Patients with liver disease are at an increased risk of both embolism and bleeding. The optimal anticoagulation strategy remains unclear when associated with venous thromboembolic disease. Moreover, currently approved oral anticoagulant drugs undergo metabolism and elimination in the liver with varying degrees of hepatic dysfunction. Thus, impaired liver function may lead to increased risk of bleeding, making anticoagulant therapy more intricate. This article summarizes the risk of bleeding and thrombosis in patients with liver disease, and the clinical research progress of oral anticoagulants in patients with liver disease to facilitate evidence for choosing oral anticoagulants therapy when required.

Objective To explore how clinical pharmacists participate in clinical drug practice.Methods Clinical pharmacists involved in the treatment of one lymphocytic hyophysitis case with glucocorticoid and provided patient with medication education to ensure the safe and effective treatment.Results Pharmacists offered an effective and feasible treatment program for doctors and the patient.Conclusion Clinical pharmacists participated actively in the clinical treatment programs to ensure the effective development of clinical diagnosis and treatment and improve the medication therapy results.

Machine learning has been applied in the medical field due to its powerful data analysis and exploration capabilities. In recent years， more and more studies have applied it to therapeutic drug monitoring and individual drug therapy of immunosuppressants， anti-infective drugs， antiepileptic drugs， etc. Compared with the traditional population pharmacokinetic modeling methods， the constructed models based on machine learning can predict blood drug concentration and drug dose more accurately， improve the level of clinical precision drug use and reduce the occurrence of adverse drug reactions. Based on this， this article reviews the application of machine learning in therapeutic drug monitoring and individual drug therapy， with a view to providing theoretical basis and technical support for clinical precise drug use.

Objective:To describe the COVID-19 epidemic and its characteristics in Heilongjiang province, and provide evidence for the further prevention and control of COVID-19 in the province.Methods:The information of COVID-19 cases and clusters were collected from national notifiable disease report system and management information system for reporting public health emergencies of China CDC. The Software’s of Excel 2010 and SPSS 23.0 were applied for data cleaning and statistical analysis on the population, time and area distributions of COVID-19 cases.Results:On January 22, 2020, the first confirmed case of COVID-19 was reported in Heilongjiang. By March 11, 2020, a total of 482 cases domestic case of COVID-19, The incidence rate was 1.28/100 000, the mortality rate was 2.70% (13/482) in 13 municipalities in Heilongjiang. There were 81 clusters of COVID-19, The number of confirmed cases accounted for 79.25% (382/482) of the total confirmed cases and 12 cases of deaths. The family clusters accounted for 86.42% (70/81). Compared with the sporadic cases, the mortality rate, proportion of elderly cases aged 60 or above and severe or critical cases of clinical classification were all higher in the clusters especially the family clusters, but the differences were not significant ( P>0.05). There were 34 clusters involving more than 5 confirmed cases accounted for 41.98% (34/81) of the total clusters, the involved cases accounted for 68.31% (261/382) of the total cases of clusters. There were significant differences in age distribution of the cases among the case clusters with different case numbers. In the clusters involving 6-9 cases, the proportion of cases aged 65 years or above was more (26.53%, 39/147). Conclusions:The incidence rate of COVID-19 was relatively high and the early epidemic was serious in Heilongjiang, The number of cases was large in clusters especially family clusters.