Stephansenbennett1419

OBJECTIVE We investigated the comparative efficacy and tolerability of pharmacological treatment strategies for the treatment of acute bipolar depression. DATA SOURCES A systematic review and network meta-analysis was conducted by searching eight registries for published and unpublished, double-blind, randomized controlled trials of pharmacotherapies for the acute treatment of bipolar depression. DATA EXTRACTION AND SYNTHESIS PRISMA guidelines were used for abstracting data, while the Cochrane Risk of Bias Tool was used to assess data quality. Data extraction was done independently by two reviewers, with discrepancies resolved by consensus. Data were pooled using a random-effects model. MAIN OUTCOMES AND MEASURES Primary outcomes were efficacy (response and remission rate) and acceptability (completion of treatment and dropouts due to adverse events). Summary odds ratios (ORs) were estimated using pairwise and network meta-analysis with random effects. RESULTS Identified citations (4,404) included 50 trials cdence-based practice and inform patients, physicians, guideline developers, and policymakers on the relative benefits of the different antidepressants, antipsychotics, and mood-stabilizing agents for the treatment of bipolar depression. REGISTRATION PROSPERO (CRD42019122172). BACKGROUND Postpartum depression (PPD) negatively impacts maternal health, parenting and development of children. Most previous studies on PPD risk factors are based on Western populations. Additionally, little is known about the association between psychosocial factors during early pregnancy period and PPD. We aimed to identify early risk factors for PPD until three months after delivery using a longitudinal population-based sample from Japan. METHODS The data was collected from 1050 mothers at four time points first trimester, after the birth, and one and three months post-delivery. Mothers who had a Japanese Edinburgh Postnatal Depression Scale (EPDS) cutoff score above 9 at one or 3 months after delivery were recognized as having PPD (n = 91/8.7%). RESULTS Negative feelings about pregnancy, combined breast and bottle feeding, first-time motherhood, motherhood 24 or less years old, perceived maternal mental illness before pregnancy, and lack of social support were all significantly associated with PPD at three months after delivery. LIMITATIONS The data was collected from one city in Japan, which limits the generalization of the findings. Additionally, PPD was assessed by an EPDS questionnaire, and not by a clinical interview. CONCLUSIONS Even after controlling for the perceived mental illness before pregnancy, several risk factors as early as in the first trimester were associated with PPD. These risk factors should be identified and the mothers should be offered a suitable intervention, in order to prevent the development of PPD. Training of a convolutional neural network (CNN) generally requires a large dataset. However, it is not easy to collect a large medical image dataset. The purpose of this study is to investigate the utility of synthetic images in training CNNs and to demonstrate the applicability of unrelated images by domain transformation. Mammograms showing 202 benign and 212 malignant masses were used for evaluation. To create synthetic data, a cycle generative adversarial network was trained with 599 lung nodules in computed tomography (CT) and 1430 breast masses on digitized mammograms (DDSM). A CNN was trained for classification between benign and malignant masses. The classification performance was compared between the networks trained with the original data, augmented data, synthetic data, DDSM images, and natural images (ImageNet dataset). selleck chemical The results were evaluated in terms of the classification accuracy and the area under the receiver operating characteristic curves (AUC). The classification accuracy improved from 65.7% to 67.1% with data augmentation. The use of an ImageNet pretrained model was useful (79.2%). Performance was slightly improved when synthetic images or the DDSM images only were used for pretraining (67.6 and 72.5%, respectively). When the ImageNet pretrained model was trained with the synthetic images, the classification performance slightly improved (81.4%), although the difference in AUCs was not statistically significant. The use of the synthetic images had an effect similar to the DDSM images. The results of the proposed study indicated that the synthetic data generated from unrelated lesions by domain transformation could be used to increase the training samples. In this work we examine some of the problems associated with the development of machine learning models with the objective to achieve robust generalization capabilities on common-task multiple-database scenarios. Referred to as the "database variability problem", we focus on a specific medical domain (sleep staging in sleep medicine) to show the non-triviality of translating the estimated model's local generalization capabilities into independent external databases. We analyze some of the scalability problems when multiple-database data are used as inputs to train a single learning model. Then, we introduce a novel approach based on an ensemble of local models, and we show its advantages in terms of inter-database generalization performance and data scalability. In addition, we analyze different model configurations and data pre-processing techniques to determine their effects on the overall generalization performance. For this purpose, we carry out experimentation that involves several sleep databases and evaluates different machine learning models based on convolutional neural networks. BACKGROUND This paper presents a novel iterative approach and rigorous accuracy testing for geometry modeling language - a Partition-based Optimization Model for Generative Anatomy Modeling Language (POM-GAML). POM-GAML is designed to model and create anatomical structures and their variations by satisfying any imposed geometric constraints using a non-linear optimization model. Model partitioning of POM-GAML creates smaller sub-problems of the original model to reduce the exponential execution time required to solve the constraints in linear time with a manageable error. METHOD We analyzed our model concerning the iterative approach and graph parameters for different constraint hierarchies. The iteration was used to reduce the error for partitions and solve smaller sub-problems generated by various clustering/community detection algorithms. We empirically tested our model with eleven graph parameters. Graphs for each parameter with increasing constraint sets were generated to evaluate the accuracy of our method.