Cardenas McDermott (playphone77)

86±12.7%); p<0.001, and lower LAA emptying velocity (17.53cm/s, IQR 9.54-77.4 vs 63.5cm/s, IQR 7.89-86.4; p<0.001). There was a good correlation between LA TDI and speckle tracking PALS and PALSR and LAA EF% and velocity p<0.001. TDI and PALS and PALSR were found to be significant predictors for LAA thrombus (P<0.05) with good sensitivity and specificity. Left atrium deformation indices are predictors of LAA thrombus or SEC in patients with non-valvular AF with accepted sensitivity and specificity. Left atrium deformation indices are predictors of LAA thrombus or SEC in patients with non-valvular AF with accepted sensitivity and specificity. Machine learning (ML)-based stroke risk stratification systems have typically focused on conventional risk factors (CRF) (AtheroRisk-conventional). Besides CRF, carotid ultrasound image phenotypes (CUSIP) have shown to be powerful phenotypes risk stratification. This is the first ML study of its kind that integrates CUSIP and CRF for risk stratification (AtheroRisk-integrated) and compares against AtheroRisk-conventional. Two types of ML-based setups called (i) AtheroRisk-integrated and (ii) AtheroRisk-conventional were developed using random forest (RF) classifiers. AtheroRisk-conventional uses a feature set of 13 CRF such as age, gender, hemoglobin A1c, fasting blood sugar, low-density lipoprotein, and high-density lipoprotein (HDL) cholesterol, total cholesterol (TC), a ratio of TC and HDL, hypertension, smoking, family history, triglyceride, and ultrasound-based carotid plaque score. AtheroRisk-integrated system uses the feature set of 38 features with a combination of 13 CRF and 25 CUSIP features (6 types of current CUSIP, 6 types of 10-year CUSIP, 12 types of quadratic CUSIP (harmonics), and age-adjusted grayscale median). Logistic regression approach was used to select the significant features on which the RF classifier was trained. The performance of both ML systems was evaluated by area-under-the-curve (AUC) statistics computed using a leave-one-out cross-validation protocol. Left and right common carotid arteries of 202 Japanese patients were retrospectively examined to obtain 404 ultrasound scans. RF classifier showed higher improvement in AUC (~57%) for leave-one-out cross-validation protocol. Using RF classifier, AUC statistics for AtheroRisk-integrated system was higher (AUC=0.99,p-value<0.001) compared to AtheroRisk-conventional (AUC=0.63,p-value<0.001). The AtheroRisk-integrated ML system outperforms the AtheroRisk-conventional ML system using RF classifier. The AtheroRisk-integrated ML system outperforms the AtheroRisk-conventional ML system using RF classifier. Patients undergoing successful balloon mitral valvuloplasty (BMV) have variable improvement in New York Heart Association (NYHA) functional class (FC), exercise capacity (EC) and regression of systolic pulmonary artery pressure (sPAP). Improvement in net atrioventricular compliance (Cn), one of the major determinants of above factors is not routinely assessed. Aim of present study was to assess the change in Cn after successful BMV and its correlation with above factors. 50 patients of very severe mitral stenosis in sinus rhythm who underwent successful BMV have been studied. NYHA FC, 6min walk test (6MWT) and echocardiographic evaluation was done 24h before and at 2 weeks, 12 weeks and 24 weeks after BMV. Echocardiographic parameters of patients with improvement in NYHA class of ≥2 (group A) were also compared with those with improvement in NYHA class of ≤1 (group B). Following successful BMV, there was progressive improvement in Cn upto 12 weeks with no further significant improvement till 24 weeks. Change in Cn showed very good correlation with change in NYHA class [r=0.62, p<0.01], 6MWT [r=0.30, p0.03] and regression of sPAP assessed at 12 weeks and was maintained upto 24 weeks. Change in MVA did