The clinical presentation of Obstructive Sleep Apnea (OSA) in children is insidious and harmful. Early identification of children with OSA, particularly those at a higher risk for severe symptoms, is essential for making informed clinical decisions and improving long-term outcomes. Therefore, we developed and validated a risk prediction model for severity in Chinese children with OSA to effectively identify children with moderate-to-severe OSA in a clinical setting. Patients and Methods From June 2023 to September 2023, we retrospectively analyzed the medical records of 367 Children diagnosed with OSA through portable bedside polysomnography (PSG). Predictor variables were screened using the least absolute shrinkage and selection operator (LASSO) and logistic regression techniques to construct nomogram to predict the severity of OSA. Receiver operating characteristic curve (ROC), calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC) were used to determine the discrimination, calibration, and clinical usefulness of the nomogram. Results A total of 367 children with a median age of 84 months were included in this study. Neck circumference, ANB, gender, learning problem, and level of obstruction were identified as independent risk factors for moderate-severe OSA. The consistency indices of the nomogram in the training and validation cohorts were 0.841 and 0.75, respectively. The nomogram demonstrated a strong concordance between the predicted probabilities and the observed probabilities for children diagnosed with moderate-severe OSA. With threshold probabilities ranging from 0.1 to 1.0, the predictive model demonstrated strong predictive efficacy and yielded improved net benefit for clinical decision-making. ROC analysis was employed to classify the children into high and low-risk groups, utilizing the Optimal Cutoff value of 0.39. Conclusion A predictive model using LASSO regression was developed and validated for children with varying levels of OSA. This model identifies children at risk of developing OSA at an early stage.

show abstract

“…Furthermore, many studies across different ethnic populations have shown that measurements of surface craniofacial dimensions are correlated with OSA severity. [12][13][14][15]26,[29][30][31] The techniques used in these previous studies have included MRI, CT, lateral cephalometry, and 2D photography. Although cephalometry and MRI allow accurate measurement of specific dimensions of the facial skeleton and upper airway, these techniques are not suitable for routine clinical assessment and their use is limited by cost in the case of MRI and the risks associated with exposure to ionizing radiation in the case of cephalometry and CT. Craniofacial measurements from 2D photography have been used to predict OSA severity with reasonable accuracy 15,16 ; however 2D photography is unable to effectively capture the nonlinear nature of craniofacial anatomy, such as shape and contour.…”

Section: Extract Linear Distance Between the P Landmarks On Each Face Such Thatmentioning

confidence: 99%

Predicting sleep apnea from three-dimensional face photography

Eastwood

Gilani

McArdle

et al. 2020

Journal of Clinical Sleep Medicine

View full text Add to dashboard Cite

Study Objectives: Craniofacial anatomy is recognized as an important predisposing factor in the pathogenesis of obstructive sleep apnea (OSA). This study used three-dimensional (3D) facial surface analysis of linear and geodesic (shortest line between points over a curved surface) distances to determine the combination of measurements that best predicts presence and severity of OSA. Methods: 3D face photographs were obtained in 100 adults without OSA (apnea-hypopnea index [AHI] < 5 events/h), 100 with mild OSA (AHI 5 to < 15 events/h), 100 with moderate OSA (AHI 15 to < 30 events/h), and 100 with severe OSA (AHI ≥ 30 events/h). Measurements of linear distances and angles, and geodesic distances were obtained between 24 anatomical landmarks from the 3D photographs. The accuracy with which different combinations of measurements could classify an individual as having OSA or not was assessed using linear discriminant analyses and receiver operating characteristic analyses. These analyses were repeated using different AHI thresholds to define presence of OSA. Results: Relative to linear measurements, geodesic measurements of craniofacial anatomy improved the ability to identify individuals with and without OSA (classification accuracy 86% and 89% respectively, P < .01). A maximum classification accuracy of 91% was achieved when linear and geodesic measurements were combined into a single predictive algorithm. Accuracy decreased when using AHI thresholds ≥ 10 events/h and ≥ 15 events/h to define OSA although greatest accuracy was always achieved using a combination of linear and geodesic distances. Conclusions: This study suggests that 3D photographs of the face have predictive value for OSA and that geodesic measurements enhance this capacity.

show abstract

Prediction of obstructive sleep apnea using visual photographic analysis

Cited by 13 publications

References 22 publications

Development and validation of a model for diagnosis of obstructive sleep apnoea in primary care

Development and validation of a model for diagnosis of obstructive sleep apnoea in primary care

Development and Validation of a Nomogram for Predicting Obstructive Sleep Apnea Severity in Children

Predicting sleep apnea from three-dimensional face photography

Contact Info

Product

Resources

About