Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.

The fish-borne clonorchiasis caused by the oriental liver fluke Clonorchis sinensis is endemic in a number of countries with over 35 million people being infected globally. Rapid and accurate detection of C. sinensis in its intermediate host fish is important for the control and prevention of clonorchiasis in areas where the disease is endemic. In the present study, we established a loop-mediated isothermal amplification (LAMP) approach for the sensitive and rapid detection of C. sinensis metacercariae in fish. The specificity and sensitivity of primers designed from the C. sinensis cathepsins B3 gene were evaluated, and specific amplification products were obtained with C. sinensis, while no amplification products were detected with DNA of related trematodes, demonstrating the specificity of the assay. The LAMP assay was proved to be 100 times more sensitive than a conventional polymerase chain reaction for detection of C. sinensis. The established LAMP assay provides a useful tool for the rapid and sensitive detection of C. sinensis in fish, which has important implications for the effective control of human clonorchiasis.

BackgroundClonorchiasis, caused by Clonorchis sinensis, is one of the major parasitic zoonoses in China, particularly in China's southern Guangdong province where the prevalence of C. sinensis infection in humans is high. However, little is known of the prevalence of C. sinensis infection in its reservoir hosts dogs and cats. Hence, the prevalence of C. sinensis infection in dogs and cats was investigated in Guangdong province, China between October 2006 and March 2008.ResultsA total of 503 dogs and 194 cats from 13 administrative regions in Guangdong province were examined by post-mortem examination. The worms were examined, counted, and identified to species according to existing keys and descriptions. The average prevalences of C. sinensis infection in dogs and cats were 20.5% and 41.8%, respectively. The infection intensities in dogs were usually light, but in cats the infection intensities were more serious. The prevalences were higher in some of the cities located in the Pearl River Delta region which is the most important endemic area in Guangdong province, but the prevalences were relatively lower in seaside cities.ConclusionsThe present investigation revealed a high prevalence of C. sinensis infection in its reservoir hosts dogs and cats in China's subtropical Guangdong province, which provides relevant "base-line" data for conducting control strategies and measures against clonorchiasis in this region.

No abstract