Diagnostic accuracy of artificial intelligence in detecting left ventricular hypertrophy by electrocardiograph: a systematic review and meta-analysis.

Several studies suggested the utility of artificial intelligence (AI) in screening left ventricular hypertrophy (LVH). We hence conducted systematic review and meta-analysis comparing diagnostic accuracy of AI to Sokolow-Lyon's and Cornell's criteria. Our aim was to provide a comprehensive overview of the newly developed AI tools for diagnosing LVH. We searched MEDLINE, EMBASE, and Cochrane databases for relevant studies until May 2023. Included were observational studies evaluating AI's accuracy in LVH detection. The area under the receiver operating characteristic curves (ROC) and pooled sensitivities and specificities assessed AI's performance against standard criteria. A total of 66,479 participants, with and without LVH, were included. Use of AI was associated with improved diagnostic accuracy with summary ROC (SROC) of 0.87. Sokolow-Lyon's and Cornell's criteria had lower accuracy (0.68 and 0.60). AI had sensitivity and specificity of 69% and 87%. In comparison, Sokolow-Lyon's specificity was 92% with a sensitivity of 25%, while Cornell's specificity was 94% with a sensitivity of 19%. This indicating its superior diagnostic accuracy of AI based algorithm in LVH detection. Our study demonstrates that AI-based methods for diagnosing LVH exhibit higher diagnostic accuracy compared to conventional criteria, with notable increases in sensitivity. These findings contribute to the validation of AI as a promising tool for LVH detection.

Screening for viral hepatitis B infection in cancer patients before receiving chemotherapy - A systematic review and meta-analysis.

AIM: We conducted a systematic review and meta-analysis to assess the hepatitis B virus (HBV) screening rate in cancer patients before systemic chemotherapy, aiming to identify those needing antiviral prophylaxis for HBV reactivation. METHODS: We searched PubMed, Embase, Scopus, and Google Scholar for relevant studies. The pooled screening rate was estimated using a random effects model. Subgroup analyses were conducted based on malignancy types, chemotherapy regimens, study period, and HBV endemic regions. RESULTS: The meta-analysis included 29 studies from various endemic regions (19 low-endemic, three lower intermediate-endemic, and seven higher intermediate-endemic). These studies encompassed hematologic malignancies (n = 10), solid-organ tumors (n = 4), and combinations (n = 15). Seven studies used rituximab-containing regimens, four did not, and the remaining 11 did not specify chemotherapy regimens. The pooled screening rate was 57% (95% confidence interval [95%CI]: 46%-68%, I2 = 100%). Over time, screening rates improved from 37% (95%CI: 23%-53%) in 2006-2010 to 68% (54%-80%) in 2011-2015 and 69% (48%-84%) in 2016-2020. Screening rates were highest at 89% (74%-96%) in high endemic countries, followed by 60% (45-73%) in lower-intermediate and 49% (34-64%) in low-endemic countries. Patients with hematological malignancies had a higher screening rate than those with solid organ tumors, 65% (55%-74%) versus 37% (21%-57%), respectively. A screening rate was higher in patients receiving rituximab-containing chemotherapy than non-rituximab regimens, 68% (55%-79%) versus 45% (27%-65%). CONCLUSION: Despite existing guidelines, pre-chemotherapy HBV screening rate remains unsatisfactory, with substantial heterogeneous rates globally. These findings underscore the need for effective strategies to align practices with clinical guidelines.

Abbreviated MRI for Hepatocellular Carcinoma Surveillance - A Systematic Review and Meta-analysis.

BACKGROUND: Given the limited sensitivity of ultrasound in hepatocellular carcinoma (HCC) surveillance, this systematic review and meta-analysis were aimed to assess the diagnostic performance of non-contrast abbreviated MRI (NC-aMRI) compared to contrast-enhanced abbreviated MRI (CE-aMRI) for HCC surveillance, offering evidence-based guidance for clinical decision-making. METHODS: A comprehensive search was conducted across five databases, identifying studies on aMRI for HCC surveillance. The pooled sensitivity and specificity were estimated using a random effects model. Subgroup analyses and meta-regression were performed by study location, proportion of patients with cirrhosis and HCC, and underlying liver diseases. RESULTS: The meta-analysis included 27 studies (2009-2023), distributed between Western (n = 14) and Eastern (n = 13) countries. The pooled sensitivity and specificity (95%CI, I2) were 86% (83-88%, 63%) and 92% (90%-94%, 74%). The NC-aMRI protocols reported in 21 studies exhibited 83% (79-87%, 63%) sensitivity and 91% (88-93%, 67%) specificity, while the 15 studies on CE-aMRI protocols displayed 88% (84-91%, 64%) sensitivity and 94% (90-96%, 78%) specificity, with no statistically significant differences in sensitivity (p = 0.078) or specificity (p = 0.157). Subgroup analysis in NC-aMRI studies showed significant differences in sensitivity for high-prevalent chronic hepatitis B (87% vs. 78%, p = 0.003) and studies done in eastern countries (86% vs. 76%, p = 0.018). Additionally, specificity showed significant differences for high-prevalent chronic hepatitis C (94% vs. 90%, p = 0.009), with meta-regression identifying major sources of study heterogeneity as the inclusion of a majority of patients with chronic hepatitis B (p = 0.008) and the geographic regions where studies were conducted (p = 0.030). CONCLUSION: Surveillance aMRI protocols exhibit satisfactory performance for detecting HCC. NC-aMRI may be used effectively for HCC surveillance, especially in chronic hepatitis B prevalent settings.