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 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.

1267 Utility of Artificial Intelligence in the Cystoscopic Detection of Bladder Cancer: A Systematic Review and Meta-Analysis

2021 ◽  
Vol 108 (Supplement_6) ◽  
Author(s):  
S Ganesananthan ◽  
S Ganesananthan ◽  
B S Simpson ◽  
J M Norris
Keyword(s):  
Artificial Intelligence ◽  
Bladder Cancer ◽  
Sensitivity And Specificity ◽  
Meta Analysis ◽  
External Validation ◽  
High Sensitivity ◽  
Diagnostic Odds Ratio ◽  
Pooled Analysis ◽  
Likelihood Ratios ◽  
Novel Technology

Abstract Aim Detection of suspected bladder cancer at diagnostic cystoscopy is challenging and is dependent on clinician skill. Artificial Intelligence (AI) algorithms, specifically, machine learning and deep learning, have shown promise in accurate classification of pathological images in various specialties. However, utility of AI for urothelial cancer diagnosis is unknown. Here, we aimed to systematically review the extant literature in this field and quantitively summarise the role of these algorithms in bladder cancer detection. Method The EMBASE, PubMed and CENTRAL databases were searched up to December 22nd 2020 , in accordance with the PRISMA guidelines, for studies that evaluated AI algorithms for cystoscopic diagnosis of bladder cancer. Random-effects meta-analysis was performed to summarise eligible studies. Risk of Bias was assessed using the QUADAS-2 tool. Results Five from 6715 studies met criteria for inclusion. Pooled sensitivity and specificity values were 0.93 (95% CI 0.89–0.95) and 0.93 (95% CI 0.80–0.89) respectively. Pooled positive likelihood and negative likelihood ratios were 14 (95% CI 4.3–44) and 0.08 (95% CI: 0.05–0.11), respectively. Pooled diagnostic odds ratio was 182 (95% CI 61–546). Summary AUC curve value was 0.95 (95% CI 0.93–0.97). No significant publication bias was noted. Conclusions In summary, AI algorithms performed very well in detection of bladder cancer in this pooled analysis, with high sensitivity and specificity values. However, as with other clinical AI usage, further external validation through deployment in real clinical situations is essential to assess true applicability of this novel technology.

scholarly journals Automated Breast Cancer Detection in Digital Mammograms of Various Densities via Deep Learning

2020 ◽  
Vol 10 (4) ◽  
pp. 211 ◽  
Author(s):  
Yong Joon Suh ◽  
Jaewon Jung ◽  
Bum-Joo Cho
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Malignant Lesion ◽  
Model Performance ◽  
Mean Values ◽  
The Mean ◽  
Deep Learning Model

Mammography plays an important role in screening breast cancer among females, and artificial intelligence has enabled the automated detection of diseases on medical images. This study aimed to develop a deep learning model detecting breast cancer in digital mammograms of various densities and to evaluate the model performance compared to previous studies. From 1501 subjects who underwent digital mammography between February 2007 and May 2015, craniocaudal and mediolateral view mammograms were included and concatenated for each breast, ultimately producing 3002 merged images. Two convolutional neural networks were trained to detect any malignant lesion on the merged images. The performances were tested using 301 merged images from 284 subjects and compared to a meta-analysis including 12 previous deep learning studies. The mean area under the receiver-operating characteristic curve (AUC) for detecting breast cancer in each merged mammogram was 0.952 ± 0.005 by DenseNet-169 and 0.954 ± 0.020 by EfficientNet-B5, respectively. The performance for malignancy detection decreased as breast density increased (density A, mean AUC = 0.984 vs. density D, mean AUC = 0.902 by DenseNet-169). When patients’ age was used as a covariate for malignancy detection, the performance showed little change (mean AUC, 0.953 ± 0.005). The mean sensitivity and specificity of the DenseNet-169 (87 and 88%, respectively) surpassed the mean values (81 and 82%, respectively) obtained in a meta-analysis. Deep learning would work efficiently in screening breast cancer in digital mammograms of various densities, which could be maximized in breasts with lower parenchyma density.

Performance of Serum Glypican 3 in Diagnosis of Hepatocellular Carcinoma: A meta-analysis

2018 ◽  
Vol 17 (5) ◽  
pp. 0-10
Author(s):  
Dahai Xu ◽  
Chang Su ◽  
Liang Sun ◽  
Yuanyuan Gao ◽  
Youjun Li
Keyword(s):  
Hepatocellular Carcinoma ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Web Of Science ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Positive Control ◽  
Cochrane Library ◽  
Non Invasive

Introduction and aim. Serum glypican-3 (GPC3) has been explored as a non-invasive biomarker of hepatocellular carcinoma (HCC). However, controversy remains on its diagnostic accuracy. Therefore, we aimed to conduct a systematic review and metaanalysis to evaluate the differential diagnostic accuracy of serum GPC3 between HCC and liver cirrhosis (LC) cases. Material and methods. After the strict filtering and screening of studies from NCBI, PUBMED, Clinical Trials, Cochrane library, Embase, Prospero and Web of Science databases, 11 studies were selected. All studies provided the sensitivity and specificity of GPC3 and the alpha-fetoprotein (AFP) in the HCC and LC diagnosis. The sensitivity and specificity, and the area under the receiver operating characteristic curve (AUC) were determined and compared between GPC3 and AFP, which was set as a positive control. Results. Pooled sensitivity (95% CI) and specificity (95% CI) were 0.55 (0.52-0.58) and 0.58 (0.54-0.61) for GPC3, 0.54 (0.51-0.57) and 0.83 (0.80-0.85) for AFP, and 0.85 (0.81-0.89) and 0.79 (0.73-0.84) for GPC3 + AFP, respectively. The AUCs of GPC3, AFP and GPC3 + AFP were 0.7793, 0.7867 and 0.9366, respectively. GPC3 had a nearly similar sensitivity as AFP, while the specificity and AUC of GPC3 was lower than that of AFP. The combination of GPC3 and AFP yielded a better sensitivity and AUC than GPC3 or AFP. Conclusion. Serum GPC3 is inferior to AFP in the differential diagnosis between HCC and LC. However, the combination of GPC3 and AFP exhibited a much better performance.

scholarly journals Evaluation on the Diagnostic Efficiency of Different Methods in Detecting COVID-19.

2020 ◽  
Author(s):  
Haitao Yang ◽  
Yuzhu Lan ◽  
Xiujuan Yao ◽  
Sheng Lin ◽  
Baosong Xie
Keyword(s):  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Web Of Science ◽  
Characteristic Curve ◽  
Positive Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Diagnostic Efficiency ◽  
Summary Receiver Operating Characteristic ◽  
Operating Characteristic Curve ◽  
Higher Sensitivity

Abstract Objective: To evaluate the diagnostic efficiency of different methods in detecting COVID-19.Methods: PubMed, Web of Science and Embase databases were searched for identifing eligible articles. All data were calculated utilizing Meta Disc 1.4, Revman 5.3.2 and Stata 12. The diagnostic efficiency was assessed via these indicators including summary sensitivity and specificity, positive likelihood ratio (PLR), negative LR (NLR), diagnostic odds ratio (DOR), summary receiver operating characteristic curve (sROC) and calculate the AUC. Results: 18 articles (3648 cases) were included. EPlex: pooled sensitivity was 0.94; specificity 1.0; PLR 90.91; NLR 0.07; DOR 1409.49; AUC=0.9979, Q*=0.9840. Panther Fusion: pooled sensitivity was 0.99; specificity 0.98; PLR 42.46; NLR 0.02; DOR 2300.38; AUC=0.9970, Q*=0.9799. Simplexa: pooled sensitivity was 1.0; specificity 0.97; PLR 26.67; NLR 0.01; DOR 3100.93; AUC=0.9970, Q*=0.9800. Cobas®: pooled sensitivity was 0.99; specificity 0.96; PLR 37.82; NLR 0.02; DOR 3754.05; AUC=0.9973, Q*=0.9810. RT-LAMP: pooled sensitivity was 0.98; specificity 0.99; PLR 36.22; NLR 0.04; DOR 751.24; AUC=0.9905, Q*=0.9596. Xpert Xpress: pooled sensitivity was 0.99; specificity 0.97; PLR 27.44; NLR 0.01; DOR 3488.15; AUC=0.9977, Q*=0.9829.Conclusions: These methods (ePlex, Panther Fusion, Simplexa, Cobas®, RT-LAMP and Xpert Xpress) bear higher sensitivity and specificity, and might be efficient methods complement to the gold standard.

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.

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.

scholarly journals Evaluation on the diagnostic efficiency of different methods in detecting COVID-19

2020 ◽  
Author(s):  
Haitao Yang ◽  
Yuzhu Lan ◽  
Xiujuan Yao ◽  
Sheng Lin ◽  
Baosong Xie
Keyword(s):  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Web Of Science ◽  
Characteristic Curve ◽  
Positive Likelihood Ratio ◽  
Diagnostic Odds Ratio ◽  
Preliminary Evidence ◽  
Diagnostic Efficiency ◽  
Summary Receiver Operating Characteristic ◽  
Higher Sensitivity

AbstractObjectiveTo evaluate the diagnostic efficiency of different methods in detecting COVID-19 to provide preliminary evidence on choosing favourable method for COVID-19 detection.MethodsPubMed, Web of Science and Embase databases were searched for identifing eligible articles. All data were calculated utilizing Meta Disc 1.4, Revman 5.3.2 and Stata 12. The diagnostic efficiency was assessed via these indicators including summary sensitivity and specificity, positive likelihood ratio (PLR), negative LR (NLR), diagnostic odds ratio (DOR), summary receiver operating characteristic curve (sROC) and calculate the AUC.Results18 articles (3648 cases) were included. The results showed no significant threshold exist. EPlex: pooled sensitivity was 0.94; specificity was 1.0; PLR was 90.91; NLR was 0.07; DOR was 1409.49; AUC=0.9979, Q*=0.9840. Panther Fusion: pooled sensitivity was 0.99; specificity was 0.98; PLR was 42.46; NLR was 0.02; DOR was 2300.38; AUC=0.9970, Q*=0.9799. Simplexa: pooled sensitivity was 1.0; specificity was 0.97; PLR was 26.67; NLR was 0.01; DOR was 3100.93; AUC=0.9970, Q*=0.9800. Cobas®: pooled sensitivity was 0.99; specificity was 0.96; PLR was 37.82; NLR was 0.02; DOR was 3754.05; AUC=0.9973, Q*=0.9810. RT-LAMP: pooled sensitivity was 0.98; specificity was 0.99; PLR was 36.22; NLR was 0.04; DOR was 751.24; AUC=0.9905, Q*=0.9596. Xpert Xpress: pooled sensitivity was 0.99; specificity was 0.97; PLR was 27.44; NLR was 0.01; DOR was 3488.15; AUC=0.9977, Q*=0.9829.ConclusionsThese methods (ePlex, Panther Fusion, Simplexa, Cobas®, RT-LAMP and Xpert Xpress) bear higher sensitivity and specificity, and might be efficient methods complement to the gold standard.

scholarly journals Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea

2020 ◽  
Vol 13 (8) ◽  
Author(s):  
Demilade Adedinsewo ◽  
Rickey E. Carter ◽  
Zachi Attia ◽  
Patrick Johnson ◽  
Anthony H. Kashou ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Receiver Operating Characteristic Curve ◽  
Receiver Operating Characteristic ◽  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Left Ventricular Systolic Dysfunction ◽  
Characteristic Curve ◽  
Left Ventricular ◽  
Operating Characteristic Curve ◽  
Receiver Operating

Background: Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD). Methods: We retrospectively applied a validated artificial intelligence-enabled ECG algorithm for the identification of LVSD (defined as LV ejection fraction ≤35%) to a cohort of patients aged ≥18 years who were evaluated in the ED at a Mayo Clinic site with dyspnea. Patients were included if they had at least one standard 12-lead ECG acquired on the date of the ED visit and an echocardiogram performed within 30 days of presentation. Patients with prior LVSD were excluded. We assessed the model performance using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. Results: A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86–0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83–0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76–0.84). Conclusions: The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Graphic Abstract: A graphic abstract is available for this article.

scholarly journals Diagnostic accuracy of synovial fluid D-lactate for periprosthetic joint infection: a systematic review and meta-analysis

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Zhizhuo Li ◽  
Chengxin Li ◽  
Guangxue Wang ◽  
Lijun Shi ◽  
Tengqi Li ◽  
...  
Keyword(s):  
Synovial Fluid ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Periprosthetic Joint Infection ◽  
Odds Ratio ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Joint Infection ◽  
Diagnostic Odds Ratio ◽  
Likelihood Ratios

Abstract Background Periprosthetic joint infection is a grievous complication after arthroplasty that greatly affects the quality of life of patients. Rapid establishment of infection diagnosis is essential, but great challenges still exist. Methods We conducted research in the PubMed, Embase, and Cochrane databases to evaluate the diagnostic accuracy of D-lactate for PJI. Data extraction and quality assessment were completed independently by two reviewers. The pooled sensitivity, specificity, likelihood ratios, diagnostic odds ratio (DOR), summarized receiver operating characteristic curve (sROC), and area under the sROC curve (AUC) were constructed using the bivariate meta-analysis framework. Results Five eligible studies were included in the quantitative analysis. The pooled sensitivity and specificity of D-lactate for the diagnosis of PJI were 0.82 (95% CI 0.70–0.89) and 0.76 (95% CI 0.69–0.82), respectively. The value of the pooled diagnostic odds ratio (DOR) of D-lactate for PJI was 14.18 (95% CI 6.17–32.58), and the area under the curve (AUC) was 0.84 (95% CI 0.80–0.87). Conclusions According to the results of our meta-analysis, D-lactate is a valuable synovial fluid marker for recognizing PJI, with high sensitivity and specificity.

Sign in / Sign up

Export Citation Format

Share Document