RESUMO
Background: The accuracy and consistency of bone age assessments (BAA) using standard methods can vary with physicians' level of experience. Methods: To assess the impact of information from an artificial intelligence (AI) deep learning convolutional neural network (CNN) model on BAA, specialists with different levels of experience (junior, mid-level, and senior) assessed radiographs from 316 children aged 4-18 years that had been randomly divided into two equal sets-group A and group B. Bone age (BA) was assessed independently by each specialist without additional information (group A) and with information from the model (group B). With the mean assessment of four experts as the reference standard, mean absolute error (MAE), and intraclass correlation coefficient (ICC) were calculated to evaluate accuracy and consistency. Individual assessments of 13 bones (radius, ulna, and short bones) were also compared between group A and group B with the rank-sum test. Results: The accuracies of senior, mid-level, and junior physicians were significantly better (all P < 0.001) with AI assistance (MAEs 0.325, 0.344, and 0.370, respectively) than without AI assistance (MAEs 0.403, 0.469, and 0.755, respectively). Moreover, for senior, mid-level, and junior physicians, consistency was significantly higher (all P < 0.001) with AI assistance (ICCs 0.996, 0.996, and 0.992, respectively) than without AI assistance (ICCs 0.987, 0.989, and 0.941, respectively). For all levels of experience, accuracy with AI assistance was significantly better than accuracy without AI assistance for assessments of the first and fifth proximal phalanges. Conclusions: Information from an AI model improves both the accuracy and the consistency of bone age assessments for physicians of all levels of experience. The first and fifth proximal phalanges are difficult to assess, and they should be paid more attention.
RESUMO
BACKGROUND: Haemolytic uraemic syndrome (HUS) is a severe syndrome that causes a substantial burden for patients and their families and is the leading cause of acute kidney injury in children. However, data on the epidemiology and disease burden of HUS in Asia, including China, are limited. We aimed to estimate the incidence and cost of HUS in China. METHODS: Data about HUS from 2012 to 2016 were extracted from the Urban Employee Basic Medical Insurance (UEBMI) and Urban Resident Basic Medical Insurance (URBMI) databases. All cases were identified by ICD code and Chinese diagnostic terms. The 2016 national incidence rates were estimated and stratified by sex, age and season. The associated medical costs were also calculated. RESULTS: The crude incidence of HUS was 0.66 per 100,000 person-years (95% CI: 0.35 to 1.06), and the standardized incidence was 0.57 (0.19 to 1.18). The incidence of HUS in males was slightly higher than that in females. The age group with the highest incidence of HUS was patients < 1 year old (5.08, 95% CI: 0.23 to 24.87), and the season with the highest incidence was autumn, followed by winter. The average cost of HUS was 2.15 thousand US dollars per patient, which was higher than the national average cost for all inpatients in the same period. CONCLUSIONS: This is the first population-based study on the incidence of HUS in urban China. The age and seasonal distributions of HUS in urban China are different from those in most developed countries, suggesting a difference in aetiology.