简介：无

简介：AbstractBackground:The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images.Methods:Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR-), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists.Results:The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87-0.91, 0.89-0.92, 0.87-0.91, and 0.86-0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P < 0.001). The accuracy of the CNN classifications for the test set (89.2%) was significantly higher than that of all the radiologists (30%).Conclusions:The CNN may have high accuracy for classification of US images of breast masses and perform significantly better than human radiologists.Trial registration:Chictr.org, ChiCTR1900021375; http://www.chictr.org.cn/showproj.aspx?proj=33139.

简介：无

简介：AbstractBackground:Lipid abnormalities are prevalent among people living with human immunodeficiency virus (HIV) (PLWH) and contribute to increasing risk of cardiovascular events. This study aims to investigate the incidence of dyslipidemia and its risk factors in PLWH after receiving different first-line free antiretroviral regimens.Methods:PLWH who sought care at the Third People’s Hospital of Shenzhen from January 2014 to December 2018 were included, and the baseline characteristics and clinical data during the follow-up were collected, including total cholesterol (TC), triglyceride (TG), low-density lipoprotein cholesterol (LDL-C) and high-density lipoprotein cholesterol (HDL-C). The risk factors of dyslipidemia after antiretroviral therapy were analyzed with the generalized estimating equation model.Results:Among the 7623 PLWH included, the mean levels of TC, HDL-C and LDL-C were 4.23 ± 0.85 mmol/L, 1.27 ± 0.29 mmol/L and 2.54 ± 0.65 mmol/L, respectively, and the median TG was 1.17 (IQR: 0.85-1.68) mmol/L. Compared with that in PLWH receiving tenofovir disoproxil fumarate (TDF) + lamivudine (3TC) + ritonavir-boosted lopinavir (LPV/r), zidovudine (AZT) + 3TC + efavirenz (EFV), and AZT + 3TC + LPV/r, the incidence of dyslipidemia was lower in PLWH receiving TDF + 3TC + EFV. In multivariate analysis, we found that the risks of elevations of TG, TC, and LDL-C were higher with TDF + 3TC + LPV/r (TG: odds ratio [OR] = 2.82, 95% confidence interval [CI]: 2.55-3.11, P < 0.001; TC: OR = 1.24, 95% CI: 1.14-1.35, P < 0.001; LDL: OR = 1.06, 95% CI: 1.00-1.12, P = 0.041), AZT + 3TC + EFV (TG: OR = 1.41, 95% CI: 1.28-1.55, P < 0.001; TC: OR = 1.43, 95% CI: 1.31-1.56, P < 0.001; LDL: OR = 1.18, 95% CI: 1.12-1.25, P < 0.001), and AZT + 3TC + LPV/r (TG: OR = 3.08, 95% CI: 2.65-3.59, P < 0.001; TC: OR = 2.40, 95% CI: 1.96-2.94, P < 0.001; LDL: OR = 1.52, 95% CI: 1.37-1.69, P < 0.001) than with TDF + 3TC + EFV, while treatment with TDF + 3TC + LPV/r was less likely to restore HDL-C levels compared with TDF + 3TC + EFV (OR = 0.95, 95% CI: 0.92-0.97, P < 0.001). In addition to antiretroviral regimens, antiretroviral therapy duration, older age, overweight, obesity and other traditional factors were also important risk factors for dyslipidemia.Conclusion:The incidence of dyslipidemia varies with different antiretroviral regimens, with TDF + 3TC + EFV having lower risk for dyslipidemia than the other first-line free antiretroviral regimens in China.

简介：AbstractBackground:Albuvirtide is a once-weekly injectable human immunodeficiency virus (HIV)-1 fusion inhibitor. We present interim data for a phase 3 trial assessing the safety and efficacy of albuvirtide plus lopinavir-ritonavir in HIV-1-infected adults already treated with antiretroviral drugs.Methods:We carried out a 48-week, randomized, controlled, open-label non-inferiority trial at 12 sites in China. Adults on the World Health Organization (WHO)-recommended first-line treatment for >6 months with a plasma viral load >1000 copies/mL were enrolled and randomly assigned (1:1) to receive albuvirtide (once weekly) plus ritonavir-boosted lopinavir (ABT group) or the WHO-recommended second-line treatment (NRTI group). The primary endpoint was the proportion of patients with a plasma viral load below 50 copies/mL at 48 weeks. Non-inferiority was prespecified with a margin of 12%.Results:At the time of analysis, week 24 data were available for 83 and 92 patients, and week 48 data were available for 46 and 50 patients in the albuvirtide and NRTI groups, respectively. At 48 weeks, 80.4% of patients in the ABT group and 66.0% of those in the NRTI group had HIV-1 RNA levels below 50 copies/mL, meeting the criteria for non-inferiority. For the per-protocol population, the superiority of albuvirtide over NRTI was demonstrated. The frequency of grade 3 to 4 adverse events was similar in the two groups; the most common adverse events were diarrhea, upper respiratory tract infections, and grade 3 to 4 increases in triglyceride concentration. Renal function was significantly more impaired at 12 weeks in the patients of the NRTI group who received tenofovir disoproxil fumarate than in those of the ABT group.Conclusions:The TALENT study is the first phase 3 trial of an injectable long-acting HIV drug. This interim analysis indicates that once-weekly albuvirtide in combination with ritonavir-boosted lopinavir is well tolerated and non-inferior to the WHO-recommended second-line regimen in patients with first-line treatment failure.Trial registration:ClinicalTrials.gov Identifier: NCT02369965; https://www.clinicaltrials.gov.Chinese Clinical Trial Registry No. ChiCTR-TRC-14004276; http://www.chictr.org.cn/enindex.aspx

简介：无

简介：无

简介：无

简介：无

简介：AbstractBackground:Blood glucose control is closely related to type 2 diabetes mellitus (T2DM) prognosis. This multicenter study aimed to investigate blood glucose control among patients with insulin-treated T2DM in North China and explore the application value of combining an elastic network (EN) with a machine-learning algorithm to predict glycemic control.Methods:Basic information, biochemical indices, and diabetes-related data were collected via questionnaire from 2787 consecutive participants recruited from 27 centers in six cities between January 2016 and December 2017. An EN regression was used to address variable collinearity. Then, three common machine learning algorithms (random forest [RF], support vector machine [SVM], and back propagation artificial neural network [BP-ANN]) were used to simulate and predict blood glucose status. Additionally, a stepwise logistic regression was performed to compare the machine learning models.Results:The well-controlled blood glucose rate was 45.82% in North China. The multivariable analysis found that hypertension history, atherosclerotic cardiovascular disease history, exercise, and total cholesterol were protective factors in glycosylated hemoglobin (HbA1c) control, while central adiposity, family history, T2DM duration, complications, insulin dose, blood pressure, and hypertension were risk factors for elevated HbA1c. Before the dimensional reduction in the EN, the areas under the curve of RF, SVM, and BP were 0.73, 0.61, and 0.70, respectively, while these figures increased to 0.75, 0.72, and 0.72, respectively, after dimensional reduction. Moreover, the EN and machine learning models had higher sensitivity and accuracy than the logistic regression models (the sensitivity and accuracy of logistic were 0.52 and 0.56; RF: 0.79, 0.70; SVM: 0.84, 0.73; BP-ANN: 0.78, 0.73, respectively).Conclusions:More than half of T2DM patients in North China had poor glycemic control and were at a higher risk of developing diabetic complications. The EN and machine learning algorithms are alternative choices, in addition to the traditional logistic model, for building predictive models of blood glucose control in patients with T2DM.

简介：AbstractPurpose:The purpose of this study was to review the microsurgical anatomy and clipping of ruptured anterior communicating artery (AComA) aneurysms and to plan and avoid complications before operation.Methods:A total of 523 cases of cerebral aneurysms admitted to the neurosurgery department of the Third Affiliated Hospital of Sun Yat-Sen University from September 2010 to October 2018 were analyzed retrospectively. Among them, 85 patients had ruptured AComA aneurysms. This study was limited to 85 of these cases, whose satisfactory preoperative angiographic diagnostic films can be retrieved from the hospital database system because of the need for detailed review.Results:We performed supraorbital eyebrow keyhole approach (SOEK) craniotomy in 85 patients to clip 85 AComA aneurysms, in the setting of subarachnoid hemorrhage (SAH). Patients’ mean age was (52.69 ± 9.94) years (range, 28-78 years). The proportions of small, medium and large aneurysms were 83.5%, 15.3%, and 1.2%, respectively. The average size of the aneurysms was (5.07 ± 2.36) mm. There were 77.8% of patients with inferior aneurysms and 81.3% of patients with superior aneurysms achieved good results. There was a significant correlation between A1 dominance and operation method (p < 0.001). There was no significant relationship between surgical approach and aneurysm projection or A2 plane (p = 0.157 & p = 0.318).Conclusion:Regardless of whether the A2 plane is open or closed, the A1 dominant side is still a better choice for accessing AComA aneurysms to avoid dangerous premature bleeding.