Prevalence and risk factors of stroke in China: a national serial cross-sectional study from 2003 to 2018.

Stroke imposes a substantial burden worldwide. With the rapid economic and lifestyle transition in China, trends of the prevalence of stroke across different geographic regions in China remain largely unknown. Capitalizing on the data in the National Health Services Surveys (NHSS), we assessed the prevalence and risk factors of stroke in China from 2003 to 2018. In this study, data from 2003, 2008, 2013, and 2018 NHSS were collected. Stroke cases were based on participants' self-report of a previous diagnosis by clinicians. We estimated the trends of stroke prevalence for the overall population and subgroups by age, sex, and socioeconomic factors, then compared across different geographic regions. We applied multivariable logistic regression to assess associations between stroke and risk factors. The number of participants aged 15 years or older were 154,077, 146,231, 230,067, and 212,318 in 2003, 2008, 2013, and 2018, respectively, among whom, 1435, 1996, 3781, and 6069 were stroke patients. The age and sex standardized prevalence per 100,000 individuals was 879 in 2003, 1100 in 2008, 1098 in 2013, and 1613 in 2018. Prevalence per 100,000 individuals in rural areas increased from 669 in 2003 to 1898 in 2018, while urban areas had a stable trend from 1261 in 2003 to 1365 in 2018. Across geographic regions, the central region consistently had the highest prevalence, but the western region has an alarmingly increasing trend from 623/100,000 in 2003 to 1898/100,000 in 2018 (P trend<0.001), surpassing the eastern region in 2013. Advanced age, male sex, rural area, central region, hypertension, diabetes, depression, low education and income level, retirement or unemployment, excessive physical activity, and unimproved sanitation facilities were significantly associated with stroke. In conclusion, the increasing prevalence of stroke in China was primarily driven by economically underdeveloped regions. It is important to develop targeted prevention programs in underdeveloped regions. Besides traditional risk factors, more attention should be paid to nontraditional risk factors to improve the prevention of stroke.

JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation.

Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries, influencing billions of humans. To control the infection, identifying and separating the infected people is the most crucial step. The main diagnostic tool is the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Still, the sensitivity of the RT-PCR test is not high enough to effectively prevent the pandemic. The chest CT scan test provides a valuable complementary tool to the RT-PCR test, and it can identify the patients in the early-stage with high sensitivity. However, the chest CT scan test is usually time-consuming, requiring about 21.5 minutes per case. This paper develops a novel Joint Classification and Segmentation (JCS) system to perform real-time and explainable COVID- 19 chest CT diagnosis. To train our JCS system, we construct a large scale COVID- 19 Classification and Segmentation (COVID-CS) dataset, with 144,167 chest CT images of 400 COVID- 19 patients and 350 uninfected cases. 3,855 chest CT images of 200 patients are annotated with fine-grained pixel-level labels of opacifications, which are increased attenuation of the lung parenchyma. We also have annotated lesion counts, opacification areas, and locations and thus benefit various diagnosis aspects. Extensive experiments demonstrate that the proposed JCS diagnosis system is very efficient for COVID-19 classification and segmentation. It obtains an average sensitivity of 95.0% and a specificity of 93.0% on the classification test set, and 78.5% Dice score on the segmentation test set of our COVID-CS dataset. The COVID-CS dataset and code are available at https://github.com/yuhuan-wu/JCS.

[Prediction of Pathological Subtypes of Lung Adenocarcinoma with Pure Ground Glass Nodules by Deep Learning Model].

Objective To make a preliminary pathological classification of lung adenocarcinoma with pure ground glass nodules(pGGN)on CT by using a deep learning model. Methods CT images and pathological data of 219 patients(240 lesions in total)with pGGN on CT and pathologically confirmed adenocarcinoma were collected.According to pathological subtypes,the lesions were divided into non-invasive lung adenocarcinoma group(which included atypical adenomatous hyperplasia and adenocarcinoma in situ and micro-invasive adenocarcinoma)and invasive lung adenocarcinoma group.First,the lesions were outlined and labeled by two young radiologists,and then the labeled data were randomly divided into two datasets:the training set(80%)and the test set(20%).The prediction Results of deep learning were compared with those of two experienced radiologists by using the test dataset. Results The deep learning model achieved high performance in predicting the pathological types(non-invasive and invasive)of pGGN lung adenocarcinoma.The accuracy rate in pGGN diagnosis was 0.8330(95% CI=0.7016-0.9157)for of deep learning model,0.5000(95% CI=0.3639-0.6361)for expert 1,0.5625(95% CI=0.4227-0.6931)for expert 2,and 0.5417(95% CI=0.4029-0.6743)for both two experts.Thus,the accuracy of the deep learning model was significantly higher than those of the experienced radiologists(P=0.002).The intra-observer agreements were good(Kappa values:0.939 and 0.799,respectively).The inter-observer agreement was general(Kappa value:0.667)(P=0.000). Conclusion The deep learning model showed better performance in predicting the pathological types of pGGN lung adenocarcinoma compared with experienced radiologists.