Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations that are not directly amenable to the tabular domain. Instead, we introduce Contrastive Mixup, a semisupervised learning framework for tabular data and demonstrate its effectiveness in limited annotated data settings. Our proposed method leverages Mixup-based augmentation under the manifold assumption by mapping samples to a low dimensional latent space and encourage interpolated samples to have high a similarity within the same labeled class. Unlabeled samples are additionally employed via a transductive label propagation method to further enrich the set of similar and dissimilar pairs that can be used in the contrastive loss term. We demonstrate the effectiveness of the proposed framework on public tabular datasets and real-world clinical datasets.Preprint. Under review.
Background: Infection with human immunodeficiency virus (HIV) leads to cellular immune deficiency and theoretically patients infected with HIV are susceptible to brucellosis. Objectives: The current study aimed to determine brucellosis rate in the patients infected with HIV. Patients and Methods: We included 89 HIV + patients from Sanandaj Consultation Center for Behavioral Diseases. Patients signed informed written consent before filling out the questionnaire. After serum collection, standard Wright tube, Coombs-Wright and 2ME-Wright tests were performed. Moreover, blood samples obtained from 502 individuals, who were not infected with HIV, were served as the control.
Results:The mean age of participants in the experimental and control groups were 33.31 ± 7.47 and 34.38 ± 11.29 years, respectively. In the Wright tube test for the HIV + group, 71 individuals (79.8%) did not have an antibody against Brucella spp., while 18 patients (20.2%) were positive for the antibody. According to the results of Wright tube test for the control group, 63 (12.5%) participants were positive for antiBrucella antibody. The frequency of antibody against Brucella spp. in the HIV + group was significantly higher than that of the control group (P = 0.042). Conclusions: HIV positive individuals in areas endemic for brucellosis must be investigated for the disease.
Background: Vitamin D deficiency is one of the most common
nutritional deficiencies. Cardiovascular disease patients are also prone
to this condition. Recently, a relationship between vitamin D deficiency
and cardiovascular diseases has been suggested. This study aims to
compare the relationship between ventricular systolic function and
vitamin D deficiency. Methods: This study investigated patients
without obvious coronary artery disease between 2020 and 2021. First,
vitamin D levels were measured in the patients. Then, they were divided
into two groups based on a 30 ng/dl cut-off point. All patients
underwent echocardiography and ventricular systolic function parameters
were evaluated and compared. Results: In this study, 27
patients with normal vitamin D levels and 47 patients with vitamin D
deficiency entered the study. There was no significant difference in
demographic variables and underlying diseases between these two groups.
There was no significant difference between left ventricular (LV)
systolic function parameters including ejection fraction (EF), and LV
end-systolic/diastolic volume. No significant difference was also
observed between right ventricular (RV) systolic function parameters
including Tricuspid Annular Plane Systolic Excursion (TAPSE), RV
fractional area change (RVFAC), Right ventricular systolic velocity
(RVSM) in tissue Doppler echocardiography as well as RV diastolic
parameters such as A, E, E´, deceleration time (DT), right atrial volume
(RAVi) as a precursor of right ventricular systolic dysfunction groups.
Conclusion: Based on the results of this study, there is no
relationship between vitamin D levels and ventricular systolic
dysfunction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.