Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis

Gut ◽  
2020 ◽  
pp. gutjnl-2020-321922 ◽  
Author(s):  
Julia Arribas ◽  
Giulio Antonelli ◽  
Leonardo Frazzoni ◽  
Lorenzo Fuccio ◽  
Alanna Ebigbo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Likelihood Ratio ◽  
Precancerous Lesions ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Clinical Value ◽  
Predictive Values ◽  
Upper Gi ◽  
Neoplastic Lesion

ObjectiveArtificial intelligence (AI) may reduce underdiagnosed or overlooked upper GI (UGI) neoplastic and preneoplastic conditions, due to subtle appearance and low disease prevalence. Only disease-specific AI performances have been reported, generating uncertainty on its clinical value.DesignWe searched PubMed, Embase and Scopus until July 2020, for studies on the diagnostic performance of AI in detection and characterisation of UGI lesions. Primary outcomes were pooled diagnostic accuracy, sensitivity and specificity of AI. Secondary outcomes were pooled positive (PPV) and negative (NPV) predictive values. We calculated pooled proportion rates (%), designed summary receiving operating characteristic curves with respective area under the curves (AUCs) and performed metaregression and sensitivity analysis.ResultsOverall, 19 studies on detection of oesophageal squamous cell neoplasia (ESCN) or Barrett's esophagus-related neoplasia (BERN) or gastric adenocarcinoma (GCA) were included with 218, 445, 453 patients and 7976, 2340, 13 562 images, respectively. AI-sensitivity/specificity/PPV/NPV/positive likelihood ratio/negative likelihood ratio for UGI neoplasia detection were 90% (CI 85% to 94%)/89% (CI 85% to 92%)/87% (CI 83% to 91%)/91% (CI 87% to 94%)/8.2 (CI 5.7 to 11.7)/0.111 (CI 0.071 to 0.175), respectively, with an overall AUC of 0.95 (CI 0.93 to 0.97). No difference in AI performance across ESCN, BERN and GCA was found, AUC being 0.94 (CI 0.52 to 0.99), 0.96 (CI 0.95 to 0.98), 0.93 (CI 0.83 to 0.99), respectively. Overall, study quality was low, with high risk of selection bias. No significant publication bias was found.ConclusionWe found a high overall AI accuracy for the diagnosis of any neoplastic lesion of the UGI tract that was independent of the underlying condition. This may be expected to substantially reduce the miss rate of precancerous lesions and early cancer when implemented in clinical practice.

scholarly journals The value of glycosylated hemoglobin in the diagnosis of diabetic retinopathy: a systematic review and Meta-analysis

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Bo Zhang ◽  
Bingjie Zhang ◽  
Zhulin Zhou ◽  
Yutong Guo ◽  
Dan Wang
Keyword(s):  
Diabetic Retinopathy ◽  
Likelihood Ratio ◽  
Roc Curve ◽  
Meta Analysis ◽  
Glycosylated Hemoglobin ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Biomedical Literature ◽  
Cochrane Library ◽  
Clinical Value

AbstractObjectiveGlycosylated hemoglobin (HbA1c) has obvious clinical value in the diagnosis of diabetes, but the conclusions on the diagnostic value of diabetic retinopathy (DR) are not consistent. This study aims to comprehensively evaluate the accuracy of glycosylated hemoglobin in the diagnosis of diabetic retinopathy through the meta-analysis of diagnostic tests.MethodsCochrane Library, Embase, PubMed, Web of Science, China National Knowledge Infrastructure (CNKI), China Wanfang Database, Chinese Biomedical Literature Database (CBM) were searched until November, 2020. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was used to assess the quality of the included studies. The pooled sensitivity, specificity, positive likelihood ratio (+LR), negative likelihood ratio (-LR), diagnostic odds ratio (DOR) and areas under the receiver operating characteristic (ROC) curve were calculated by Stata 15.0 software.ResultsAfter screening, 18 high-quality papers were included. The results of meta-analysis showed that the combined DOR = 18.19 (95% CI: 10.99–30.11), the sensitivity= 0.81 (95% CI): 0.75 ~ 0.87), specificity = 0.81 (95%CI: 0.72 ~ 0.87), +LR = 4.2 (95%CI: 2.95 ~ 6.00), −LR = 0.23 (95%CI: 0.17 ~ 0.31), and the area under the Summary ROC curve was 0.88 (95%CI:  0.85 ~ 0.90).ConclusionThe overall accuracy of HbA1cC forin diagnosing diabetic retinopathy is good. As it is more stable than blood sugar and is not affected by meals, it may be a suitable indicator for diabetic retinopathy.

scholarly journals Systematic Review and Meta-Analysis of the Utility of Circular RNAs as Biomarkers of Hepatocellular Carcinoma

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Qingqin Hao ◽  
Yadi Han ◽  
Wei Xia ◽  
Qinghui Wang ◽  
Huizhong Qian
Keyword(s):  
Likelihood Ratio ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Clinicopathological Characteristics ◽  
Cochrane Library ◽  
Circular Rnas ◽  
Clinical Value ◽  
Sensitivity Specificity

Emerging studies have reported circRNAs were dysregulated in HCC. However, the clinical value of these circRNAs remains to be clarified. Herein, we aimed to comprehensively explore their association with the diagnosis, prognosis, and clinicopathological characteristics of HCC. PubMed, EMBASE, Web of Science, and Cochrane Library databases were comprehensively searched for eligible studies up to October 30, 2018. The diagnostic effect was evaluated by the pooled sensitivity, specificity, and other indexes. The pooled hazard ratio (HR) for overall survival (OS) and recurrence free survival (RFS) was calculated to assess the prognostic value. Ten studies on diagnosis, 12 on prognosis, and 23 on clinicopathology were identified from the databases. A total of 11 upregulated and 11 downregulated circRNAs showed an association with clinicopathological features of HCC. For the diagnosis analyses, the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR) of circRNAs for HCC were 0.74 (95%CI: 0.65-0.82) and 0.76 (95%CI: 0.70-0.81), 3.1 (95%CI: 2.5-3.8), 0.34 (95%CI: 0.25-0.47), and 9 (95%CI: 6-14), respectively. The area under SROC curve (AUC) was 0.81 (95% CI: 0.78–0.84), indicating moderate diagnostic accuracy. In stratified analyses, the diagnostic performance of circRNAs varied based on the source of control and specimen type. For the prognosis analyses, increased expression of upregulated circRNAs was associated with worse OS (HR: 3.67, 95%: 2.07-6.48), while high expression of downregulated circRNAs was associated with better OS (HR: 0.38, 95%: 0.30-0.48). In conclusion, this study reveals that circRNAs may serve as promising diagnostic and prognostic biomarkers for HCC. However, further investigations are still required to explore the clinical value of circRNAs.

scholarly journals The effectiveness of eye tracking in the diagnosis of cognitive disorders: A systematic review and meta-analysis

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254059
Author(s):  
Zicai Liu ◽  
Zhen Yang ◽  
Yueming Gu ◽  
Huiyu Liu ◽  
Pu Wang
Keyword(s):  
Cognitive Impairment ◽  
Eye Tracking ◽  
Likelihood Ratio ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Cognitive Disorders ◽  
Negative Likelihood Ratio ◽  
Cognitive Testing ◽  
Cochrane Library ◽  
Clinical Value

Background Eye tracking (ET) is a viable marker for the recognition of cognitive disorders. We assessed the accuracy and clinical value of ET for the diagnosis of cognitive disorders in patients. Methods We searched the Medline, Embase, Web of Science, Cochrane Library, and Pubmed databases from inception to March 2, 2021, as well as the reference lists of identified primary studies. We included articles written in English that investigated ET for cognitive disorder patients—Mild cognitive impairment (MCI), Alzheimer’s disease (AD), Amyotrophic lateral sclerosis (ALS), and dementia. Two independent researchers extracted the data and the characteristics of each study; We calculated pooled sensitivities and specificities. A hierarchical summary of receiver performance characteristics (HSROC) model was used to test the diagnostic accuracy of ET for cognitive impairment (CI). Findings 11 studies met the inclusion criteria and were included in qualitative comprehensive analysis. Meta-analysis was performed on 9 trials using Neuropsychological Cognitive Testing (NCT) as the reference standard. The comprehensive sensitivity and specificity of ET for detecting cognitive disorders were 0.75 (95% CI 0.72–0.79) and 0.73 (95% CI 0.70 to 0.76), respectively. The combined positive likelihood ratio (LR+) was 2.74 (95%CI 2.32–3.24) and the negative likelihood ratio (LR−) was 0.27 (95%CI 0.18–0.42). Conclusions This review showed that ET technology could be used to detect the decline in CI, clinical use of ET techniques in combination with other tools to assess CI can be encouraged.

scholarly journals Clinical value of thoracic ultrasonography in the diagnosis of pulmonary embolism: a systematic review and meta-analysis

2021 ◽  
Author(s):  
Wu Chen ◽  
Kun Xu ◽  
Yiying Li ◽  
Meifang Hao ◽  
Yongsheng Yang ◽  
...  
Keyword(s):  
Systematic Review ◽  
Pulmonary Embolism ◽  
Likelihood Ratio ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Cochrane Library ◽  
Clinical Value ◽  
Sensitivity Specificity

Aims: The present study investigated and evaluated the accuracy of thoracic ultrasonography (TUS) in the diagnosis of pulmonary embolism (PE) by conducting a systematic review and meta-analysis. Material and methods: The PubMed, Em-base and the Cochrane library databases were searched till March 2019 to retrieve relevant articles and the overall diagnostic accuracy of TUS in PE diagnosis was evaluated by meta-analysis. Results: Overall, 16 studies including 1,916 patients were enrolled in this meta-analysis. Of these, 762 (39.8%) had confirmed PE. The overall sensitivity, specificity, and area under the ROC curve (AUC) of TUS for PE were 82% (95% confidence interval (CI), 72%–88%), 89% (95% CI, 79%–95%), and 0.91 (95% CI, 0.88–0.93), respectively. Other efficacy parameters assessed demonstrated a positive likelihood ratio (PLR) of (7.6; 95% CI, 4.0–14.5), negative likelihood ratio of (NLR) (0.21; 95% CI, 0.14–0.30), and diagnostic odds’ ratio (DOR) of (36.86; 95% CI, 21.41–63.48). Conclusions: The current study suggested that although TUS cannot safely rule out PE, it is likely to be used as an aid or guidance to establish procedures and help to improve the diagnostic deficits in patients with PE.

scholarly journals The Potential Diagnostic Accuracy of Circulating MicroRNAs for Leukemia: A Meta-Analysis

2021 ◽  
Vol 20 ◽  
pp. 153303382110119
Author(s):  
Wen-Ting Zhang ◽  
Guo-Xun Zhang ◽  
Shuai-Shuai Gao
Keyword(s):  
Diagnostic Accuracy ◽  
Likelihood Ratio ◽  
Subgroup Analysis ◽  
Meta Analysis ◽  
Area Under The Curve ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Circulating Micrornas ◽  
Sensitivity Specificity

Background: Leukemia is a common malignant disease in the human blood system. Many researchers have proposed circulating microRNAs as biomarkers for the diagnosis of leukemia. We conducted a meta-analysis to evaluate the diagnostic accuracy of circulating miRNAs in the diagnosis of leukemia. Methods: A comprehensive literature search (updated to October 13, 2020) in PubMed, EMBASE, Web of Science, Cochrane Library, Wanfang database and China National Knowledge Infrastructure (CNKI) was performed to identify eligible studies. The sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC) for diagnosing leukemia were pooled for both overall and subgroup analysis. The meta-regression and subgroup analysis were performed to explore heterogeneity and Deeks’ funnel plot was used to assess publication bias. Results: 49 studies from 22 publications with a total of 3,489 leukemia patients and 2,756 healthy controls were included in this meta-analysis. The overall sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio and area under the curve were 0.83, 0.92, 10.8, 0.18, 59 and 0.94, respectively. Subgroup analysis shows that the microRNA clusters of plasma type could carry out a better diagnostic accuracy of leukemia patients. In addition, publication bias was not found. Conclusions: Circulating microRNAs can be used as a promising noninvasive biomarker in the early diagnosis of leukemia.

scholarly journals Diagnostic accuracy of MALDI-TOF mass spectrometry for the direct identification of clinical pathogens from urine

Open Medicine ◽  
2020 ◽  
Vol 15 (1) ◽  
pp. 266-273
Author(s):  
Min Tang ◽  
Jia Yang ◽  
Ying Li ◽  
Luhua Zhang ◽  
Ying Peng ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Likelihood Ratio ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Urine Samples ◽  
Direct Identification ◽  
Maldi Tof Ms ◽  
Maldi Tof ◽  
Tof Ms

AbstractMatrix-assisted laser desorption ionization time of flight mass spectrometry (MALDI-TOF MS) has become one of the most popular methods for the rapid and cost-effective detection of clinical pathogenic microorganisms. This study aimed to evaluate and compare the diagnostic performance of MALDI-TOF MS with that of conventional approaches for the direct identification of pathogens from urine samples. A systematic review was conducted based on a literature search of relevant databases. The pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR) and area under the summary receiver operating characteristic (SROC) curve of the combined studies were estimated. Nine studies with a total of 3920 subjects were considered eligible and included in the meta-analysis. The pooled sensitivity was 0.85 (95% CI 0.79-0.90), and the pooled specificity was 0.93 (95% CI 0.82-0.97). The PLR and NLR were 11.51 (95% CI 4.53-29.26) and 0.16 (95% CI 0.11-0.24), respectively. The area under the SROC curve was 0.93 (95% CI 0.91-0.95). Sensitivity analysis showed that the results of this meta-analysis were stable. MALDI-TOF MS could directly identify microorganisms from urine samples with high sensitivity and specificity.

scholarly journals Predictive Value of Interim PET/CT in DLBCL Treated with R-CHOP: Meta-Analysis

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Na Sun ◽  
Jinhua Zhao ◽  
Wenli Qiao ◽  
Taisong Wang
Keyword(s):  
Likelihood Ratio ◽  
Predictive Value ◽  
Meta Analysis ◽  
Prognostic Significance ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Chop Chemotherapy ◽  
Interim Pet ◽  
Pet Ct ◽  
Fdg Pet Ct

Objective.We conducted a meta-analysis to evaluate the predictive value of interim18F-FDG PET/CT in patients with DLBCL treated with R-CHOP chemotherapy.Methods.We searched for articles published in PubMed, ScienceDirect, Wiley, Scopus, and Ovid database from inception to March 2014. Articles related to interim PET/CT in patients with DLBCL treated with R-CHOP chemotherapy were selected. PFS with or without OS was chosen as the endpoint to evaluate the prognostic significance of interim PET/CT.Results.Six studies with a total of 605 cases were included. The sensitivity of interim PET/CT ranged from 21.2% to 89.7%, and the pooled sensitivity was 52.4%. The specificity of interim PET/CT ranged from 37.4% to 90.7%, and the pooled specificity was 67.8%. The pooled positive likelihood ratio and negative likelihood ratio were 1.780 and 0.706, respectively. The explained AUC was 0.6978 and theQ*was 0.6519.Conclusions.The sensitivity and specificity of interim PET/CT in predicting the outcome of DLBCL patients treated with R-CHOP chemotherapy were not satisfactory (52.4% and 67.8%, resp.). To improve this, some more work should be done to unify the response criteria and some more research to assess the prognostic value of interim PET/CT with semiquantitative analysis.

scholarly journals Pooled analysis of T2 Candida for rapid diagnosis of candidiasis

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Dong-Lan Tang ◽  
Xiao Chen ◽  
Chang-Guo Zhu ◽  
Zhong-wei Li ◽  
Yong Xia ◽  
...  
Keyword(s):  
Likelihood Ratio ◽  
Web Of Science ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Pooled Analysis ◽  
Current Evidence ◽  
Cochrane Library ◽  
Research Subjects

Abstract Background The present meta-analysis examined the diagnostic accuracy of T2 Candida for candidiasis. Methods The literature databases, such as PubMed, Embase, DVIO, Cochrane library, Web of Science, and CNKI, were searched on T2 Candida detection. Results A total of 8 articles, comprising of 2717 research subjects, were included in the study. The pooled sensitivity and specificity were 0.91 (95% confidence interval (CI): 0.88–0.94) and 0.94 95% CI: 0.93–0.95), respectively. The pooled positive likelihood ratio and negative likelihood ratio was 10.16 (95% CI: 2.75–37.50) and 0.08 (95% CI: 0.02–0.35), respectively. The combined diagnostic odds ratio is 133.65 95% CI: 17.21–1037.73), and the AUC of SROC is 0.9702 [(SE = 0.0235), Q* = 0.9201(SE = 0.0381)]. Conclusions The current evidence supported that T2 Candida has high accuracy and sensitivity and is of major clinical significance in the diagnosis of Candida infection.

scholarly journals Predictive value of pregnancy-associated plasma protein-A in relation to fetal loss: A systematic review and meta-analysis

2020 ◽  
Author(s):  
Zahra Hadizadeh-Talasaz ◽  
Ali Taghipour ◽  
Seyede Houra Mousavi-Vahed ◽  
Robab Latifnejad Roudsari
Keyword(s):  
Systematic Review ◽  
Likelihood Ratio ◽  
Plasma Protein ◽  
Predictive Value ◽  
Meta Analysis ◽  
Protein A ◽  
Fetal Loss ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Forest Plot

Background: For a woman with bleeding and threatened abortion, ultrasound scan is done to confirm the viability of the fetus; however, 10-15% of the embryos are eventually aborted. Distinguishing between women with good and poor prognosis can be a helpful approach. Objective: This study aimed to review the predictive value of Pregnancy-associated Plasma Protein A (PAPP-A) in relation to the diagnosis of fetal loss. Materials and Methods: The articles published in multiple databases including Web of Science, PubMed, MEDLINE, Scopus, and Persian databases such as ISC, Magiran, and IranMedx were searched for articles published until May 2019. MeSH terms was used for searching the databases including fetal loss OR pregnancy loss OR abortion OR miscarriage with the following word using AND; Pregnancy-Associated Plasma Protein- A OR PAPP-A. Two reviewers extracted data and recorded them in a pre-defined form and assessed the quality of articles using the Newcastle-Ottawa tool. Meta-analysis was done using the Comprehensive Meta-Analysis/2.0 software and MetaDisc. Results: A total number of 16 studies were eligible for the qualitative data synthesis, out of which 8 studies were included in the meta-analysis. All studies had high and medium quality. The forest plot analysis showed a sensitivity of 57% (95% CI: 53-63%), a specificity of 83% (95% CI: 80-85%), a positive likelihood ratio of 3.52 (95% CI: 2.44- 5.07), a negative likelihood ratio of 0.54 (95% CI: 0.37-0.79), and a diagnostic odds ratio of 6.95 (95% CI: 3.58-13.50). Conclusion: PAPP-A cannot be recommended on a routine basis for predicting fetal loss and still further research with a combination of other biomarkers is required. Key words: Pregnancy-associated plasma protein-A, Fetal loss, Pregnancy, Systematic review.

scholarly journals Prognostic Value of N-terminal Probrain Natriuretic Peptide for Patients with Acute Respiratory Distress Syndrome: A Systematic Review and Meta-Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Qi Ni ◽  
Chaoqian Li ◽  
Hua Lin
Keyword(s):  
Systematic Review ◽  
Acute Respiratory Distress Syndrome ◽  
Likelihood Ratio ◽  
Odds Ratio ◽  
Distress Syndrome ◽  
Meta Analysis ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Sensitivity Specificity

Objectives. The mortality rate of patients with acute respiratory distress syndrome (ARDS) is high. Hence, it is crucial to identify a reliable biomarker with wide clinical applications for predicting the prognosis of patients with ARDS. This systematic review and meta-analysis was conducted to investigate the value of plasma N-terminal probrain natriuretic peptide (NT-proBNP) for predicting mortality in patients with ARDS. Methods. An electronic search of databases including PubMed, Web of Science, Cochrane Library, and Chinese National Knowledge Infrastructure was conducted up to May 31, 2019, without language restrictions. The quality of the included studies was evaluated using QUADAS-2. Data were extracted and analyzed to obtain pooled estimates of sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio. A forest graph was used to evaluate heterogeneity. Potential causes of heterogeneity were further explored by subgroup analysis based on the testing day, testing method, observation endpoint, or cut-off points. A summary receiver operating characteristic curve was drawn to obtain the pooled area under the curve. Results. A total of 7 studies involving 581 patients with ARDS were included. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were as follows: 0.79 (95% CI: 0.72–0.84), 0.79 (95% CI: 0.66–0.88), 3.68 (95% CI: 2.16–6.28), 0.27 (95% CI: 0.20–0.38), and 13.58 (95% CI: 6.17–29.90), respectively. The results of subgroup analysis showed that the testing day influenced the summary sensitivity and that the cut-off points influenced the summary sensitivity and specificity. Conclusion. Our results indicate that elevated plasma NT-proBNP levels have a moderate value for predicting the mortality of patients with ARDS.

Sign in / Sign up

Export Citation Format

Share Document