Warfarin anticoagulation management during the COVID-19 pandemic: The role of internet clinic and machine learning

Background: Patients who received warfarin require constant monitoring by hospital staff. However, social distancing and stay-at-home orders, which were universally adopted strategies to avoid the spread of COVID-19, led to unprecedented challenges. This study aimed to optimize warfarin treatment during the COVID-19 pandemic by determining the role of the Internet clinic and developing a machine learning (ML) model to predict anticoagulation quality. Methods: This retrospective study enrolled patients who received warfarin treatment in the hospital anticoagulation clinic (HAC) and “Internet + Anticoagulation clinic” (IAC) of the Nanjing Drum Tower Hospital between January 2020 and September 2021. The primary outcome was the anticoagulation quality of patients, which was evaluated by both the time in therapeutic range (TTR) and international normalized ratio (INR) variability. Anticoagulation quality and incidence of adverse events were compared between HAC and IAC. Furthermore, five ML algorithms were used to develop the anticoagulation quality prediction model, and the SHAP method was introduced to rank the feature importance. Results: Totally, 241 patients were included, comprising 145 patients in the HAC group and 96 patients in the IAC group. In the HAC group and IAC group, 73.1 and 69.8% (p = 0.576) of patients achieved good anticoagulation quality, with the average TTR being 79.9 ± 20.0% and 80.6 ± 21.1%, respectively. There was no significant difference in the incidence of adverse events between the two groups. Evaluating the five ML models using the test set, the accuracy of the XGBoost model was 0.767, and the area under the receiver operating characteristic curve was 0.808, which showed the best performance. The results of the SHAP method revealed that age, education, hypertension, aspirin, and amiodarone were the top five important features associated with poor anticoagulation quality. Conclusion: The IAC contributed to a novel management method for patients who received warfarin during the COVID-19 pandemic, as effective as HAC and with a low risk of virus transmission. The XGBoost model could accurately select patients at a high risk of poor anticoagulation quality, who could benefit from active intervention.

The Use of Oral Anticoagulation Is Not Associated With a Reduced Risk of Mortality in Patients With COVID-19: A Systematic Review and Meta-Analysis of Cohort Studies.

Background: Hypercoagulability and thromboembolic events are associated with poor prognosis in coronavirus disease 2019 (COVID-19) patients. Whether chronic oral anticoagulation (OAC) improve the prognosis is yet controversial. The present study aimed to investigate the association between the chronic OAC and clinical outcomes in COVID-19 patients. Methods: PubMed, Embase, Web of Science, and the Cochrane Library were comprehensively searched to identify studies that evaluated OAC for COVID-19 until 24 July 2021. Random-effects model meta-analyses were performed to pool the relative risk (RR) and 95% confidence interval (CI) of all-cause mortality and intensive care unit (ICU) admission as primary and secondary outcomes, respectively. According to the type of oral anticoagulants [direct oral anticoagulants (DOACs) or vitamin K antagonists (VKAs)], subgroup and interaction analyses were performed to compare DOACs and VKAs. Meta-regression was performed to explore the potential confounders on all-cause mortality. Results: A total of 12 studies involving 30,646 patients met the inclusion criteria. The results confirmed that chronic OAC did not reduce the risk of all-cause mortality (RR: 0.92; 95% CI 0.82-1.03; p = 0.165) or ICU admission (RR: 0.65; 95% CI 0.40-1.04; p = 0.073) in patients with COVID-19 compared to those without OAC. The chronic use of DOACs did not reduce the risk of all-cause mortality compared to VKAs (P interaction = 0.497) in subgroup and interaction analyses. The meta-regression failed to detect any potential confounding on all-cause mortality. Conclusion: COVID-19 patients with chronic OAC were not associated with a lower risk of all-cause mortality and ICU admission compared to those without OAC, and the results were consistent across DOACs and VKA subgroups. Systematic Review Registration: clinicaltrials.gov, identifier CRD42021269764.

Traditional Chinese medicine network pharmacology study on exploring the mechanism of Xuebijing Injection in the treatment of coronavirus disease 2019.

As a representative drug for the treatment of severe community-acquired pneumonia and sepsis, Xuebijing (XBJ) injection is also one of the recommended drugs for the prevention and treatment of coronavirus disease 2019 (COVID-19), but its treatment mechanism for COVID-19 is still unclear. Therefore, this study aims to explore the potential mechanism of XBJ injection in the treatment of COVID-19 employing network pharmacology and molecular docking methods. The corresponding target genes of 45 main active ingredients in XBJ injection and COVID-19 were obtained by using multiple database retrieval and literature mining. 102 overlapping targets of them were screened as the core targets for analysis. Then built the PPI network, TCM-compound-target-disease, and disease-target-pathway networks with the help of Cytoscape 3.6.1 software. After that, utilized DAVID to perform gene ontology (GO) function enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis to predict the action mechanism of overlapping targets. Finally, by applying molecular docking technology, all compounds were docked with COVID-19 3 CL protease(3CLpro), spike protein (S protein), and angiotensin-converting enzyme II (ACE2). The results indicated that quercetin, luteolin, apigenin and other compounds in XBJ injection could affect TNF, MAPK1, IL6 and other overlapping targets. Meanwhile, anhydrosafflor yellow B (AHSYB), salvianolic acid B (SAB), and rutin could combine with COVID-19 crucial proteins, and then played the role of anti-inflammatory, antiviral and immune response to treat COVID-19. This study revealed the multiple active components, multiple targets, and multiple pathways of XBJ injection in the treatment of COVID-19, which provided a new perspective for the study of the mechanism of traditional Chinese medicine (TCM) in the treatment of COVID-19.

Incidence of Venous Thromboembolism in Hospitalized Coronavirus Disease 2019 Patients: A Systematic Review and Meta-Analysis.

Background: Emerging evidence shows that coronavirus disease 2019 (COVID-19) is commonly complicated by coagulopathy, and venous thromboembolism (VTE) is considered to be a potential cause of unexplained death. Information on the incidence of VTE in COVID-19 patients, however, remains unclear. Method: English-language databases (PubMed, Embase, Cochrane), Chinese-language databases (CNKI, VIP, WANFANG), and preprint platforms were searched to identify studies with data of VTE occurrence in hospitalized COVID-19 patients. Pooled incidence and relative risks (RRs) of VTE were estimated by a random-effects model. Variations were examined based on clinical manifestations of VTE (pulmonary embolism-PE and deep vein thrombosis-DVT), disease severity (severe patients and non-severe patients), and rate of pharmacologic thromboprophylaxis (≥60 and <60%). Sensitivity analyses were conducted to strengthen the robustness of results. Meta-regression was performed to explore the risk factors associated with VTE in COVID-19 patients. Results: A total of 17 studies involving 1,913 hospitalized COVID-19 patients were included. The pooled incidence of VTE was 25% (95% CI, 19-31%; I 2, 95.7%), with a significant difference between the incidence of PE (19%; 95% CI, 13-25%; I 2, 93.2%) and DVT (7%; 95% CI, 4-10%; I 2, 88.3%; P interaction < 0.001). Higher incidence was observed in severe COVID-19 patients (35%; 95 CI%, 25-44%; I 2, 92.4%) than that in non-severe patients (6%; 95 CI%, 3-10%; I 2, 62.2%; P interaction < 0.001). The high rate of pharmacologic thromboprophylaxis in COVID-19 patients (≥60%) was associated with a lower incidence of VTE compared with the low pharmacologic thromboprophylaxis rate (<60%) (19 vs. 40%; P interaction = 0.052). Severe patients had a 3.76-fold increased risk of VTE compared with non-severe patients (RR, 4.76; 95% CI, 2.66-8.50; I 2, 47.0%). Sensitivity analyses confirmed the robustness of the primacy results. Conclusions: This meta-analysis revealed that the estimated VTE incidence was 25% in hospitalized COVID-19 patients. Higher incidence of VTE was observed in COVID-19 patients with a severe condition or with a low rate of pharmacologic thromboprophylaxis. Assessment of VTE risk is strongly recommended in COVID-19 patients, and effective measures of thromboprophylaxis should be taken in a timely manner for patients with high risk of VTE.