Evolution of Care and Outcomes Across Surges in Hospitalized Patients with Coronavirus Disease 2019.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has unfolded in distinct surges. Understanding how surges differ may reveal important insights into the evolution of the pandemic and improve patient care. METHODS: We leveraged the Michigan Medicine COVID-19 Cohort, a prospective observational study at an academic tertiary medical center that systematically enrolled 2309 consecutive patients hospitalized for COVID-19, comprising 5 distinct surges. RESULTS: As the pandemic evolved, patients hospitalized for COVID-19 tended to have a lower burden of comorbidities and a lower inflammatory burden as measured by admission levels of C-reactive protein, ferritin, lactate dehydrogenase, and D-dimer. Use of hydroxychloroquine and azithromycin decreased substantially after Surge 1, while use of corticosteroids and remdesivir markedly increased (P < .001 for all). In-hospital mortality significantly decreased from 18.3% in Surge 1 to 5.3% in Surge 5 (P < .001). The need for mechanical ventilation significantly decreased from 42.5% in Surge 1 to 7.0% in Surge 5 (P < .001), while the need for renal replacement therapy decreased from 14.4% in Surge 1 to 2.3% in Surge 5 (P < .001). Differences in patient characteristics, treatments, and inflammatory markers accounted only partially for the differences in outcomes between surges. CONCLUSIONS: The COVID-19 pandemic has evolved significantly with respect to hospitalized patient populations and therapeutic approaches, and clinical outcomes have substantially improved. Hospitalization after the first surge was independently associated with improved outcomes, even after controlling for relevant clinical covariates.

Disease-related compound identification based on deeping learning method.

Acute lung injury (ALI) is a serious respiratory disease, which can lead to acute respiratory failure or death. It is closely related to the pathogenesis of New Coronavirus pneumonia (COVID-19). Many researches showed that traditional Chinese medicine (TCM) had a good effect on its intervention, and network pharmacology could play a very important role. In order to construct "disease-gene-target-drug" interaction network more accurately, deep learning algorithm is utilized in this paper. Two ALI-related target genes (REAL and SATA3) are considered, and the active and inactive compounds of the two corresponding target genes are collected as training data, respectively. Molecular descriptors and molecular fingerprints are utilized to characterize each compound. Forest graph embedded deep feed forward network (forgeNet) is proposed to train. The experimental results show that forgeNet performs better than support vector machines (SVM), random forest (RF), logical regression (LR), Naive Bayes (NB), XGBoost, LightGBM and gcForest. forgeNet could identify 19 compounds in Erhuang decoction (EhD) and Dexamethasone (DXMS) more accurately.