Understanding crowd motion dynamics is critical to realworld applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show STAR outperforms the state-of-the-art models on 4 out of 5 real-world pedestrian trajectory prediction datasets, and achieves comparable performance on the rest.

Background The outbreak of COVID-19 has led to international concern. We aimed to establish an effective screening strategy in Shanghai, China, to aid early identification of patients with COVID-19. MethodsWe did a multicentre, observational cohort study in fever clinics of 25 hospitals in 16 districts of Shanghai. All patients visiting the clinics within the study period were included. A strategy for COVID-19 screening was presented and then suspected cases were monitored and analysed until they were confirmed as cases or excluded. Logistic regression was used to determine the risk factors of COVID-19. Findings We enrolled patients visiting fever clinics fromJan 17 to Feb 16, 2020. Among 53 617 patients visiting fever clinics, 1004 (1•9%) were considered as suspected cases, with 188 (0•4% of all patients, 18•7% of suspected cases) eventually diagnosed as confirmed cases. 154 patients with missing data were excluded from the analysis. Exposure history (odds ratio [OR] 4•16, 95% CI 2•74-6•33; p<0•0001), fatigue (OR 1•56, 1•01-2•41; p=0•043), white blood cell count less than 4 × 10⁹ per L (OR 2•44, 1•28-4•64; p=0•0066), lymphocyte count less than 0•8 × 10⁹ per L (OR 1•82, 1•00-3•31; p=0•049), ground glass opacity (OR 1•95, 1•32-2•89; p=0•0009), and having both lungs affected (OR 1•54, 1•04-2•28; p=0•032) were independent risk factors for confirmed COVID-19.Interpretation The screening strategy was effective for confirming or excluding COVID-19 during the spread of this contagious disease. Relevant independent risk factors identified in this study might be helpful for early recognition of the disease.

Epithelial-to-mesenchymal transition (EMT) has profound impacts on cancer progression and also on drug resistance, including epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs). Nowadays, there is still no predictive biomarker identified for the use of EGFR-TKIs in non-small cell lung cancer (NSCLC) patients with wild-type EGFR. To clarify the role of EMT phenotype as a predictive marker for EGFR-TKI, we performed a retrospective study in 202 stage IV or recurrent NSCLC patients receiving gefitinib or erlotinib therapy from June 2008 to September 2012 in our institute. Clinical data and EGFR mutational status were collected, while epithelial, epithelial to mesenchymal, not specified or mesenchymal phenotype were classified according to EMT markers such as E-cadherin, fibronectin, N-cadherin and vimentin by immunohistochemistry. Epithelial phenotype was more frequently found in patients with EGFR mutation (p 5 0.044). Epithelial phenotype was associated with a significantly higher objective response rate (23.5 vs. 11.1 vs. 0.0 vs. 2.4%, p 5 0.011), longer progression-free survival (4.4 vs. 1.9 vs. 1.7 vs. 1.0 months, p < 0.001) and longer overall survival (11.5 vs. 8.9 vs. 4.5 vs. 4.9 months, p < 0.001) compared to epithelial to mesenchymal, not specified and mesenchymal phenotype in the wild-type EGFR subgroup. In the subgroup with EGFR mutation, the trend remained but without a statistically significant difference. In conclusion, epithelial phenotype was more likely expressed in patients with EGFR mutation and was associated with a better outcome in advanced NSCLC patients with wild-type EGFR, which indicates that the EMT phenotype might be a potential marker to guide EGFR-TKI therapy in this population.Tailored therapy based on biomarker analysis has entered reality of lung cancer treatment. Patients with EGFR-activated mutation or ALK/ROS1 fusion gain significant benefit from targeted therapy with epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) or ALK inhibitors. However, only a minority of patients express these markers, with EGFR

No abstract

Background: Few studies have investigated the epidemiology of secondary glaucoma (SG) in China. This study analyzed the current profile of admitted patients with SG at the largest ophthalmic center in China.Methods: SG cases were retrieved retrospectively by International Classification of Disease-10 clinical coding data from January 2010 to December 2019. Demographic data, etiologies, and the management of SG were analyzed. The ratios of the etiologies were compared with previously reported data from other regions. The etiologies and management between the 2010 to 2014 group and the 2015 to 2019 group were compared.Results: A total of 11,730 cases were enrolled. The mean age of the patients with SG was 44.45 ± 19.45 years old. Men (66.94%) were more vulnerable than women (33.06%). The etiologies of SG in 2010 to 2019 were trauma (28%), vascular disease (18%), lens-induced (9%), inflammation (11%), drug-induced (2%), anterior segment surgery (7%), posterior segment surgery (11%), syndrome-associated (4%), and tumors (1%). Compared with other regions, our data have a higher proportion of trauma and vascular disease-associated SG. Compared with 2010 to 2014, trauma-induced SG declined, and drug-induced SG, anterior segment surgery, and syndrome-associated SG increased in 2015 to 2019 (P < 0.001). Vascular disease-associated SG cases were older than trauma-induced SCs and had a higher percentage in retired patients (P < 0.001), whereas trauma-induced SGs were more prevalent in pediatric patients than vascular disease-related SGs (P < 0.001). In addition, the application of drainage device implantation, cataract surgery, and cyclophotocoagulation increased, whereas trabeculectomy and anterior chamber paracentesis and cyclocryotherapy decreased in 2015 to 2019 (P < 0.005). Conclusion:Although the etiology spectrum has changed during the last 10 years, trauma and vascular disease are still common causes of SG in southern China. Traditional antiglaucoma surgery decreased gradually, and more advanced treatments emerged for its treatment. Up-to-date knowledge of SGs reflects the impact of economic development and ophthalmic service improvement on SGs and is of great value for ophthalmologists to detect SGs early and manage them in a timely manner.