Self-helped detection of obstructive sleep apnea based on automated facial recognition and machine learning.

PURPOSE: The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay diagnosis. With the widespread use of artificial intelligence, we presumed that the combination of simple clinical information and imaging recognition based on facial photos may be a useful tool to screen for OSA. METHODS: We recruited consecutive subjects suspected of OSA who had received sleep examination and photographing. Sixty-eight points from 2-dimensional facial photos were labelled by automated identification. An optimized model with facial features and basic clinical information was established and tenfold cross-validation was performed. Area under the receiver operating characteristic curve (AUC) indicated 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. Witnessed apnea by sleep partner was the most powerful variable, followed by body mass index, neck circumference, facial parameters, and hypertension. The model's performance became more robust with a sensitivity of 0.94, for patients with frequent supine sleep apnea. CONCLUSION: The findings suggest that craniofacial features extracted from 2-dimensional frontal photos, especially in the mandibular segment, have the potential to become predictors of OSA in the Chinese population. Machine learning-derived automatic recognition may facilitate the self-help screening for OSA in a quick, radiation-free, and repeatable manner.

Atorvastatin Promotes Macrocalcification, But Not Microcalcification in Atherosclerotic Rabbits: An 18F-NaF PET/CT Study.

INTRODUCTION: Our study aimed to investigate the effect of atorvastatin on plaque calcification by matching the results obtained by 18F-sodium fluoride (18F-NaF) positron emission tomography (PET)/computed tomography (CT) with data from histologic sections. METHODS AND RESULTS: The rabbits were divided into 2 groups as follows: an atherosclerosis group (n = 10) and an atorvastatin group (n = 10). All rabbits underwent an abdominal aortic operation and were fed a high-fat diet to induce atherosclerosis. Plasma samples were used to analyze serum inflammation markers and blood lipid levels. 18F-NaF PET/CT scans were performed twice. The plaque area, macrophage number and calcification were measured, and the data from the pathological sections were matched with the 18F-NaF PET/CT scan results. The mean standardized uptake value (0.725 ± 0.126 vs. 0.603 ± 0.071, P < 0.001) and maximum standardized uptake value (1.024 ± 0.116 vs. 0.854 ± 0.091, P < 0.001) significantly increased in the atherosclerosis group, but only slightly increased in the atorvastatin group (0.616 ± 0.103 vs. 0.613 ± 0.094, P = 0.384; 0.853 ± 0.099 vs.0.837 ± 0.089, P < 0.001, respectively). The total calcium density was significantly increased in rabbits treated with atorvastatin compared with rabbits not treated with atorvastatin (1.64 ± 0.90 vs. 0.49 ± 0.35, P < 0.001), but the microcalcification level was significantly lower. There were more microcalcification deposits in the areas with increased radioactive uptake of 18F-NaF. CONCLUSIONS: Our study suggests that the anti-inflammatory activity of atorvastatin may promote macrocalcification but not microcalcification within atherosclerotic plaques. 18F-NaF PET/CT can detect plaque microcalcifications.

Double-Network Hydrogel with Tunable Mechanical Performance and Biocompatibility for the Fabrication of Stem Cells-Encapsulated Fibers and 3D Assemble.

Fabrication of cell-encapsulated fibers could greatly contribute to tissue engineering and regenerative medicine. However, existing methods suffered from not only unavoidability of cell damaging conditions and/or sophisticated equipment, but also unavailability of proper materials to satisfy both mechanical and biological expectations. In this work, a simple method is proposed to prepare cell-encapsulated fibers with tunable mechanical strength and stretching behavior as well as diameter and microstructure. The hydrogel fibers are made from optimal combination of alginate and poly(N-iso-propylacrylamide)-poly(ethylene glycol), characteristics of double-network hydrogel, with enough stiffness and flexibility to create a variety of three dimensional structures like parallel helical and different knots without crack. Furthermore, such hydrogel fibers exhibit better compatibility as indicated by the viability, proliferation and expression of pluripotency markers of embryonic stem cells encapsulated after 4-day culture. The double-network hydrogel possesses specific quick responses to either of alginate lyase, EDTA or lower environmental temperature which facilitate the optional degradation of fibers or fibrous assemblies to release the cells encapsulated for subsequent assay or treatment.