scholarly journals A Novel Approach for Predicting Atrial Fibrillation Recurrence After Ablation Using Deep Convolutional Neural Networks by Assessing Left Atrial Curved M-Mode Speckle-Tracking Images

2021 ◽  
Vol 7 ◽  
Author(s):  
Yi-Ting Hwang ◽  
Hui-Ling Lee ◽  
Cheng-Hui Lu ◽  
Po-Cheng Chang ◽  
Hung-Ta Wo ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Logistic Regression ◽  
Left Atrial ◽  
Speckle Tracking ◽  
Activation Function ◽  
Predictor Variables ◽  
Deep Convolutional Neural Networks ◽  
Logistic Regression Models ◽  
Novel Approach ◽  
Deformation Mechanics

Aims: Curved M-mode images of global strain (GS) and strain rate (GSR) provide sufficiently detailed spatiotemporal information of deformation mechanics. This study investigated whether a deep convolutional neural network (CNN) could accurately classify these images in patients with atrial fibrillation (AF) who underwent radiofrequency catheter ablation (RFCA) with different outcomes.Methods and Results: We retrospectively evaluated 606 consecutive patients who underwent RFCA for drug-refractory AF. Patients were divided into AF-free (n = 443) and AF-recurrent (n = 163) groups. Transthoracic echocardiography was performed within 24 h after RFCA. Left atrial curved M-mode speckle-tracking images were acquired from randomly selected 163 patients in AF-free group and 163 patients in AF-recurrent group as the dataset for deep CNN modeling. We used the ReLu activation function and repeatedly performed CNN model for 32 times to evaluate the stability of hyperparameters. Logistic regression models with the left atrial dimension, emptying fraction, and peak systolic GS as predictor variables were used for comparisons. Images from the apical 2-chamber (2-C) and 4-chamber (4-C) views had distinct features, leading to different CNN performance between settings; of them, the “4-C GS+4-C GSR” setting provided the highest performance index values. All four predictor variables used for logistic regression modeling were significant; however, none of them, individually or in any combined form, could outperform the optimal CNN model.Conclusion: The novel approach using deep CNNs for learning features of left atrial curved M-mode speckle-tracking images seems to be optimal for classifying outcome status after AF ablation.

scholarly journals Relationship between left atrial strain and left atrial bipolar voltage in patients undergoing catheter ablation for atrial fibrillation

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
Y Takahashi ◽  
T Kitai ◽  
T Watanabe ◽  
T Fujita
Keyword(s):  
Atrial Fibrillation ◽  
Left Atrial ◽  
Speckle Tracking ◽  
Longitudinal Strain ◽  
Low Voltage ◽  
Pulmonary Veins ◽  
Global Longitudinal Strain ◽  
Inferior Wall ◽  
Bipolar Voltage ◽  
Global Mean

Abstract Background Low-voltage zone (LVZ) in the left atrium (LA) seems to represent fibrosis. LA longitudinal strain assessed by speckle tracking method is known to correlate with the extent of fibrosis in patients with mitral valve disease. Purpose We sought to identify the relationship between LA longitudinal strain and LA bipolar voltage in patients with atrial fibrillation (AF). We tested the hypothesis that LA strain can predict LA bipolar voltage. Methods A total of 96 consecutive patients undergoing initial AF ablation were analyzed. All patients underwent transthoracic echocardiography including 2D speckle tracking measurement on the day before ablation during sinus rhythm (SR group, N=54) or during AF (AF group, N=42). LA longitudinal strain was measured at basal, mid, and roof level of septal, lateral, anterior, and inferior wall in apical 4- and 2-chamber view. Global longitudinal strain (GLS) was defined as an average value of the 12 segments. LA voltage map was created using EnSite system, and global mean voltage was defined as a mean of bipolar voltage of the whole LA excluding pulmonary veins and left atrial appendage. LVZ was defined as less than 1.0 mV. Results There was a significantly positive correlation between GLS and global mean voltage (r=0.708, p<0.001). Multivariate regression analysis showed that GLS and age were independent predictors of global mean voltage. There was a significant negative correlation between global mean voltage and LVZ areas. Conclusions There was a strong correlation between LA longitudinal strain and LA mean voltage. GLS can independently predict LA mean voltage, subsequently LVZ areas in patients with AF. Funding Acknowledgement Type of funding source: None

Consideration of non-valvular atrial fibrillation with left atrial appendage thrombus formation despite under appropriate oral anticoagulation therapy

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
H Shiraki ◽  
H Tanaka ◽  
K Yamashita ◽  
Y Tanaka ◽  
K Sumimoto ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Oral Anticoagulation ◽  
Left Atrial ◽  
Thrombus Formation ◽  
Anticoagulation Therapy ◽  
Left Ventricular ◽  
Volume Index ◽  
Oral Anticoagulation Therapy

Abstract Background Atrial fibrillation (AF) is the most frequently sustained cardiac arrhythmia, with a prevalence of about 2–3% in the general population. In accordance with CHADS2 or CHA2DS2-VASc score, appropriate oral anticoagulation therapy such as warfarin or direct oral anticoagulants (DOAC) significantly reduced the risk of thromboembolic events. However, left atrial (LA) thrombus can be detected in the LA appendage (LAA) in AF patients despite appropriate oral anticoagulation therapy. Purpose Our purpose was to investigate the associated factors of LAA thrombus formation in non-valvular atrial fibrillation (NVAF) patients despite under appropriate oral anticoagulation therapy. Methods We retrospectively studied consecutive 286 NVAF patients for scheduled catheter ablation or electrical cardioversion for AF in our institution between February 2017 and September 2019. Mean age was 67.1±9.4 years, 79 patients (29.5%) were female, and 140 (52.2%) were paroxysmal AF. All patients underwent transthoracic and transesophageal echocardiography before catheter ablation or electrical cardioversion. All patients received appropriate oral anticoagulation therapy including warfarin or DOAC for at least 3 weeks prior to transesophageal echocardiography based on the current guidelines. LAA thrombus was defined as an echodense intracavitary mass distinct from the underlying endocardium and not caused by pectinate muscles by at least three senior echocardiologists. Results Of 286 NVAF patients with under appropriate oral anticoagulation therapy, LAA thrombus was observed in 9 patients (3.3%). Univariate logistic regression analysis showed that age, paroxysmal AF, CHADS2 score ≥3, left ventricular end-diastolic volume index (LVEDVI), left ventricular ejection fraction (LVEF), left ventricular mass index (LVMI), LA volume index (LAVI), mitral inflow E and mitral e' annular velocities ratio (E/e'), and LAA flow were associated with LAA thrombus formation. It was noteworthy that multivariate logistic regression analysis showed that LAA flow was independent predictor of LAA thrombus (OR: 0.72, 95% CI: 0.59–0.89, p<0.005) as well as LVEF. Furthermore, receiver operating characteristic (ROC) curve analysis identified the optimal cutoff value of LAA flow for predicting LAA thrombus as ≤15cm/s, with a sensitivity of 88%, specificity of 93%, and area under the curve (AUC) of 0.95. Conclusions LAA flow was strongly associated with LAA thrombus formation even in NVAF patients with appropriate oral anticoagulation therapy. According to our findings, further strengthen of oral anticoagulation therapy or percutaneous transcatheter closure of the LAA may be considered in NVAF patients with appropriate oral anticoagulation therapy but low LAA flow, especially <15cm/s. Funding Acknowledgement Type of funding source: None

scholarly journals Left Atrial Deformation And Risk of Transient Ischemic Attack And Stroke In Paroxysmal Atrial Fibrillation

2021 ◽  
Author(s):  
Jian Chen ◽  
Ying Zhao ◽  
Changsheng Ma ◽  
Xin Du ◽  
Yihua He
Keyword(s):  
Atrial Fibrillation ◽  
Body Mass Index ◽  
Regression Analysis ◽  
Linear Regression ◽  
Body Mass ◽  
Left Atrial ◽  
Speckle Tracking ◽  
Linear Regression Analysis ◽  
Volume Index ◽  
Chamber View

Abstract Left atrial (LA) remodeling is closely related to cerebral stroke, but the relationship between impaired deformability of LA in early stages and stroke/TIA is not clear. The aim of this study was to evaluate the changes of LA deformability and its relationship with stroke/TIA events by using Speckle Tracking echocardiography. In 365 patients with paroxysmal atrial fibrillation (AF) (318, Non stroke/TIA; 47, stroke/TIA), comprehensive echocardiography was performed by using speckle tracking imaging to calculate mean LA longitudinal strain and strain rate values from apical four chamber view, apical two chamber view and apical three cavity view. The patients in stroke/TIA group had greater ages, a greater proportion of men and lower LA strain rate during left ventricular (LV) early diastole (SRE), and the difference was statistically significant(p<0.05). In the univariate linear regression analysis, the following clinical and conventional echocardiographic parameters each had a significant linear correlation with SRE(p<0.001), they were E/A ratio, LA volume index, body mass index, mean E/e′, LV ejection fraction, age, proportion of hypertension. Through a multiple linear regression analysis, the results show that there is a linear dependence between SRE and E/A ratio, LA volume index and Body mass index. The regression equation is y=-1.430-0.394X1+0.012X2+0.019X3(p<0.001) (y,SRE; X1,E/A ratio; X2,LA volume index; X3,Body mass index).In the multivariate logistic regression analyses, SRE and Sex ratio were independently risk factors stroke/TIA. (SRE, OR 2.945, 95% CI 1.092-7.943, p= 0.033; Sex, OR 0.462, 95% CI 0.230-0.930, p = 0.031)In patients with paroxysmal AF, SRE could reflect the impaired deformability of LA in early stages, and it was associated with the risk of stroke/TIA.

scholarly journals P594Contrast transthoracic echocardiography as a gatekeeper for patent foramen ovale closureP595Mitral annular displacement in apical four-chamber view by speckle-tracking echocardiography as a simple index for left ventricular longitudinal systolic functionP596Impact of chronic glycemic control on left ventricular myocardial function in young patients with type 1 diabetes mellitusP597Association of left atrial function echocardiographic parametres with fibrosis assesed invasively in patients with sinus rhythm and atrial fibrillation undergoing ablation for atrial fibrillationP598Mitral annular calcification decreases diastolic tissue Doppler velocity(E') in regions affected with calcificationsP5992D longitudinal LV speckle tracking strain pattern in breast cancer survivors: sports activity vs exercise as prescription modelP600Catheter related atrial fibrillation is associated with left atrial deformation in patients with paroxsymal supraventricular tachycardia: a study of two-dimensional speckle tracking echocardiographyP601Early radiotherapy-induced ecg changes and their comparison with echocardiography in breast cancer patientsP602Renal function is a major determinant of decreased sub-epicardial longitudinal strain in hypertensionP603Evaluation of left atrial function in patients with non valvular atrial fibrillation post cardioversion: speckle tracking echocardiographyP604Myocardial dysfunction in ANCA vasculitis measured by two-dimensional speckle tracking echocardiographyP605CRT, arterial stiffness and ventricular-arterial coupling in HFrEFP606Mitral annular morphology and function in cardiac amyloidosis as assessed by three-dimensional speckle tracking echocardiographyP607Coronary plaque characterization in Egyptian metabolic syndrome patients using 64-MDCT

2016 ◽  
Vol 17 (suppl 2) ◽  
pp. ii109-ii113 ◽  
Author(s):  
M. Muratori ◽  
T. Hozumi ◽  
C. Ruisanchez Villar ◽  
E. Pilichowska ◽  
L. Chebrolu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Atrial Fibrillation ◽  
Left Atrial ◽  
Speckle Tracking ◽  
Young Patients ◽  
Left Ventricular ◽  
Atrial Function ◽  
Left Atrial Function ◽  
Doppler Velocity ◽  
Two Dimensional

Abstract 15257: Epicardial and Peri-atrial Fat Attenuation Predict Recurrence in Patients Undergoing Repeat Catheter Ablation for Refractory Atrial Fibrillation

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Mark S Brahier ◽  
Fengwei Zou ◽  
Frank Migliarese ◽  
Milos Tomovic ◽  
Alexandra Taylor ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Logistic Regression ◽  
Adipose Tissue ◽  
Catheter Ablation ◽  
Left Atrial ◽  
Left Atrial Volume ◽  
Epicardial Fat ◽  
Volume Index ◽  
Atrial Volume ◽  
Af Recurrence

Background: Identifying factors predictive of atrial fibrillation (AF) recurrence after catheter ablation (CA) can improve patient selection. It has been hypothesized that inflammatory paracrine signaling by metabolically active adipose tissue induces pathologic changes in surrounding cardiovascular tissue. In fact, fat attenuation on CT has been previously associated with AF recurrence after de novo CA. The purpose of this study was to investigate the predictive qualities of epicardial and peri-atrial adipose tissue in a population undergoing repeat CA. We hypothesized that higher epicardial and left peri-atrial fat attenuation would predict recurrence as markers of increased localized inflammation. Methods: The study population consisted of 84 patients with symptomatic, drug and ablation-refractory AF undergoing repeat CA. All patients had a pre-ablation, contrast-enhanced cardiac CT, which was analyzed for mean fat attenuation in Hounsfield units (HU) and left atrial volume using the post-processing program 3D Slicer. Patients were followed for recurrence of atrial tachyarrhythmias after a 3-month blanking period. We performed logistic regression to adjust for age, sex, BMI, hypertension, smoking history, diabetes, obstructive sleep apnea, and left atrial volume index. Results: Repeat CA patients with recurrence (n=52) had a higher epicardial fat attenuation (-84.8 ±5.6 vs -88.1 ±5.2 HU; p=0.009) and peri-atrial fat attenuation (-81.0 ±4.7 vs -83.2 ±4.3 HU; p=0.036) than those without recurrence (n=32) at a mean follow-up period of 26 ±18 months. Logistic regression analysis showed that epicardial fat attenuation (OR 1.21; p=0.005) and peri-atrial fat attenuation (OR 1.27; p=0.007) are predictive of AF recurrence independent of traditional risk factors. Conclusions: Epicardial and left peri-atrial adipose attenuation are predictive of recurrence in patients undergoing repeat CA for AF.

scholarly journals Risk Assessment Models for Wheat Fusarium Head Blight Epidemics Based on Within-Season Weather Data

2003 ◽  
Vol 93 (4) ◽  
pp. 428-435 ◽  
Author(s):  
E. D. De Wolf ◽  
L. V. Madden ◽  
P. E. Lipps
Keyword(s):  
Logistic Regression ◽  
Relative Humidity ◽  
Fusarium Head Blight ◽  
Prediction Accuracy ◽  
Regression Models ◽  
Weather Conditions ◽  
Predictor Variables ◽  
Stepwise Logistic Regression ◽  
Head Blight ◽  
Logistic Regression Models

Logistic regression models for wheat Fusarium head blight were developed using information collected at 50 location-years, including four states, representing three different U.S. wheat-production regions. Non-parametric correlation analysis and stepwise logistic regression analysis identified combinations of temperature, relative humidity, and rainfall or durations of specified weather conditions, for 7 days prior to anthesis, and 10 days beginning at crop anthesis, as potential predictor variables. Prediction accuracy of developed logistic regression models ranged from 62 to 85%. Models suitable for application as a disease warning system were identified based on model prediction accuracy, sensitivity, specificity, and availability of weather variables at crop anthesis. Four of the identified models correctly classified 84% of the 50 location-years. A fifth model that used only pre-anthesis weather conditions correctly classified 70% of the location-years. The most useful predictor variables were the duration (h) of precipitation 7 days prior to anthesis, duration (h) that temperature was between 15 and 30°C 7 days prior to anthesis, and the duration (h) that temperature was between 15 and 30°C and relative humidity was greater than or equal to 90%. When model performance was evaluated with an independent validation set (n = 9), prediction accuracy was only 6% lower than the accuracy for the original data sets. These results indicate that narrow time periods around crop anthesis can be used to predict Fusarium head blight epidemics.

Sign in / Sign up

Export Citation Format

Share Document