Predicting stroke and mortality in mitral stenosis with atrial flutter: A machine learning approach.

BACKGROUND: Our study hypothesized that an intelligent gradient boosting machine (GBM) model can predict cerebrovascular events and all-cause mortality in mitral stenosis (MS) with atrial flutter (AFL) by recognizing comorbidities, electrocardiographic and echocardiographic parameters. METHODS: The machine learning model was used as a statistical analyzer in recognizing the key risk factors and high-risk features with either outcome of cerebrovascular events or mortality. RESULTS: A total of 2184 patients with their chart data and imaging studies were included and the GBM analysis demonstrated mitral valve area (MVA), right ventricular systolic pressure, pulmonary artery pressure (PAP), left ventricular ejection fraction (LVEF), New York Heart Association (NYHA) class, and surgery as the most significant predictors of transient ischemic attack (TIA/stroke). MVA, PAP, LVEF, creatinine, hemoglobin, and diastolic blood pressure were predictors for all-cause mortality. CONCLUSION: The GBM model assimilates clinical data from all diagnostic modalities and significantly improves risk prediction performance and identification of key variables for the outcome of MS with AFL.

Tachycardia Therapy Outcomes of Ischemic Versus Nonischemic Cardiomyopathy on Cardiac Resynchronization Therapy: A Propensity Score-matched Analysis.

Objective: This investigation aimed to investigate differences between dilated cardiomyopathy (DCM) and ischemic cardiomyopathy (ICM) patients treated with cardiac resynchronization therapy with defibrillator (CRT-D) for tachycardia therapy-related outcomes as well as mortality during follow-up of at least 1 year. Methods: Seventy-eight patients with DCM (n = 42) and ICM (n = 36) with implantation or upgradation to CRT-D were included in this study and analyzed for incidence of non-sustained ventricular tachycardia (NSVT), non-sustained ventricular fibrillation (NSVF), defibrillator therapies, anti-tachycardia pacing (ATP), and mortality. Results: DCM was the underlying etiology in 42 (53.84%) and ICM in 36 (46.15%). Time to first therapy was numerically longer in DCM than in ICM (9.5 ± 2.4 vs. 7.1 ± 3.2; P-value = 0.088). DCM patients had significantly higher therapy-free survival and mortality compared with ICM patients (OR (95%CI): 0.238 (0.155-0.424); log-rank P = 0.017) and (OR (95% CI): 0.612 (0.254-0.924); log-rank P = 0.029). ICM (HR (95%CI): 0.529 (0.243-0.925); P-value = 0.014) CAD (HR (95%CI): 0.326 (0.122-0.691): P-value = 0.003), and NSVT (HR (95%CI): 0.703 (0.513-0.849): P-value = 0.005) were demonstrated as independent predictors of the primary endpoint of appropriate therapy in CRT-D and ICM (HR (95%CI): 0.421 (0.321-0.524); P-value = 0.037), chronic kidney disease (CKD; HR (95%CI): 0.289 (0.198-0.380); P-value = 0.013), and CAD (HR (95%CI): 0.786 (0.531-0.967); P-value = 0.003) were predictors of mortality. Conclusion: The clinical course of ICM and DCM cohorts who were treated with CRT-D differs significantly during follow-up, with increased tachycardia therapy and increased incidence of mortality in ICM patients.

Early Diagnosis of Coronary Artery Disease by Inflammatory Biomarkers of Atherosclerosis in Patients with Angina.

Early diagnosis of coronary artery disease (CAD) in patients with chest pain is a challenge. Currently diagnosis of CAD is confirmed by coronary angiography, which is invasive and not easily available in developing countries. Therefore, it is imperative to establish noninvasive biomarker for early diagnosis of CAD in patients with angina and determine the diagnostic accuracy of inflammatory biomarkers of atherosclerosis in comparison to angiography and correlate with severity of CAD in patients with angina. Diagnostic accuracy study was carried out in tertiary care hospitals, Rawalpindi, Pakistan. Total of 58 patients aged 55.24 ± 11.61 years, with chest pain and troponin-I -ve, having coronary artery stenosis ≥50% were included as cases of CAD and 55 subjects having stenosis <50% were included as controls. Nuclear factor kappa-B (NF-κB), tumor necrosis factor-alpha (TNF-α), interleukin-6 (IL-6), and high-sensitivity C-reactive protein (hs-CRP) were analyzed on immunoassay analyzers. The receiver operating characteristic curve analysis revealed significant (P < 0.05) high area under curve (95% confidence interval) with sensitivity and specificity of NF-κB 0.76 (0.65-0.85), 73% and 65%; TNF-α 0.72 (0.61-0.81), 71% and 69%; IL-6 0.62 (0.52-0.71), 64% and 53% and hs-CRP 0.62 (0.52-0.71), and 53% and 56% in CAD patients compared to controls. There was significant positive correlation between NF-κB (r = 0.44), TNF-α (r = 0.37), IL-6 (r = 0.23), and hs-CRP (r = 0.23) with severity of CAD by Gensini score. The inflammatory biomarkers, especially NF-κB and TNF-α, have highest diagnostic accuracy and indicate severity of atherosclerosis in patients with angina. These markers may be used as noninvasive biomarkers to exclude healthy individuals before undergoing angiography.

Renal arteriovenous malformation: An unusual pathology.

Renal arteriovenous malformations are rare renal vascular abnormalities. More commonly, the term refers to the congenital type of malformation. Only a few cases have ever been presented and reported in the literature, mostly with a nidus. We present the clinical, ultrasound and computed tomography findings and discuss the management related to a 63-year-old male with a right congenital renal arteriovenous malformation without a nidus that was successfully managed with coil embolisation. Relevant literature is hereby reviewed to highlight characteristic imaging and appropriate treatment.