metadata
license: openrail
metrics:
- type: f1
value: 0.93
library_name: transformers
pipeline_tag: text-classification
tags:
- medical
- biomedical
- rct
widget:
- text: |-
TITLE:
The Effect of Combined Vitamin C and Vitamin E Supplementation on Oxidative Stress Markers in Women with Endometriosis: A Randomized, Triple-Blind Placebo-Controlled Clinical Trial
ABSTRACT:
Background: Endometriosis is a chronic and estrogen-dependent pelvic inflammatory disease, which may have various causes, such as oxidative stress. Dysmenorrhea, dyspareunia, and pelvic pain are well-known symptoms of endometriosis. The present clinical trial assessed the role of supplementation with antioxidant vitamins on the indices of oxidative stress as well as the severity of pain in women with endometriosis.
Materials and methods: We enrolled 60 reproductive-aged (15-45 years) women with pelvic pain in this triple-blind clinical trial. They had 1-3 stages of laparoscopic-proven endometriosis. The participants were randomized to group A (n = 30), given vitamin C (1000 mg/day, 2 tablets of 500 mg each) and vitamin E (800 IU/day, 2 tablets of 400 IU each) combination, or group B (n = 30), given placebo pills daily for 8 weeks.
Results: Following treatment with vitamin C and vitamin E, we found a significant reduction in MDA and ROS compared with the placebo group. There was no significant decline in total antioxidant capacity after treatment. However, the severity of pelvic pain (p value <0.001), dysmenorrhea (p value <0.001), and dyspareunia (p value <0.001) significantly decreased in the treatment group after 8 weeks of supplementation.
Conclusions: The present findings support the potential role of antioxidants in the management of endometriosis. The intake of vitamin C and vitamin E supplements effectively reduced dysmenorrhea severity and improved dyspareunia and severity of pelvic pain.
output:
- label: '1'
score: 0.688
- label: '0'
score: 0.312
System RCT Classifier
Description
This is a BERT-based model intended for identifying Randomized-Controlled Trials based on title and abstract. It is fine-tuned based on https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract, with an additional binary classifier layer.
Model Performance
F1 Score
In out-of-sample testing, the model exhibits an F1 score of 0.93 on a sample of 500 abstracts from PubMed.
Confusion Matrix
Use
This model is made available under the Open RAIL-M license.
For more information on System, visit https://about.system.com