Development and external evaluation of predictions models for mortality of COVID-19 patients using machine learning method.

To predict the mortality of patients with coronavirus disease 2019 (COVID-19). We collected clinical data of COVID-19 patients between January 18 and March 29 2020 in Wuhan, China . Gradient boosting decision tree (GBDT), logistic regression (LR) model, and simplified LR were built to predict the mortality of COVID-19. We also evaluated different models by computing area under curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) under fivefold cross-validation. A total of 2924 patients were included in our evaluation, with 257 (8.8%) died and 2667 (91.2%) survived during hospitalization. Upon admission, there were 21 (0.7%) mild cases, 2051 (70.1%) moderate case, 779 (26.6%) severe cases, and 73 (2.5%) critically severe cases. The GBDT model exhibited the highest fivefold AUC, which was 0.941, followed by LR (0.928) and LR-5 (0.913). The diagnostic accuracies of GBDT, LR, and LR-5 were 0.889, 0.868, and 0.887, respectively. In particular, the GBDT model demonstrated the highest sensitivity (0.899) and specificity (0.889). The NPV of all three models exceeded 97%, while their PPV values were relatively low, resulting in 0.381 for LR, 0.402 for LR-5, and 0.432 for GBDT. Regarding severe and critically severe cases, the GBDT model also performed the best with a fivefold AUC of 0.918. In the external validation test of the LR-5 model using 72 cases of COVID-19 from Brunei, leukomonocyte (%) turned to show the highest fivefold AUC (0.917), followed by urea (0.867), age (0.826), and SPO2 (0.704). The findings confirm that the mortality prediction performance of the GBDT is better than the LR models in confirmed cases of COVID-19. The performance comparison seems independent of disease severity. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at(10.1007/s00521-020-05592-1).

Safety, Tolerability, and Pharmacokinetics of Intravenous Doses of PF-07304814, a Phosphate Prodrug Protease Inhibitor for the Treatment of SARS-CoV-2, in Healthy Adult Participants.

Studies on targeted antivirals for treatment of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of the ongoing pandemic, are limited. PF-07304814 (lufotrelvir) is the phosphate prodrug of PF-00835231, a protease inhibitor targeting the 3C-like protease of SARS-CoV-2. This phase 1 study evaluated the safety, tolerability, and pharmacokinetics (PK) of single ascending intravenous doses of lufotrelvir (continuous 24-hour infusion of 50, 150, 500, or 700 mg) versus placebo in healthy volunteers (2 interleaving cohorts: 1, n = 8; 2, n = 7). Each dosing period was separated by a washout interval (≥5 days). Treatment-emergent adverse events, PK, and biomarker concentrations were estimated from plasma/urine samples. Lufotrelvir was administered to 15 volunteers (mean [SD] age 39.7 [11.8] years). No serious adverse events, discontinuations, or deaths were reported. Mean maximum observed concentration of PF-00835231 (active moiety; 97.0 ng/mL to 1288 ng/mL) were observed between median time to maximum concentration of 14 to 16 hours after the start of the lufotrelvir infusion. Near-maximum plasma concentrations of PF-00835231 were observed ≈6 hours after infusion start and sustained until infusion end. PF-00835231 plasma concentrations declined rapidly after infusion end (mean terminal half-life: 500 mg, 2.0 hours; 700 mg, 1.7 hours). Approximately 9%-11% of the dose was recovered in urine as PF-00835231 across doses. A continuous, single-dose, 24-hour infusion of lufotrelvir (50-700 mg) was rapidly converted to PF-00835231 (active moiety), with dose-proportional PK exposures and no significant safety concerns. A daily, 24-hour continuous infusion of 270 to 350 mg is expected to maintain PF-00835231 concentration at steady state/above effective antiviral concentrations. Further studies exploring lufotrelvir efficacy in patients with coronavirus disease 2019 are ongoing.

Thank You to Our 2020 Peer Reviewers

Key PointThe editors thank the 2020 peer reviewers

Switching to electric vehicles can lead to significant reductions of PM2.5 and NO2 across China

Summary Transportation contributes to around one-fifth of global greenhouse gas emissions, while also causing severe air pollution. The conversion to electric vehicles (EVs) represents a major path to decarbonize the transport sector, with potentially significant co-benefits for human health. However, the scale of such co-benefits largely remains an empirical question and lacks observational evidence. The full lockdown in China during the coronavirus disease 2019 (COVID-19) pandemic provides an unprecedented real-world experiment to evaluate emission reduction potentials of a large-scale transition to EVs. Here, we utilize ground and satellite observations of air quality during the full lockdown to constrain predictions of a comprehensive chemical transport model and find that the substantial traffic reductions are near-linearly linked to reductions of PM2.5 (particles with an aerodynamic diameter ≤2.5 μm) and NO2. A further extrapolation of a full conversion to EVs shows a significant reduction of PM2.5 (30%–70%) and NO2 (30%–80%) in most of China. Our findings provide fact-based evidence of potential environmental benefits generated by fully switching to EVs.

Identifying the Risk of SARS-CoV-2 Infection and Environmental Monitoring in Airborne Infectious Isolation Rooms (AIIRs).

Healthcare workers (HCWs) are at high risk of occupational exposure to the new pandemic human coronavirus, SARS-CoV-2, and are a source of nosocomial transmission in airborne infectious isolation rooms (AIIRs). Here, we performed comprehensive environmental contamination surveillance to evaluate the risk of viral transmission in AIIRs with 115 rooms in three buildings at the Shanghai Public Health Clinical Center, Shanghai, during the treatment of 334 patients infected with SARS-CoV-2. The results showed that the risk of airborne transmission of SARS-CoV-2 in AIIRs was low (1.62%, 25/1544) due to the directional airflow and strong environmental hygiene procedures. However, we detected viral RNA on the surface of foot-operated openers and bathroom sinks in AIIRs (viral load: 55.00-3154.50 copies/mL). This might be a source of contamination to connecting corridors and object surfaces through the footwear and gloves used by HCWs. The risk of infection was eliminated by the use of disposable footwear covers and the application of more effective environmental and personal hygiene measures. With the help of effective infection control procedures, none of 290 HCWs was infected when working in the AIIRs at this hospital. This study has provided information pertinent for infection control in AIIRs during the treatment of COVID-19 patients.

SARS pandemic exposure impaired early childhood development in China.

Social and mental stressors associated with the pandemic of a novel infectious disease, e.g., COVID-19 or SARS may promote long-term effects on child development. However, reports aimed at identifying the relationship between pandemics and child health are limited. A retrospective study was conducted to associate the SARS pandemic in 2003 with development milestones or physical examinations among longitudinal measurements of 14,647 children. Experiencing SARS during childhood was associated with delayed milestones, with hazard ratios of 3.17 (95% confidence intervals CI: 2.71, 3.70), 3.98 (3.50, 4.53), 4.96 (4.48, 5.49), or 5.57 (5.00, 6.20) for walking independently, saying a complete sentence, counting 0-10, and undressing him/herself for urination, respectively. These results suggest relevant impacts from COVID-19 on child development should be investigated.

A novel screening strategy of anti-SARS-CoV-2 drugs via blocking interaction between Spike RBD and ACE2.

Corona virus disease 2019 has spread worldwide, and appropriate drug design and screening activities are required to overcome the associated pandemic. Using computational simulation, blockade mechanism of SARS-CoV-2 spike receptor binding domain (S RBD) and human angiotensin converting enzyme 2 (hACE2) was clarified based on interactions between RBD and hesperidin. Interactions between anti-SARS-CoV-2 drugs and therapy were investigated based on the binding energy and druggability of the compounds, and they exhibited negative correlations; the compounds were classified into eight common types of structures with highest activity. An anti-SARS-CoV-2 drug screening strategy based on blocking S RBD/hACE2 binding was established according to the first key change (interactions between hesperidin and S RBD/hACE2) vs the second key change (interactions between anti-SARS-CoV-2 drugs and RBD/hACE2) trends. Our findings provide valuable information on the mechanism of RBD/hACE2 binding and on the associated screening strategies for anti-SARS-CoV-2 drugs based on blocking mechanisms of pockets.

Blood molecular markers associated with COVID-19 immunopathology and multi-organ damage.

COVID-19 is characterized by dysregulated immune responses, metabolic dysfunction and adverse effects on the function of multiple organs. To understand host responses to COVID-19 pathophysiology, we combined transcriptomics, proteomics, and metabolomics to identify molecular markers in peripheral blood and plasma samples of 66 COVID-19-infected patients experiencing a range of disease severities and 17 healthy controls. A large number of expressed genes, proteins, metabolites, and extracellular RNAs (exRNAs) exhibit strong associations with various clinical parameters. Multiple sets of tissue-specific proteins and exRNAs varied significantly in both mild and severe patients suggesting a potential impact on tissue function. Chronic activation of neutrophils, IFN-I signaling, and a high level of inflammatory cytokines were observed in patients with severe disease progression. In contrast, COVID-19-infected patients experiencing milder disease symptoms showed robust T-cell responses. Finally, we identified genes, proteins, and exRNAs as potential biomarkers that might assist in predicting the prognosis of SARS-CoV-2 infection. These data refine our understanding of the pathophysiology and clinical progress of COVID-19.

Cardiac Involvement in Patients Recovered From COVID-2019 Identified Using Magnetic Resonance Imaging.

Objectives: This study evaluated cardiac involvement in patients recovered from coronavirus disease-2019 (COVID-19) using cardiac magnetic resonance (CMR). Background: Myocardial injury caused by COVID-19 was previously reported in hospitalized patients. It is unknown if there is sustained cardiac involvement after patients' recovery from COVID-19. Methods: Twenty-six patients recovered from COVID-19 who reported cardiac symptoms and underwent CMR examinations were retrospectively included. CMR protocols consisted of conventional sequences (cine, T2-weighted imaging, and late gadolinium enhancement [LGE]) and quantitative mapping sequences (T1, T2, and extracellular volume [ECV] mapping). Edema ratio and LGE were assessed in post-COVID-19 patients. Cardiac function, native T1/T2, and ECV were quantitatively evaluated and compared with controls. Results: Fifteen patients (58%) had abnormal CMR findings on conventional CMR sequences: myocardial edema was found in 14 (54%) patients and LGE was found in 8 (31%) patients. Decreased right ventricle functional parameters including ejection fraction, cardiac index, and stroke volume/body surface area were found in patients with positive conventional CMR findings. Using quantitative mapping, global native T1, T2, and ECV were all found to be significantly elevated in patients with positive conventional CMR findings, compared with patients without positive findings and controls (median [interquartile range]: native T1 1,271 ms [1,243 to 1,298 ms] vs. 1,237 ms [1,216 to 1,262 ms] vs. 1,224 ms [1,217 to 1,245 ms]; mean ± SD: T2 42.7 ± 3.1 ms vs. 38.1 ms ± 2.4 vs. 39.1 ms ± 3.1; median [interquartile range]: 28.2% [24.8% to 36.2%] vs. 24.8% [23.1% to 25.4%] vs. 23.7% [22.2% to 25.2%]; p = 0.002; p < 0.001, and p = 0.002, respectively). Conclusions: Cardiac involvement was found in a proportion of patients recovered from COVID-19. CMR manifestation included myocardial edema, fibrosis, and impaired right ventricle function. Attention should be paid to the possible myocardial involvement in patients recovered from COVID-19 with cardiac symptoms.