scholarly journals Public Covid-19 X-ray datasets and their impact on model bias – A systematic review of a significant problem

2021 ◽  
Vol 74 ◽  
pp. 102225
Author(s):  
Beatriz Garcia Santa Cruz ◽  
Matías Nicolás Bossa ◽  
Jan Sölter ◽  
Andreas Dominik Husch
Keyword(s):  
Systematic Review ◽  
Significant Problem ◽  
Model Bias ◽  
X Ray

scholarly journals Magnitude and determinants of neural tube defect in Africa: a systematic review and meta-analysis

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Daniel Atlaw ◽  
Yohannes Tekalegn ◽  
Biniyam Sahiledengle ◽  
Kenbon Seyoum ◽  
Damtew Solomon ◽  
...  
Keyword(s):  
Systematic Review ◽  
Neural Tube ◽  
Meta Analysis ◽  
Random Effect ◽  
Random Effect Model ◽  
Folic Acid Supplementation ◽  
Maternal Exposure ◽  
X Ray ◽  
Effect Model ◽  
Pooled Prevalence

Abstract Background Neural tube defects (NTDs) are a group of disorders that arise from the failure of the neural tube close between 21 and 28 days after conception. About 90% of neural tube defects and 95% of death due to these defects occurs in low-income countries. Since these NTDs cause considerable morbidity and mortality, this study aimed to determine the prevalence and associated factors of NTDs in Africa. Methods The protocol of this study was registered in the International Prospective Register of Systematic Reviews (PROSPERO number: CRD42020149356). All major databases such as PubMed/MEDLINE, EMBASE, CINAHL, Web of Science, African Journals Online (AJOL), and Google Scholar search engine were systematically searched. A random-effect model was used to estimate the pooled prevalence of NTDs in Africa, and Cochran’s Q-statistics and I2 tests were used to assess heterogeneity between included studies. Publication bias was assessed using Begg ’s tests, and the association between determinant factors and NTDs was estimated using a random-effect model. Results Of the total 2679 articles, 37 articles fulfilled the inclusion criteria and were included in this systematic review and meta-analysis. The pooled prevalence of NTDs in Africa was 50.71 per 10,000 births (95% CI: 48.03, 53.44). Folic acid supplementation (AOR: 0.40; 95% CI: 0.19–0.85), maternal exposure to pesticide (AOR: 3.29; 95% CI: 1.04–10.39), mothers with a previous history of stillbirth (AOR: 3.35, 95% CI: 1.99–5.65) and maternal exposure to x-ray radiation (AOR 2.34; 95% CI: 1.27–4.31) were found to be determinants of NTDs. Conclusions The pooled prevalence of NTDs in Africa was found to be high. Maternal exposure to pesticides and x-ray radiation were significantly associated with NTDs. Folic acid supplementation before and within the first month of pregnancy was found to be a protective factor for NTDs.

scholarly journals The systematic review and meta-analysis of X-ray detective rate of Kashin-Beck disease from 1992 to 2016

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Xi Wang ◽  
Yujie Ning ◽  
Amin Liu ◽  
Xin Qi ◽  
Meidan Liu ◽  
...  
Keyword(s):  
Systematic Review ◽  
Meta Analysis ◽  
X Ray ◽  
Beck Disease

scholarly journals The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2206
Author(s):  
Dana Li ◽  
Lea Marie Pehrson ◽  
Carsten Ammitzbøl Lauridsen ◽  
Lea Tøttrup ◽  
Marco Fraccaro ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Assessment Tool ◽  
Cochrane Library ◽  
Original Research ◽  
Quality Assessment Tool ◽  
Bias Assessment ◽  
X Ray ◽  
Chest X Ray ◽  
Sensitivity Specificity

Our systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE, PubMed, Cochrane library, SCOPUS, and Web of Science were retrieved. Included articles were published within the last 20 years and used a device based on artificial intelligence (AI) technology to detect or diagnose pulmonary findings. The AI-based device had to be used in an observer test where the performance of human observers with and without addition of the device was measured as sensitivity, specificity, accuracy, AUC, or time spent on image reading. A total of 38 studies were included for final assessment. The quality assessment tool for diagnostic accuracy studies (QUADAS-2) was used for bias assessment. The average sensitivity increased from 67.8% to 74.6%; specificity from 82.2% to 85.4%; accuracy from 75.4% to 81.7%; and Area Under the ROC Curve (AUC) from 0.75 to 0.80. Generally, a faster reading time was reported when radiologists were aided by AI-based devices. Our systematic review showed that performance generally improved for the physicians when assisted by AI-based devices compared to unaided interpretation.

scholarly journals A systematic review of the clinical effectiveness of EOS 2D/3D X-ray imaging system

2012 ◽  
Vol 22 (2) ◽  
pp. 296-304 ◽  
Author(s):  
Ros Wade ◽  
Huiqin Yang ◽  
Claire McKenna ◽  
Rita Faria ◽  
Nigel Gummerson ◽  
...  
Keyword(s):  
Systematic Review ◽  
Imaging System ◽  
Clinical Effectiveness ◽  
X Ray ◽  
X Ray Imaging

Radio-protective Effects and Mechanisms of Medicinal Plants against X-ray: A Systematic Review

2019 ◽  
Vol 25 (1) ◽  
pp. 1-11
Author(s):  
Mohamad Ali Dayani ◽  
Saeid Heidari-Soureshjani ◽  
Johannes Salcher
Keyword(s):  
Systematic Review ◽  
Medicinal Plants ◽  
Protective Effects ◽  
X Ray

scholarly journals Triceps Tendon Ruptures: A Systematic Review

Hand ◽  
2016 ◽  
Vol 12 (5) ◽  
pp. 431-438 ◽  
Author(s):  
John C. Dunn ◽  
Nicholas Kusnezov ◽  
Austin Fares ◽  
Sydney Rubin ◽  
Justin Orr ◽  
...  
Keyword(s):  
Systematic Review ◽  
Renal Disease ◽  
Anabolic Steroid ◽  
Steroid Use ◽  
Medical Comorbidities ◽  
X Ray ◽  
Delay In Diagnosis ◽  
Lateral Elbow ◽  
Tendon Ruptures ◽  
Triceps Tendon

Background: Triceps tendon ruptures (TTR) are an uncommon injury. The aim of this systematic review was to classify diagnostic signs, report outcomes and rerupture rates, and identify potential predisposing risk factors in all reported cases of surgical treated TTR. Methods: A literature search collecting surgical treated cases of TTR was performed, identifying 175 articles, 40 of which met inclusion criteria, accounting for 262 patients. Data were pooled and analyzed focusing on medical comorbidities, presence of a fleck fracture on the preoperative lateral elbow x-ray film (Dunn-Kusnezov Sign [DKS]), outcomes, and rerupture rates. Results: The average age of injury was 45.6 years. The average time from injury to day of surgery was 24 days while 10 patients had a delay in diagnosis of more than 1 month. Renal disease (10%) and anabolic steroid use (7%) were the 2 most common medical comorbidities. The DKS was present in 61% to 88% of cases on the lateral x-ray film. Postoperatively, 89% of patients returned to preinjury level of activity, and there was a 6% rerupture rate at an average follow-up of 34.6 months. The vast majority (81%) of the patients in this review underwent repair via suture fixation. Conclusions: TTR is an uncommon injury. Risks factors for rupture include renal disease and anabolic steroid use. Lateral elbow radiographs should be scrutinized for the DKS in patients with extension weakness. Outcomes are excellent following repair, and rates of rerupture are low.

scholarly journals Public Covid-19 X-ray datasets and their impact on model bias - a systematic review of a significant problem

2021 ◽  
Author(s):  
Beatriz Garcia Santa Cruz ◽  
Matías Nicolás Bossa ◽  
Jan Sölter ◽  
Andreas Dominik Husch
Keyword(s):  
Systematic Review ◽  
Prediction Models ◽  
Risk Of Bias ◽  
Systematic Evaluation ◽  
Bias Assessment ◽  
X Ray ◽  
Inappropriate Use ◽  
Chest X Ray ◽  
Almost All ◽  
Aided Diagnosis

ABSTRACTComputer-aided-diagnosis for COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and improper consideration of confounders prevents the translation of prediction models into clinical practice. This study provides a systematic evaluation of publicly available COVID-19 chest X-ray datasets, determining their potential use and evaluating potential sources of bias.Only 5 out of 256 identified datasets met at least the criteria for proper assessment of risk of bias and could be analysed in detail. Remarkably almost all of the datasets utilised in 78 papers published in peer-reviewed journals, are not among these 5 datasets, thus leading to models with high risk of bias. This raises concerns about the suitability of such models for clinical use.This systematic review highlights the limited description of datasets employed for modelling and aids researchers to select the most suitable datasets for their task.

scholarly journals EOS 2D/3D X-ray imaging system: a systematic review and economic evaluation

2012 ◽  
Vol 16 (14) ◽  
Author(s):  
C McKenna ◽  
R Wade ◽  
R Faria ◽  
H Yang ◽  
L Stirk ◽  
...  
Keyword(s):  
Systematic Review ◽  
Economic Evaluation ◽  
Imaging System ◽  
X Ray ◽  
System A ◽  
X Ray Imaging
Sign in / Sign up

Export Citation Format

Share Document