RESUMO
BACKGROUND: Williams-Beuren syndrome, Noonan syndrome, and Alagille syndrome are common types of genetic syndromes (GSs) characterized by distinct facial features, pulmonary stenosis, and delayed growth. In clinical practice, differentiating these three GSs remains a challenge. Facial gestalts serve as a diagnostic tool for recognizing Williams-Beuren syndrome, Noonan syndrome, and Alagille syndrome. Pretrained foundation models (PFMs) can be considered the foundation for small-scale tasks. By pretraining with a foundation model, we propose facial recognition models for identifying these syndromes. METHODS: A total of 3297 (n = 1666) facial photos were obtained from children diagnosed with Williams-Beuren syndrome (n = 174), Noonan syndrome (n = 235), and Alagille syndrome (n = 51), and from children without GSs (n = 1206). The photos were randomly divided into five subsets, with each syndrome and non-GS equally and randomly distributed in each subset. The proportion of the training set and the test set was 4:1. The ResNet-100 architecture was employed as the backbone model. By pretraining with a foundation model, we constructed two face recognition models: one utilizing the ArcFace loss function, and the other employing the CosFace loss function. Additionally, we developed two models using the same architecture and loss function but without pretraining. The accuracy, precision, recall, and F1 score of each model were evaluated. Finally, we compared the performance of the facial recognition models to that of five pediatricians. RESULTS: Among the four models, ResNet-100 with a PFM and CosFace loss function achieved the best accuracy (84.8%). Of the same loss function, the performance of the PFMs significantly improved (from 78.5% to 84.5% for the ArcFace loss function, and from 79.8% to 84.8% for the CosFace loss function). With and without the PFM, the performance of the CosFace loss function models was similar to that of the ArcFace loss function models (79.8% vs 78.5% without PFM; 84.8% vs 84.5% with PFM). Among the five pediatricians, the highest accuracy (0.700) was achieved by the senior-most pediatrician with genetics training. The accuracy and F1 scores of the pediatricians were generally lower than those of the models. CONCLUSIONS: A facial recognition-based model has the potential to improve the identification of three common GSs with pulmonary stenosis. PFMs might be valuable for building screening models for facial recognition. Key messages What is already known on this topic: Early identification of genetic syndromes (GSs) is crucial for the management and prognosis of children with pulmonary stenosis (PS). Facial phenotyping with convolutional neural networks (CNNs) often requires large-scale training data, limiting its usefulness for GSs. What this study adds: We successfully built multi-classification models based on face recognition using a CNN to accurately identify three common PS-associated GSs. ResNet-100 with a pretrained foundation model (PFM) and CosFace loss function achieved the best accuracy (84.8%). Pretrained with the foundation model, the performance of the models significantly improved, although the impact of the type of loss function appeared to be minimal. How this study might affect research, practice, or policy: A facial recognition-based model has the potential to improve the identification of GSs in children with PS. The PFM might be valuable for building identification models for facial detection.
RESUMO
Background: Increasing evidence suggest a racial bias in pulse oximetry measurement, but this was under investigated in Asian pediatric populations. Methods: Via the Pediatric Intensive Care database, this retrospective study included pediatric patient records of arterial oxygen saturation (SaO2) and oxygen saturation on pulse oximetry (SpO2) measured within 10 min. Discrepancy was examined, and potential predictors of occult hypoxemia (defined as SaO2 <88% with the paired SpO2 ≥92%) as well as its association with outcomes were explored by logistic regression. Results: A total of 390 patients were included with 454 pairs of SaO2-SpO2 readings. The study population consisted of Han Chinese (99.0%) and 43.6% were female. Occult hypoxemia was observed in 20.0% of the patients, with a mean SaO2 of 71.4 ± 15.8%. Potential predictors of occult hypoxemia included female, being first admitted to cardiac ICU, congenital heart disease, increased heart rate, while patients with prior surgery records were less likely to experience occult hypoxemia. Patients with occult hypoxemia had numerically higher in-ICU mortality (16.7% versus 10.9%) and in-hospital mortality (17.9% versus 10.9%), but the associations were not statistically significant. Conclusions: There was a substantial proportion of hypoxemia that was not detected by pulse oximetry in the Chinese pediatric patients, which might be predicted by several characteristics and seemed to associate with mortality.
RESUMO
Perceptions of residents in ecological resettlement area are important for evaluating the implementation effect of ecological relocation and sustainable development of world heritage site. With the residents from three different resettlement communities in Wulingyuan Scenic Area as the research object, we carried out a diachronic study on changes of the resettlers' perceptions of ecological relocation at different times and the main driving factors based on systematic survey data in 2010 and 2016. The results showed that in the year 2010 and 2016, resettlers reacted negatively to the indicators such as "enhancement of employment opportunity", "improvement of education and training opportunity", "enhanced environment in scenic area", "recognizing the identity change 'from rural to non-rural' after relocation". They favored the indicators such as "undermining traditional value", "lack of supervision during the implementation of policies". In 2016, resettlers of different gender, age and average monthly income had substantial different opinions on the economic and psychological impacts of ecological relocation. Education and income level had great impacts on their opinions of ecological relocation policies. Resettlers relocated by the way of investment for developing perceived were more sensitive to the economic impacts. Economic and policy impacts became the dominant driving factors for their general perception of ecological relocation. They pay more attention to employment, children's education opportunity as well as social security system for relocation.