ABSTRACT
We describe the curation, annotation methodology, and characteristics of the dataset used in an artificial intelligence challenge for detection and localization of COVID-19 on chest radiographs. The chest radiographs were annotated by an international group of radiologists into four mutually exclusive categories, including "typical," "indeterminate," and "atypical appearance" for COVID-19, or "negative for pneumonia," adapted from previously published guidelines, and bounding boxes were placed on airspace opacities. This dataset and respective annotations are available to researchers for academic and noncommercial use.
Subject(s)
COVID-19 , Humans , Artificial Intelligence , Radiography , Machine Learning , Radiologists , Radiography, Thoracic/methodsABSTRACT
UNLABELLED: Cryptosporidium parvum is associated with diarrheic disease and mainly affects children and immunocompromised hosts. In most of the cases, cryptosporidiosis infection is asymptomatic in immunocompetent subjects. The objectives of the study were to determine the frequency of asymptomatic infection caused by the parasite in children with and without malnutrition and to determine the risk factors associated to infection. METHODS: Children from one to fifteen years old without diarrhea were included, somatometry were performed. The socioeconomic and sanitary conditions were investigated for each family and community. The Faust method and Kinyoun stain were employed identify parasites and Cryptosporidium parvum in feces. Odds ratio (OR), 95% confidence intervals (75% CI), chi 2 Mantel-Haenszel, Fisher exact test and chi 2 trends were calculated. RESULTS: One hundred thirty two children were included. In 10/132 (7.5%) cysts of Cryptosporidium were found, 7/71 in children with malnutrition (9.8%) and 3/61 without malnutrition (4.9%) p = 0.23. 69.7% of the children had parasitosis. According to the presence of C. parvum in feces, the different factors calculated were: Diarrhea in family OR = 5.82 (95%IC 0.86-39.18), not hand washing OR = 5.08 (95%IC 0.62-110.49), age less than 5 years old OR = 4.90 (95%IC 0.60-106.9), drinking non-potable water OR = 3.34 (95%IC 0.40-73.01) and malnutrition 2.11 (95%IC 0.46-10.89). Association was found between the number of people in the same house and the risk of infection (p = 0.005). The presence of diarrhea in the family (OR = 4.15, 95%IC 0.47-36.91) and drinking non-potable water (OR = 4.19, 95%IC 0.48-36.32) were the significant factors in the regression logistic model. CONCLUSIONS: The frequency of Cryptosporidium infection were 7.5%. Diarrhea in the family, overcrowding and drinking non-potable water were associated with C. parvum infection, malnutrition was not a significant risk factor.
