RESUMEN
COVID-19 has potential consequences on the pulmonary and cardiovascular health of millions of infected people worldwide. Chest computed tomographic (CT) imaging has remained the first line of diagnosis for individuals infected with SARS-CoV-2. However, differentiating COVID-19 from other types of pneumonia and predicting associated cardiovascular complications from the same chest-CT images have remained challenging. In this study, we have first used transfer learning method to distinguish COVID-19 from other pneumonia and healthy cases with 99.2% accuracy. Next, we have developed another CNN-based deep learning approach to automatically predict the risk of cardiovascular disease (CVD) in COVID-19 patients compared to the normal subjects with 97.97% accuracy. Our model was further validated against cardiac CT-based markers including cardiac thoracic ratio (CTR), pulmonary artery to aorta ratio (PA/A), and presence of calcified plaque. Thus, we successfully demonstrate that CT-based deep learning algorithms can be employed as a dual screening diagnostic tool to diagnose COVID-19 and differentiate it from other pneumonia, and also predicts CVD risk associated with COVID-19 infection.
Asunto(s)
COVID-19 , Aprendizaje Profundo , Cardiopatías Congénitas , Neumonía , Humanos , COVID-19/diagnóstico por imagen , SARS-CoV-2 , Tomografía Computarizada por Rayos X/métodos , Prueba de COVID-19RESUMEN
BACKGROUND: Skin sensitivity characteristics and triggers have been identified in populations in previous studies. However, few have compared these characteristics among self-reported sensitive skin. OBJECTIVE: The aim of the study was to evaluate and compare specific intrinsic and extrinsic triggers of skin sensitivity between individuals with self-reported sensitive skin and non-sensitive skin. METHODS: A systematic literature review was undertaken to identify intrinsic and extrinsic factors associated with sensitive skin. A 167-item survey was developed on the basis of the literature review. The survey was completed online by a sample of adult participants drawn from the general United Kingdom population. Participants also completed sociodemographic and self-reported health questions. RESULTS: A total of 3050 surveys were completed: 1526 participants with self-reported skin sensitivity and 1524 participants not reporting skin sensitivity. There was a decrease in self-reported skin sensitivity with increasing age (p<0.05), and proportionally more women reported sensitive skin. Smoking also led to a higher frequency of sensitive skin. All signs and symptoms of sensitive skin, such as itch, dryness/flakiness, roughness and flushing/blushing were more commonly reported by those with self-reported sensitive skin. These were frequently reported in association with external factors (cold/windy weather, clothes and fabrics), as well as internal factors such as pre-existing skin conditions and atopy. CONCLUSION: The study evaluated self-reported sensitive skin against a non-sensitive skin in order to identify common inherent and external triggers to distinguish between these groups in a large general population study in the United Kingdom. The key symptoms and signs of this syndrome identified in the literature were confirmed to be reported significantly more when compared with those without sensitive skin. However, no correlation or pattern of symptomology could be identified, reinforcing the complexity of this condition. Given the strong differentiation from the non-sensitive group, the results of this research could be utilised for the development of a clinically meaningful screening tool.