Comparative accuracy of molecular assays for detecting methicillin-resistant Staphylococcus aureus: Evidence from 32 studies.

Artificial intelligence (AI) has emerged as a promising tool for interpreting 12-lead electrocardiograms (ECGs), with the potential to enhance diagnostic accuracy for arrhythmia detection. However, published studies vary widely in methodology and validation strategy, warranting a quantitative synthesis of diagnostic performance. A systematic review and meta-analysis was conducted according to the PRISMA-DTA 2018 guidelines and registered in PROSPERO (CRD420251027264). Searches were performed in MEDLINE, Embase, and Cochrane Library through September 2025 without language restrictions. Studies evaluating AI algorithms for arrhythmia detection using 12-lead ECGs were included. Data on sensitivity, specificity, and area under the curve (AUC) were extracted. Pooled estimates were generated using a bivariate random-effects model. Risk of bias was assessed with QUADAS-2, and the certainty of evidence was quantified using GRADE. 20 studies were included in the meta-analysis, encompassing over 5.5 million ECGs. The pooled sensitivity, specificity, and AUC for AI-based arrhythmia detection were 94.0% (95% CI 90.8-96.2; I2 = 96.9%), 98.7% (95% CI 97.3-99.3; I2 = 98.3%), and 0.982 (95% CI 0.965-0.986), respectively. Detection of atrial fibrillation (AF) yielded a sensitivity of 92.6% (95% CI 86.4-96), a specificity of 99.1% (95% CI 98.4-99.5), and an AUC of 0.988. Convolutional neural networks (CNN) specifically demonstrated a sensitivity of 97.6%, specificity of 98.7%, and an AUC of 0.982 for overall arrhythmia detection. When limited to external validation (n=6), the sensitivity was 96.9% (95% CI 89.2-99.1), specificity was 95.6% (95% CI 77.6-99.3), and AUC was 0.983. No significant publication bias was detected, and the overall certainty of evidence was rated as high. AI models applied to 12-lead ECGs demonstrate excellent diagnostic performance for arrhythmia detection. Findings support potential integration into clinical workflows, particularly in settings with limited cardiology expertise. Given substantial heterogeneity, standardized datasets and multicenter prospective validation are essential to ensure effective and equitable implementation.

Sepsis remains a leading global health challenge, with delayed recognition and limited diagnostic accuracy of current tools contributing to high morbidity and mortality. Conventional clinical scores (SOFA/qSOFA), standard biomarkers (CRP, PCT), and blood cultures suffer from delayed responsiveness, insufficient specificity, or slow turnaround, underscoring the urgent need for more reliable early diagnostic strategies. Presepsin, a soluble CD14 subtype generated during pathogen recognition by innate immune cells, has emerged as a promising biomarker with potential to reflect infection status earlier and more specifically than traditional markers. This systematic review and meta-analysis quantitatively evaluated the diagnostic accuracy of presepsin across diverse populations. PubMed, EMBASE, Web of Science, and Cochrane Library were searched for studies published between 2015 and 2025. Forty-seven studies involving 7087 participants were included. Pooled sensitivity, specificity, diagnostic odds ratio (DOR), area under the curve (AUC), and likelihood ratios (PLR/NLR) with 95% confidence intervals (CI) were calculated using random-effects models. Heterogeneity was assessed with I2 statistics, meta-regression, and subgroup analyses. Study quality was evaluated using QUADAS-2. Presepsin demonstrated excellent overall diagnostic performance: pooled sensitivity 0.84 (95% CI: 0.81–0.88), specificity 0.86 (95% CI: 0.80–0.90), DOR 32.23 (95% CI: 20.11–51.66), and AUC 0.91 (95% CI: 0.88–0.93). Subgroup analyses confirmed robust performance across settings and populations, with particularly high accuracy in neonates (sensitivity 0.90, specificity 0.92, AUC 0.96), followed by children (sensitivity 0.84, specificity 0.81, AUC 0.88, NLR 0.20) and adults (sensitivity 0.81, specificity 0.82, AUC 0.87). Meta-regression identified year of publication, geographic region, specimen type, population, and diagnostic criteria as key contributors to heterogeneity, but sensitivity analyses confirmed result stability. No significant publication bias was observed (P ═ 0.33). In conclusion, presepsin is a valuable and highly promising biomarker for sepsis diagnosis, showing favorable diagnostic accuracy across populations, with strongest utility in neonates. Its application in pediatric and adult patients warrants further validation through large, prospective, multi-center studies.

Muscle ultrasound is an emerging tool for diagnosing sarcopenia. This review aims to summarize the current knowledge on the diagnostic test accuracy of ultrasound for the diagnosis of sarcopenia. We collected data from Ovid Medline, Embase and the Cochrane Central Register of Controlled Trials. Diagnostic test accuracy studies using muscle ultrasound to detect sarcopenia were included. Bivariate random-effects models based on sensitivity and specificity pairs were used to calculate the pooled estimates of sensitivity, specificity and the area under the curves (AUCs) of summary receiver operating characteristic (SROC), if possible. We screened 7332 publications and included 17 studies with 2143 participants (mean age range: 52.6-82.8years). All included studies had a high risk of bias. The study populations, reference standards and ultrasound measurement methods varied across the studies. Lower extremity muscles were commonly studied, whereas muscle thickness (MT) was the most widely measured parameter, followed by the cross-sectional area (CSA). The MTs of the gastrocnemius, rectus femoris, tibialis anterior, soleus, rectus abdominis and geniohyoid muscles showed a moderate diagnostic accuracy for sarcopenia (SROC-AUC 0.83, 8 studies; SROC-AUC 0.78, 5 studies; AUC 0.82, 1 study; AUC 0.76-0.78, 2 studies; AUC 0.76, 1 study; and AUC 0.79, 1 study, respectively), whereas the MTs of vastus intermedius, quadriceps femoris and transversus abdominis muscles showed a low diagnostic accuracy (AUC 0.67-0.71, 3 studies; SROC-AUC 0.64, 4 studies; and AUC 0.68, 1 study, respectively). The CSA of rectus femoris, biceps brachii muscles and gastrocnemius fascicle length also showed a moderate diagnostic accuracy (AUC 0.70-0.90, 3 studies; 0.81, 1 study; and 0.78-0.80, 1 study, respectively), whereas the echo intensity (EI) of rectus femoris, vastus intermedius, quadriceps femoris and biceps brachii muscles showed a low diagnostic accuracy (AUC 0.52-0.67, 2 studies; 0.48-0.50, 1 study; 0.43-0.49, 1 study; and 0.69, 1 study, respectively). The combination of CSA and EI of biceps brachii or rectus femoris muscles was better than either CSA or EI alone for diagnosing sarcopenia. Muscle ultrasound shows a low-to-moderate diagnostic test accuracy for sarcopenia diagnosis depending on different ultrasound parameters, measured muscles, reference standards and study populations. The combination of muscle quality indicators (e.g., EI) and muscle quantity indicators (e.g., MT) might provide better diagnostic test accuracy.

The diagnostic performance of AI based on dental radiographs in predicting marginal bone loss around dental implants: A systematic review and meta-analysis.

Diagnostic accuracy of elastography in differentiating parathyroid lesions from cervical tissues: A systematic review and meta-analysis.

To establish the diagnostic test accuracy of evacuation proctography, magnetic resonance imaging (MRI), transperineal ultrasonography, and endovaginal ultrasonography for detecting posterior pelvic floor disorders (rectocele, enterocele, intussusception, and anismus) in women with obstructed defecation syndrome and secondarily to identify the most patient-friendly imaging technique. In this prospective cohort study, 131 women with symptoms of obstructed defecation syndrome underwent evacuation proctogram, MRI, and transperineal and endovaginal ultrasonography. Images were analyzed by two blinded observers. In the absence of a reference standard, latent class analysis was used to assess diagnostic test accuracy of multiple tests with area under the curve (AUC) as the primary outcome measure. Secondary outcome measures were interobserver agreement calculated as Cohen's κ and patient acceptability using a visual analog scale. No significant differences in diagnostic accuracy were found among the imaging techniques for all the target conditions. Estimates of diagnostic test accuracy were highest for rectocele using MRI (AUC 0.79) or transperineal ultrasonography (AUC 0.85), for enterocele using transperineal (AUC 0.73) or endovaginal ultrasonography (AUC 0.87), for intussusception using evacuation proctography (AUC 0.76) or endovaginal ultrasonography (AUC 0.77), and for anismus using endovaginal (AUC 0.95) or transperineal ultrasonography (AUC 0.78). Interobserver agreement for the diagnosis of rectocele (κ 0.53-0.72), enterocele (κ 0.54-0.94) and anismus (κ 0.43-0.81) was moderate to excellent, but poor to fair for intussusception (κ -0.03 to 0.37) with all techniques. Patient acceptability was better for transperineal and endovaginal ultrasonography as compared with MRI and evacuation proctography (P<.001). Evacuation proctography, MRI, and transperineal and endovaginal ultrasonography were shown to have similar diagnostic test accuracy. Evacuation proctography is not the best available imaging technique. There is no one optimal test for the diagnosis of all posterior pelvic floor disorders. Because transperineal and endovaginal ultrasonography have good test accuracy and patient acceptability, we suggest these could be used for initial assessment of obstructed defecation syndrome. ClinicalTrials.gov, NCT02239302.

Background MicroRNA-1246 (miR-1246), an oncomiR that regulates the expression of multiple cancer-related genes, has been attracted and studied as a promising indicator of various tumors. However, diverse conclusions on diagnostic accuracy have been shown due to the small sample size and limited studies included. This meta-analysis is aimed at systematically assessing the performance of extracellular circulating miR-1246 in screening common cancers. Methods We searched the PubMed/MEDLINE, Web of Science, Cochrane Library, and Google Scholar databases for relevant studies until November 28, 2022. Then, the summary receiver operating characteristic (SROC) curves were drawn and calculated area under the curve (AUC), diagnostic odds ratio (DOR), sensitivity, and specificity values of circulating miR-1246 in the cancer surveillance. Results After selection and quality assessment, 29 eligible studies with 5914 samples (3232 cases and 2682 controls) enrolled in the final analysis. The pooled AUC, DOR, sensitivity, and specificity of circulating miR-1246 in screening cancers were 0.885 (95% confidence interval (CI): 0.827-0.892), 27.7 (95% CI: 17.1-45.0), 84.2% (95% CI: 79.4-88.1), and 85.3% (95% CI: 80.5-89.2), respectively. Among cancer types, superior performance was noted for breast cancer (AUC = 0.950, DOR = 98.5) compared to colorectal cancer (AUC = 0.905, DOR = 47.6), esophageal squamous cell carcinoma (AUC = 0.757, DOR = 8.0), hepatocellular carcinoma (AUC = 0.872, DOR = 18.6), pancreatic cancer (AUC = 0.767, DOR = 12.3), and others (AUC = 0.887, DOR = 27.5, P = 0.007). No significant publication bias in DOR was observed in the meta-analysis (funnel plot asymmetry test with P = 0.652; skewness value = 0.672, P = 0.071). Conclusion Extracellular circulating miR-1246 may serve as a reliable biomarker with good sensitivity and specificity in screening cancers, especially breast cancer.

AI unleashed: A meta-analysis transforming radiological insights in diagnosing abdominal infections.

IntroductionPulmonary hypertension (PH) has an incidence of approximately 6 cases per million adults, with a global prevalence ranging from 49 to 55 cases per million adults. Recent advancements in artificial intelligence (AI) have demonstrated promising improvements in the diagnostic accuracy of imaging for PH, achieving an area under the curve (AUC) of 0.94, compared to seasoned professionals.Research objectiveTo systematically synthesize available evidence on the comparative accuracy of AI versus manual interpretation in detecting PH across various chest imaging modalities, i.e., chest X-ray, echocardiography, CT scan and cardiac MRI.MethodsFollowing PRISMA guidelines, a comprehensive search was conducted across five databases—PubMed, Embase, ScienceDirect, Scopus, and the Cochrane Library—from inception through March 2025. Statistical analysis was performed using R (version 2024.12.1 + 563) with 2 × 2 contingency data. Sensitivity, specificity, and diagnostic odds ratio (DOR) were pooled using a bivariate random-effects model (reitsma() from the mada package), while the AUC were meta-analyzed using logit-transformed values via the metagen() function from the meta package.ResultsThis meta-analysis of 12 studies, encompassing 7,459 patients, demonstrated a statistically significant improvement in diagnostic accuracy of PH with AI integration, evidenced by a logit mean difference in AUC of 0.43 (95% CI: 0.23–0.64; p < 0.0001) and low heterogeneity (I2 = 21.0%, τ2 < 0.0001, p = 0.2090), which was consolidated by pooled AUC of 0.934 on bivariate model. Pooled sensitivity and specificity for AI models were 0.83 (95% CI: 0.73–0.90) and 0.91 (95% CI: 0.86–0.95), respectively, with substantial heterogeneity for sensitivity (I2 = 83.8%, τ2 = 0.4934, p < 0.0001) and moderate for specificity (I2 = 41.5%, τ2 = 0.1015, p = 0.1146); the diagnostic odds ratio was 54.26 (95% CI: 22.50–130.87) with substantial heterogeneity (I2 = 70.7%, τ2 = 0.8451, p = 0.0023). Sensitivity analysis showed stable estimates and did not reduce heterogeneity across outcomes.ConclusionAI-integrated imaging significantly enhances diagnostic accuracy for pulmonary hypertension, with higher sensitivity (0.83) and specificity (0.91) compared to manual interpretation across chest imaging modalities. However, further high-quality trials with externally validated cohorts may be needed to confirm these findings and reduce variability among AI models across diverse clinical settings.

Point-of-care ultrasound (POCUS) is increasingly used in emergency departments for the rapid detection of pneumothorax. While POCUS offers bedside convenience, its diagnostic accuracy compared with standard imaging remains variable, necessitating an updated synthesis of evidence. We conducted a systematic review and meta-analysis following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Diagnostic Test Accuracy (PRISMA-DTA) guidelines. Databases including PubMed, Scopus, Web of Science, and Google Scholar were searched for studies evaluating POCUS for pneumothorax detection in emergency settings. Data on sensitivity, specificity, and operator characteristics were extracted. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), and a bivariate random-effects model was used to pool diagnostic accuracy metrics. Subgroup and sensitivity analyses explored sources of heterogeneity. Fifteen studies comprising 3,840 patients were included. Pooled sensitivity of POCUS for detecting pneumothorax was 74.3% (95% CI: 55.4-87.4%), and pooled specificity was 99.1% (95% CI: 98.5-99.9%). Diagnostic odds ratio was 104.4 (95% CI: 93.0-112.8), with positive and negative likelihood ratios of 15.1 (95% CI: 5.66-40.38) and 0.028 (95% CI: 0.008-0.095), respectively. Subgroup analyses showed higher sensitivity for prospective studies, non-trauma patients, the two-point ultrasound protocol, and operators with greater training and experience, while specificity remained consistently high across all subgroups. No significant publication bias was detected. POCUS is a highly specific and moderately sensitive tool for the rapid detection of pneumothorax in emergency settings. Diagnostic performance improves with standardized protocols and experienced operators. Despite some variability in sensitivity, POCUS can reliably identify pneumothorax and reduce unnecessary thoracic interventions.

A meta-analysis was conducted to systematically assess the diagnostic efficacy of miRNAs in severe pneumonia, aiming to identify valuable diagnostic markers for this critical condition. Based on the research topic, relevant search terms were carefully formulated, leading to a systematic search of the PubMed, EMBASE, Cochrane Library, and Web of Science databases. Articles were selected based on inclusion and exclusion criteria. The summary receiver operating characteristic curve was plotted to derive the pooled area under the curve (AUC), sensitivity, and specificity results. Diagnostic likelihood ratio (DLR) positive, DLR negative, diagnostic score, and diagnostic odds ratio (DOR) were calculated and presented by forest plots. Subgroup analysis was conducted to investigate the source of heterogeneity. 12 articles (encompassing 17 tests) were deemed suitable for inclusion based on predetermined criteria. The findings revealed a sensitivity of 0.79 (95 % CI=0.73–0.84) and specificity of 0.88 (95 % CI=0.81–0.93), with an AUC of 0.89 (95 % CI=0.86–0.92). Additionally, the positive DLR was 6.82 (95 % CI=4.25–10.95), while the negative DLR stood at 0.24 (95 % CI=0.19–0.31). The overall diagnostic score reached 3.34 (95 % CI=2.82–3.86), and DOR was calculated at 28.28 (95 % CI=16.80–47.58), underscoring a robust diagnostic capability for pneumonia. Subgroup analyses suggested that the observed high heterogeneity could be attributed to variations in specimen types. Importantly, the assessment indicated no significant publication bias among the included tests. MiRNAs have high diagnostic value in severe pneumonia, demonstrating high sensitivity, specificity, and diagnostic accuracy.

Background/Objectives: To evaluate the diagnostic accuracy of artificial intelligence (AI)-based imaging techniques for liver fibrosis and metabolic dysfunction-associated steatotic liver disease (MASLD). Materials and Methods: We performed a comprehensive search in PubMed, Embase, Cochrane Library, and Web of Science until August 2025. A total of 15 studies (mean age of patients 56 years, 60% male) were included. The risk of bias in the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Diagnostic performance metrics were calculated using a random-effects bivariate model, including the area under the curve (AUC), sensitivity, specificity, positive and negative likelihood ratios, and diagnostic odds ratio. Meta-regression analysis was conducted to investigate potential sources of heterogeneity when I2 was ≥50%. A p-value < 0.05 was considered statistically significant. Results: For liver fibrosis, pooled sensitivity was 0.85, specificity was 0.81, and AUC was 0.92. For MASLD, sensitivity was 0.86, specificity was 0.95, and AUC was 0.99. Different imaging modalities and AI classifiers caused significant study heterogeneity. To avoid misleading pooled estimates across varied datasets, imaging modality and AI model subgroup analyses were performed. Only three studies were used to estimate MASLD; therefore, considerable between-study heterogeneity should be considered. Conclusions: AI-based imaging modalities demonstrate promising diagnostic accuracy for liver fibrosis and MASLD, warranting further standardization to enhance diagnostic consistency.

Comparison of the diagnostic accuracy of interleukin-27 and adenosine deaminase for tuberculous pleural effusion: A systematic review and meta-analysis with head-to-head design.

Ischemic stroke remains a leading cause of death and disability worldwide, with large vessel occlusion (LVO) accounting for a disproportionate share of poststroke morbidity. Early identification of LVO is essential for timely intervention with endovascular thrombectomy; however, the clinical scales currently used for triage vary widely in their application and accuracy. This study assesses the diagnostic performance of clinical stroke scales in predicting LVO. A systematic review was conducted to identify studies evaluating the diagnostic accuracy of prehospital stroke scales for detecting LVO. Pooled sensitivity and specificity were estimated using a bivariate random-effects model, with diagnostic performance further assessed through summary receiver operating characteristic (ROC) curves and area under the curve (AUC) analysis. A Bayesian network meta-analysis was conducted to rank the scales using surface under the cumulative ranking (SUCRA) probabilities, and post hoc analyses were performed to evaluate publication bias. A total of 58 studies comprising 58,381 patients and 33 unique stroke scales were included in the final analysis. The studies, published between 2014 and 2023, were primarily conducted in North America (50%) and Europe (26%), with a median sample size of 473 participants. Pooled sensitivity ranged from 0.30 (HEMIPARESIS) to 0.99 (LARIO) while specificity varied from 0.34 (FANG) to 0.94 (HEMIPLEGIA). Among the highest-performing scales overall were LARIO (AUC = 0.983), FPSS (AUC = 0.896), FACE2AD (AUC = 0.876), and ACT-FAST (AUC = 0.873). In prehospital settings, FPSS (AUC = 0.896), FAST VAN (AUC = 0.878), and FACE2AD (AUC = 0.876) demonstrated strong performance while LARIO (AUC = 0.983) and ACT-FAST (AUC = 0.883) showed the highest accuracy in hospital settings. Bayesian network meta-analysis identified POMONA (SUCRA = 0.877), NIHSS (0.856), sNIHSS EMS (0.854), G-FAST (0.823), and SAFE (0.788) as the top-ranked scales. Funnel plot analysis revealed minimal publication bias among the most frequently evaluated tools, including RACE, CPSS, and NIHSS. Numerous clinical scales are available for detecting LVO in the prehospital setting. While several demonstrate strong performance in specific contexts, there remains a clear need for a simple, accurate, and generalizable tool to reliably identify patients with LVO across diverse clinical environments.

Screening using low-dose computed tomography (LDCT) is a more effective approach and has the potential to detect lung cancer more accurately. We aimed to conduct a meta-analysis to estimate the accuracy of population-based screening studies primarily assessing baseline LDCT screening for lung cancer. MEDLINE, Excerpta Medica Database, and Web of Science were searched for articles published up to April 10, 2022. According to the inclusion and exclusion criteria, the data of true positives, false-positives, false negatives, and true negatives in the screening test were extracted. Quality Assessment of Diagnostic Accuracy Studies-2 was used to evaluate the quality of the literature. A bivariate random effects model was used to estimate pooled sensitivity and specificity. The area under the curve (AUC) was calculated by using hierarchical summary receiver-operating characteristics analysis. Heterogeneity between studies was measured using the Higgins I2 statistic, and publication bias was evaluated using a Deeks' funnel plot and linear regression test. A total of 49 studies with 157,762 individuals were identified for the final qualitative synthesis; most of them were from Europe and America (38 studies), ten were from Asia, and one was from Oceania. The recruitment period was 1992 to 2018, and most of the subjects were 40 to 75 years old. The analysis showed that the AUC of lung cancer screening by LDCT was 0.98 (95% CI: 0.96-0.99), and the overall sensitivity and specificity were 0.97 (95% CI: 0.94-0.98) and 0.87 (95% CI: 0.82-0.91), respectively. The funnel plot and test results showed that there was no significant publication bias among the included studies. Baseline LDCT has high sensitivity and specificity as a screening technique for lung cancer. However, long-term follow-up of the whole study population (including those with a negative baseline screening result) should be performed to enhance the accuracy of LDCT screening.