Accuracy of Several Cervical Screening Strategies for Early Detection of Cervical Cancer: A Meta-Analysis

2012 ◽  
Vol 22 (6) ◽  
pp. 908-921 ◽  
Author(s):  
Changxian Chen ◽  
Zhijun Yang ◽  
Zhuang Li ◽  
Li Li
Keyword(s):  
Cervical Cancer ◽  
Acetic Acid ◽  
Visual Inspection ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Cervical Screening ◽  
Diagnostic Odds Ratio ◽  
Screening Strategies ◽  
Hybrid Capture 2

ObjectiveThe objectives of this study were to assess the accuracy of 6 common cervical screening strategies, including visual inspection with acetic acid, with a magnifying device, or with Lugol iodine (VILI), human papillomavirus testing with Hybrid Capture 2 assay, conventional Papanicolaou smear, and thin liquid-based cytology (LBC), and then to compare data obtained by the aforementioned 6 strategies.MethodsPubMed, EMBASE, and The Cochrane Library were systematically searched for all original relevant studies about early detection of cervical cancer. A meta-analysis was performed to evaluate the accuracy of the 6 screening strategies covering sensitivity, specificity, diagnostic odds ratio, and the area under the receiver operating characteristic curve.ResultsFifteen articles containing 22 cross-sectional studies were finally identified. The combined estimates of sensitivity for visual inspection with acetic acid, magnified visual inspection with acetic acid, VILI, Hybrid Capture 2 assay, conventional Papanicolaou smear, and LBC were 77%, 64%, 91%, 74%, 59%, and 88%, respectively; the combined values of specificity of these screening strategies were 87%, 86%, 85%, 92%, 94%, and 88%, respectively; the diagnostic odds ratio were 22.43, 10.30, 57.44, 33.26, 22.49, and 51.56, respectively; and the area under the receiver operating characteristic curve were 0.8918, 0.7737, 0.9365, 0.9486, 0.9079, and 0.9418, respectively.ConclusionsThis meta-analysis suggests that LBC appeared to be promising in primary cervical cancer screening in resourced regions, and VILI might be a good choice to identify/exclude cervical cancerous and precancerous lesions in resource-constrained regions.

Diagnostic value of HOX transcript antisense RNA for cancer detection: a meta-analysis

2020 ◽  
Vol 14 (5) ◽  
pp. 401-411
Author(s):  
Weihao Kong ◽  
Mingwei Yang ◽  
Yunfeng Zhu ◽  
Xiaomin Zuo ◽  
Hengyi Wang ◽  
...  
Keyword(s):  
Likelihood Ratio ◽  
Antisense Rna ◽  
Noncoding Rna ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Sensitivity Specificity

Aim: Numerous studies have investigated the diagnostic role of long noncoding RNA HOX transcript antisense RNA in cancers, but its diagnostic efficacy is inconsistent. Methods: The PubMed, Embase, Web of Science and Cochrane Library databases are used to retrieve relevant studies. The bivariate effect model was used to compute the combined sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio and area under the receiver operating characteristic curve. Results: A total of 13 studies were included in this meta-analysis. The combined sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio and area under the receiver operating characteristic curve were: 0.77, 0.83, 4.7, 0.28, 17 and 0.87, respectively. Deeks’ funnel plot test (p = 0.103) indicated no publication bias. Conclusion: Long noncoding RNA HOX transcript antisense RNA may be a useful biomarker for cancer detection.

scholarly journals Visual Inspection of Cervix with Acetic Acid (VIA) as a Screening Tool for Early Detection of Cervical Pre-Cancer & Cancer.

2018 ◽  
Vol 13 (1) ◽  
pp. 24-27
Author(s):  
Zebunnessa Parvin ◽  
Lutfun Naher ◽  
Sanjoy Kumar Das ◽  
Shafeya Khanam ◽  
Nasrin Rosy
Keyword(s):  
Cervical Cancer ◽  
Acetic Acid ◽  
Early Detection ◽  
Visual Inspection ◽  
Health Workers ◽  
Cervical Screening ◽  
Public Health Problem ◽  
World Health ◽  
Major Public Health Problem ◽  
Screening Programs

Cervical cancer continues to be a major public health problem in Bangladesh in the absence of satisfactory and organized cervical screening programs. World Health Organization (WHO) considered cervical cancer as a preventable disease, as it can be identified in the pre-invasive stage. Visual inspection of the cervix with acetic acid (VIA) is an effective, inexpensive screening test that can be combined with simple treatment procedure for early cervical lesions, provided by trained health workers. To evaluate the value of visual inspection with acetic acid (VIA) for early detection of cervical pre-cancer and cancer in low resource country like Bangladesh, diluted acetic acid 5% was applied to the cervix and visual inspection was done. VIA tests were done for at least 3 years interval, in case of married woman, for cervical cancer screening. Women with positive results were sent for colposcopy. From January to December 2014, in Gynae OPD of the Faridpur Medical College Hospital, Faridpur, a total of 2000 women were screened by VIA test. Fourty-one VIA positive cases were identified and referred for colposcopy. Out of 41 cases, 27 patients underwent colposcopic examination, among them CIN-1 was found in 21 cases, CIN-2 in 2 cases and CIN-3 in 2 cases. However, two cases were colposcopically negative. So even during gynecological practice, if we arrange a setup for cervical screening by VIA test, many women can be saved from future development of carcinoma cervix later in their lives.Faridpur Med. Coll. J. Jan 2018;13(1): 24-27

scholarly journals Application of Artificial Intelligence for Screening COVID-19 Patients Using Digital Images: Meta-analysis

10.2196/21394 ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. e21394
Author(s):  
Tahmina Nasrin Poly ◽  
Md Mohaimenul Islam ◽  
Yu-Chuan Jack Li ◽  
Belal Alsinglawi ◽  
Min-Huei Hsu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Diagnostic Odds Ratio ◽  
Study Characteristics ◽  
Key Terms ◽  
Immense Potential

Background The COVID-19 outbreak has spread rapidly and hospitals are overwhelmed with COVID-19 patients. While analysis of nasal and throat swabs from patients is the main way to detect COVID-19, analyzing chest images could offer an alternative method to hospitals, where health care personnel and testing kits are scarce. Deep learning (DL), in particular, has shown impressive levels of performance when analyzing medical images, including those related to COVID-19 pneumonia. Objective The goal of this study was to perform a systematic review with a meta-analysis of relevant studies to quantify the performance of DL algorithms in the automatic stratification of COVID-19 patients using chest images. Methods A search strategy for use in PubMed, Scopus, Google Scholar, and Web of Science was developed, where we searched for articles published between January 1 and April 25, 2020. We used the key terms “COVID-19,” or “coronavirus,” or “SARS-CoV-2,” or “novel corona,” or “2019-ncov,” and “deep learning,” or “artificial intelligence,” or “automatic detection.” Two authors independently extracted data on study characteristics, methods, risk of bias, and outcomes. Any disagreement between them was resolved by consensus. Results A total of 16 studies were included in the meta-analysis, which included 5896 chest images from COVID-19 patients. The pooled sensitivity and specificity of the DL models in detecting COVID-19 were 0.95 (95% CI 0.94-0.95) and 0.96 (95% CI 0.96-0.97), respectively, with an area under the receiver operating characteristic curve of 0.98. The positive likelihood, negative likelihood, and diagnostic odds ratio were 19.02 (95% CI 12.83-28.19), 0.06 (95% CI 0.04-0.10), and 368.07 (95% CI 162.30-834.75), respectively. The pooled sensitivity and specificity for distinguishing other types of pneumonia from COVID-19 were 0.93 (95% CI 0.92-0.94) and 0.95 (95% CI 0.94-0.95), respectively. The performance of radiologists in detecting COVID-19 was lower than that of the DL models; however, the performance of junior radiologists was improved when they used DL-based prediction tools. Conclusions Our study findings show that DL models have immense potential in accurately stratifying COVID-19 patients and in correctly differentiating them from patients with other types of pneumonia and normal patients. Implementation of DL-based tools can assist radiologists in correctly and quickly detecting COVID-19 and, consequently, in combating the COVID-19 pandemic.

scholarly journals Application of Artificial Intelligence for Screening COVID-19 Patients Using Digital Images: Meta-analysis (Preprint)

2020 ◽  
Author(s):  
Tahmina Nasrin Poly ◽  
Md Mohaimenul Islam ◽  
Yu-Chuan Jack Li ◽  
Belal Alsinglawi ◽  
Min-Huei Hsu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Diagnostic Odds Ratio ◽  
Study Characteristics ◽  
Key Terms ◽  
Immense Potential

BACKGROUND The COVID-19 outbreak has spread rapidly and hospitals are overwhelmed with COVID-19 patients. While analysis of nasal and throat swabs from patients is the main way to detect COVID-19, analyzing chest images could offer an alternative method to hospitals, where health care personnel and testing kits are scarce. Deep learning (DL), in particular, has shown impressive levels of performance when analyzing medical images, including those related to COVID-19 pneumonia. OBJECTIVE The goal of this study was to perform a systematic review with a meta-analysis of relevant studies to quantify the performance of DL algorithms in the automatic stratification of COVID-19 patients using chest images. METHODS A search strategy for use in PubMed, Scopus, Google Scholar, and Web of Science was developed, where we searched for articles published between January 1 and April 25, 2020. We used the key terms “COVID-19,” or “coronavirus,” or “SARS-CoV-2,” or “novel corona,” or “2019-ncov,” and “deep learning,” or “artificial intelligence,” or “automatic detection.” Two authors independently extracted data on study characteristics, methods, risk of bias, and outcomes. Any disagreement between them was resolved by consensus. RESULTS A total of 16 studies were included in the meta-analysis, which included 5896 chest images from COVID-19 patients. The pooled sensitivity and specificity of the DL models in detecting COVID-19 were 0.95 (95% CI 0.94-0.95) and 0.96 (95% CI 0.96-0.97), respectively, with an area under the receiver operating characteristic curve of 0.98. The positive likelihood, negative likelihood, and diagnostic odds ratio were 19.02 (95% CI 12.83-28.19), 0.06 (95% CI 0.04-0.10), and 368.07 (95% CI 162.30-834.75), respectively. The pooled sensitivity and specificity for distinguishing other types of pneumonia from COVID-19 were 0.93 (95% CI 0.92-0.94) and 0.95 (95% CI 0.94-0.95), respectively. The performance of radiologists in detecting COVID-19 was lower than that of the DL models; however, the performance of junior radiologists was improved when they used DL-based prediction tools. CONCLUSIONS Our study findings show that DL models have immense potential in accurately stratifying COVID-19 patients and in correctly differentiating them from patients with other types of pneumonia and normal patients. Implementation of DL-based tools can assist radiologists in correctly and quickly detecting COVID-19 and, consequently, in combating the COVID-19 pandemic.

scholarly journals Identifying the diagnostic value of microRNA-421 in gastric cancer patients: a meta-analysis

2018 ◽  
Author(s):  
Yan Miao ◽  
Ying Zhang ◽  
Lina Wang ◽  
Lihong Yin
Keyword(s):  
Gastric Cancer ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Diagnostic Odds Ratio ◽  
Diagnostic Value ◽  
Summary Receiver Operating Characteristic ◽  
Gastric Cancer Patients ◽  
Sensitivity Specificity

ABSTRACTObjectivesEmerging evidence has shown that the expression level of microRNA-421 (miR-421) was significantly different between gastric cancer (GC) patients and healthy individuals. However, the diagnostic accuracy of miR-421 in the reports remains inconsistent. This meta-analysis aims to assess the diagnostic value of miR-421 in GC detection.MethodsAll related articles on miR-421 in GC diagnosis were retrieved until September 2018. The QUADAS-2 checklist was used to assess the methodological quality of each study. The diagnostic performance of miR-421 for GC were assessed by using Meta-DiSc 1.4 and STATA 14.0 statistical software.ResultsA total of 172 GC patients and 154 healthy controls from three articles (four studies) were enrolled in this meta-analysis. The results of pooled sensitivity, specificity, diagnostic odds ratio (DOR) with 95% confidence interval (CI) were 0.90 (95% CI: 0.85 to 0.93), 0.83 (95% CI: 0.77 to 0.87), and 37.18 (95% CI: 8.61 to 160.49), respectively. The area under the summary receiver operating characteristic curve (SROC) was 0.8977.ConclusionsThis study indicates that miR-421 could serve as a promising biomarker for GC detecting. Further studies are needed to verify the generalizability of these findings.

Sign in / Sign up

Export Citation Format

Share Document