Percutaneous Mitral Valve Repair for Secondary Mitral Regurgitation: A Systematic Review and Meta-Analysis.

This systematic review and meta-analysis aimed to investigate whether percutaneous mitral valve repair (PMVr) using MitraClip was more effective than surgery or medical therapy for long-term morbidity and mortality. We searched MEDLINE, EMBASE, and CENTRAL (Cochrane Library) databases to identify relevant studies that recruited adult patients with functional or secondary mitral valve regurgitation who underwent PMVr with MitraClip implantation using appropriate search terms and Boolean operators. The odds ratios (ORs) were pooled using the random-effects model. A total of 14 studies recruiting 2,593 patients were included. Within 12 months of follow-up, patients who underwent PMVr did not maintain mitral valve regurgitation grade 2+ (OR 0.22, 95% confidence interval [CI] 0.12 to 0.41, p <0.0001, I2 = 0.0%, p = 0.52) or symptom-free heart failure (OR 0.47, 95% CI 0.29 to 0.77, p = 0.0028, I2 = 0.0%, p = 0.66) compared with their surgical counterparts. Patients were more likely to be rehospitalized for heart failure (OR 2.79, 95% CI 1.54 to 5.05, p = 0.0007, I2 = 0.0%, p = 0.51). However, there was no difference between the groups in terms of all-cause or cardiovascular mortality. Whereas, in comparison with medical therapy, PMVr significantly reduced all-cause mortality at 12 and ≥24 months of follow-up (OR 0.41, 95% CI 0.24, 0.69, p = 0.0009, I2 = 32%, p = 0.23 and OR 0.55, 95% CI 0.40, 0.75, p = 0.0002, I2 = 0.0%, p = 0.45, respectively). In conclusion, there was no difference in all-cause death at 12 or 24 months of follow-up between PMVr and the surgical approach, but the durability of valvular repair was inferior with PMVr. In comparison with medical therapy, there was a significant reduction in mortality with PMVr.

Diagnostic Accuracy of Machine Learning AI Architectures in Detection and Classification of Lung Cancer: A Systematic Review.

The application of artificial intelligence (AI) in diagnostic imaging has gained significant interest in recent years, particularly in lung cancer detection. This systematic review aims to assess the accuracy of machine learning (ML) AI algorithms in lung cancer detection, identify the ML architectures currently in use, and evaluate the clinical relevance of these diagnostic imaging methods. A systematic search of PubMed, Web of Science, Cochrane, and Scopus databases was conducted in February 2023, encompassing the literature published up until December 2022. The review included nine studies, comprising five case-control studies, three retrospective cohort studies, and one prospective cohort study. Various ML architectures were analyzed, including artificial neural network (ANN), entropy degradation method (EDM), probabilistic neural network (PNN), support vector machine (SVM), partially observable Markov decision process (POMDP), and random forest neural network (RFNN). The ML architectures demonstrated promising results in detecting and classifying lung cancer across different lesion types. The sensitivity of the ML algorithms ranged from 0.81 to 0.99, while the specificity varied from 0.46 to 1.00. The accuracy of the ML algorithms ranged from 77.8% to 100%. The AI architectures were successful in differentiating between malignant and benign lesions and detecting small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). This systematic review highlights the potential of ML AI architectures in the detection and classification of lung cancer, with varying levels of diagnostic accuracy. Further studies are needed to optimize and validate these AI algorithms, as well as to determine their clinical relevance and applicability in routine practice.

Emerging PET Tracers in Cardiac Molecular Imaging.

18F-fluorodeoxyglucose (FDG) and 18F-sodium fluoride (NaF) represent emerging PET tracers used to assess atherosclerosis-related inflammation and molecular calcification, respectively. By localizing to sites with high glucose utilization, FDG has been used to assess myocardial viability for decades, and its role in evaluating cardiac sarcoidosis has come to represent a major application. In addition to determining late-stage changes such as loss of perfusion or viability, by targeting mechanisms present in atherosclerosis, PET-based techniques have the ability to characterize atherogenesis in the early stages to guide intervention. Although it was once thought that FDG would be a reliable indicator of ongoing plaque formation, micro-calcification as portrayed by NaF-PET/CT appears to be a superior method of monitoring disease progression. PET imaging with NaF has the additional advantage of being able to determine abnormal uptake due to coronary artery disease, which is obscured by physiologic myocardial activity on FDG-PET/CT. In this review, we discuss the evolving roles of FDG, NaF, and other PET tracers in cardiac molecular imaging.