Objective To predict the lymph node metastasis status of patients with invasive pulmonary adenocarcinoma by constructing machine learning models based on primary tumor radiomics, peritumoral radiomics, and habitat radiomics, and to evaluate the predictive performance and generalization ability of different imaging features. Methods A retrospective analysis was performed on the clinical data of 1 263 patients with invasive pulmonary adenocarcinoma who underwent surgery at the Department of Thoracic Surgery, Jiangsu Province Hospital, from 2016 to 2019. Habitat regions were delineated by applying K-means clustering (average cluster number of 2) to the grayscale values of CT images. The peritumoral region was defined as a uniformly expanded area of 3 mm around the primary tumor. The primary tumor region was automatically segmented using V-net combined with manual correction and annotation. Subsequently, radiomics features were extracted based on these regions, and stacked machine learning models were constructed. Model performance was evaluated on the training, testing, and internal validation sets using the area under the receiver operating characteristic curve (AUC), F1 score, recall, and precision. Results After excluding patients who did not meet the screening criteria, a total of 651 patients were included. The training set consisted of 468 patients (181 males, 287 females) with an average age of (58.39±11.23) years, ranging from 29 to 78 years, the testing set included 140 patients (56 males, 84 females) with an average age of (58.81±10.70) years, ranging from 34 to 82 years, and the internal validation set comprised 43 patients (14 males, 29 females) with an average age of (60.16±10.68) years, ranging from 29 to 78 years. Although the habitat radiomics model did not show the optimal performance in the training set, it exhibited superior performance in the internal validation set, with an AUC of 0.952 [95%CI (0.87, 1.00)], an F1 score of 84.62%, and a precision-recall AUC of 0.892, outperforming the models based on the primary tumor and peritumoral regions. Conclusion The model constructed based on habitat radiomics demonstrated superior performance in the internal validation set, suggesting its potential for better generalization ability and clinical application in predicting lymph node metastasis status in pulmonary adenocarcinoma.

Objective To explore the mechanism underlying the anti-hemorrhoid effects of Qingji Liangxue mixture(QLM).Methods Models of acute hemorrhoid in rats were established using a croton oil preparation(COP)and glacial acetic acid.A total of 80 SD female rats were randomly divided into two major groups:the COP group and the glacial acetic acid group,each consisting of 40 rats.In the COP group,rats were further randomly assigned to the following subgroups:control group 1(group CA),model group 1(group CB),low-dose QLM group 1-1(group CC),high-dose QLM group 1-2(group CD),and diosmin group 1(group CE),with eight rats in each subgroup.In the glacial acetic acid group,rats were randomly divided into the following subgroups:control group 2(group GA),model group 2(group GB),low-dose QLM group 2-1(group GC),high-dose QLM group 2-2(group GD),and diosmin group 2(group GE),with eight rats in each subgroup.Except for the control groups,all other subgroups were treated with COP or glacial acetic acid then treated with various drugs for 7 days.HE staining was used to observe anorectal histomorphology induced by COP and glacial acetic acid.ELIS As were used to measure serum levels of IL-6 and TNF-α induced by COP.Additionally,the area of perianal ulcers induced by glacial acetic acid was recorded.Twenty-four C57 mice were randomly divided into a control group(group A),low-dose QLM group(group B),high-dose QLM group(group C),and adrenal chromazone tablet group(group D).Results QLM significantly improved the pathological injury of animal models with similar hemorrhoids,reduced the score of pathological changes induced by COP(P＜0.05),reduced the serum levels of IL-6 and TNF-α(P＜0.05),reduced the area of perianal ulcers induced by glacial acetic acid(P＜0.05),and shortened the time of coagulation and bleeding(P＜0.05).Conclusions QLM has a good anti-hemorrhoid activity,which may be achieved by anti-inflammatory effects,hemostasis,and reducing tissue damage.

Stroke has become one of the main causes of death in China, and ischemic stroke is the most common type. At the same time, the prevalence of chronic kidney disease (CKD) is also increasing, and there are many similar risk factors with ischemic stroke. More and more studies have shown that CKD increases the incidence, severity and risk of poor outcome of ischemic stroke, but the specific mechanism of its interaction is not completely clear. For ischemic stroke patients with CKD, the most effective treatment and prevention measures are lack of sufficient evidence. This article reviews the relationship between CKD and ischemic stroke, as well as the treatment and prevention.

Objective To analyze the reasons of invalid detections occurred in using three kinds of nucleic acid detection systems in our laboratory since 2016.Methods Analyze the numbers and types of invalid detections,for Roche Cobas S201 system from January to December 2016,Procleix Tigris system from January to September 2016,and Procleix Panther system from September 2016 to March 2017,respectively.Results The invalidation rates of Cobas s201,Tigris,and Panther systems were 0.90％ (402/44 838),4.01％ (2 960/73 835),and 1.34％ (1 093/81 741),respectively,and there were statistically significant differences between the three detection systems (P＜0.05).Except for the differences between Roche Cobas s201 and Panther 1404,there were statistically significant differences between instruments (P＜0.05).Failure of instruments,invalid detection of reagent calibrators,fault operation and sample quality are the causes of invalid detection.Conelusion The main reason of invalidation is instrument failure and reagent calibrator failmre.Invalid detections of nucleic acid screening is related on different detection systems.