The Role of Mandibular Disharmony for Adult Obstructive Sleep Apnea in the Machine-learning Facial Recognition

Abstract

Abstract Purpose: The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay the diagnosis. With the widespread use of Artificial Intelligence, quick identification with simple clinical information and image recognition pointing at craniofacial features might be a useful tool for self-helped screening of OSA. Methods: The subjects suspected of OSA receiving sleep examination and frontal photographing were consecutively recruited. Sixty-eight points were labelled with automated identification. An optimized model with facial features and basic clinical information was established and ten-folds cross-validation was performed. Area under the receiver operating characteristic curve (AUC) was calculated to evaluate the model’s performance using sleep monitoring as the reference standard. Results: A total of 653 subjects (77.2% males, 55.3% OSA) were analyzed. CATBOOST was the most suitable algorithm for OSA classification with a sensitivity, specificity, accuracy and AUC of 0.75, 0.66, 0.71 and 0.76 respectively (P<0.05), which was better than STOP-Bang questionnaire, NoSAS scores and Epworth scale. And its advantage was more robust in the prediction of supine sleep apnea with a sensitivity of 0.94. Witnessed apnea by sleep partner was the most powerful variable and followed by body mass index, neck circumference, facial parameters and hypertension. Conclusion: OSA could be identified by a machine-learning derived model with automatic recognition of facial photo for Chinese adults, which may facilitate screening of suspected subjects in a simple and quick manner by mobile application. Clinical trial registration Chinese Clinical Trial Registry: No. ChiCTR-ROC-17011027 (http://chictr.org.cn.)