Accuracy of ECG indices for diagnosis of left ventricular hypertrophy in people >65 years: results from the ActiFE study

Echocardiography-based machine learning algorithm for distinguishing ischemic cardiomyopathy from dilated cardiomyopathy

BACKGROUND

Machine learning (ML) can identify and integrate connections among data and has the potential to predict events. Heart failure is primarily caused by cardiomyopathy, and different etiologies require different treatments. The present study examined the diagnostic value of a ML algorithm that combines echocardiographic data to automatically differentiate ischemic cardiomyopathy (ICM) from dilated cardiomyopathy (DCM).

METHODS

We retrospectively collected the echocardiographic data of 200 DCM patients and 199 ICM patients treated in the First Affiliated Hospital of Guangxi Medical University between July 2016 and March 2022. All patients underwent invasive coronary angiography for diagnosis of ICM or DCM. The data were randomly divided into a training set and a test set via 10-fold cross-validation. Four ML algorithms (random forest, logistic regression, neural network, and XGBoost [ML algorithm under gradient boosting framework]) were used to generate a training model for the optimal subset, and the parameters were optimized. Finally, model performance was independently evaluated on the test set, and external validation was performed on 79 patients from another center.

RESULTS

Compared with the logistic regression model (area under the curve [AUC] = 0.925), neural network model (AUC = 0.893), and random forest model (AUC = 0.900), the XGBoost model had the best identification rate, with an average sensitivity of 72% and average specificity of 78%. The average accuracy was 75%, and the AUC of the optimal subset was 0.934. External validation produced an AUC of 0.804, accuracy of 78%, sensitivity of 64% and specificity of 93%.

CONCLUSIONS

We demonstrate that utilizing advanced ML algorithms can help to differentiate ICM from DCM and provide appreciable precision for etiological diagnosis and individualized treatment of heart failure patients.

Clinical applicability and diagnostic performance of electrocardiographic criteria for left ventricular hypertrophy diagnosis in older adults

Recently, a new ECG criterion, the Peguero-Lo Presti (PLP), improved overall accuracy in the diagnosis of left ventricular hypertrophy (LVH)—compared to traditional ECG criteria, but with few patients with advanced age. We analyzed patients with older age and examined which ECG criteria would have better overall performance. A total of 592 patients were included (83.1% with hypertension, mean age of 77.5 years) and the PLP criterion was compared against Cornell voltage (CV), Sokolow-Lyon voltage (SL) and Romhilt-Estes criteria (cutoffs of 4 and 5 points, RE4 and RE5, respectively) using LVH defined by the echocardiogram as the gold standard. The PLP had higher AUC than the CV, RE and SL (respectively, 0.70 vs 0.66 vs 0.64 vs 0.67), increased sensitivity compared with the SL, CV and RE5 (respectively, 51.9% [95% CI 45.4–58.3%] vs 28.2% [95% CI 22.6–34.4%], p < 0.0001; vs 35.3% [95% CI 29.2–41.7%], p < 0.0001; vs 44.4% [95% CI 38.0–50.9%], p = 0.042), highest F1 score (58.3%) and net benefit for most of the 20–60% threshold range in the decision curve analysis. Overall, despite the best diagnostic performance in older patients, the PLP criterion cannot rule out LVH consistently but can potentially be used to guide clinical decision for echocardiogram ordering in low-resource settings.

Prediction of Left Ventricular Mass Index Using Electrocardiography in Essential Hypertension - A Multiple Linear Regression Model

Background

Current electrocardiography (ECG) criteria indicate only the presence or absence of left ventricular hypertrophy (LVH). LVH is a continuum and a direct relationship exists between left ventricular mass (LVM) and cardiovascular event rate. We developed a mathematical model predictive of LVM index (LVMI) using ECG and non-ECG variables by correlating them with echocardiography determined LVMI.

Patients and Methods

The model was developed in a cohort of patients on treatment for essential hypertension (BP>140/90 mm of Hg) who underwent concurrent ECG and echocardiography. One hundred and forty-seven subjects were included in the study (56.38±11.84 years, 66% males). LVMI was determined by echocardiography (113.76±33.06 gm/m²). A set of ECG and non-ECG variables were correlated with LVMI for inclusion in the multiple linear regression model. The model was checked for multicollinearity, normality and homogeneity of variances.

Results

The final regression equation formulated with the help of unstandardized coefficients and constant was LVMI=18.494+ 1.704 (aLL) + 0.969 (RaVL+SV3) + 0.295 (MBP) + 15.406 (IHD) (aLL – sum of deflections in augmented limb leads; RaVL+SV3 – sum of deflection of (R wave in aVL + S wave in V3); MBP – mean blood pressure; IHD=1 for the presence of the disease, IHD=0 for the absence of the disease).

Conclusion

In the model, 50.4% of the variability in LV mass is explained by the variables used. The findings warrant further studies for the development of better and validated models that can be incorporated in microprocessor-based ECG devices. The determination of LVMI with ECG only will be a cost-effective and readily accessible tool in patient care.

A speckle-tracking strain-based artificial neural network model to differentiate cardiomyopathy type

Objectives. In heart failure, invasive angiography is often employed to differentiate ischaemic from non-ischaemic cardiomyopathy. We aim to examine the predictive value of echocardiographic strain features alone and in combination with other features to differentiate ischaemic from non-ischaemic cardiomyopathy, using artificial neural network (ANN) and logistic regression modelling. Design. We retrospectively identified 204 consecutive patients with an ejection fraction <50% and a diagnostic angiogram. Patients were categorized as either ischaemic (n = 146) or non-ischaemic cardiomyopathy (n = 58). For each patient, left ventricular strain parameters were obtained. Additionally, regional wall motion abnormality, 13 electrocardiographic (ECG) features and six demographic features were retrieved for analysis. The entire cohort was randomly divided into a derivation and a validation cohort. Using the parameters retrieved, logistic regression and ANN models were developed in the derivation cohort to differentiate ischaemic from non-ischaemic cardiomyopathy, the models were then tested in the validation cohort. Results. A final strain-based ANN model, full feature ANN model and full feature logistic regression model were developed and validated, F₁ scores were 0.82, 0.79 and 0.63, respectively. Conclusions. Both ANN models were more accurate at predicting cardiomyopathy type than the logistic regression model. The strain-based ANN model should be validated in other cohorts. This model or similar models could be used to aid the diagnosis of underlying heart failure aetiology in the form of the online calculator (https://cimti.usj.edu.lb/strain/index.html) or built into echocardiogram software.

Clinical, Electrocardiographic, and Echocardiographic Features in Hospitalized Nonagenarians (90+): Comparison between the Genders

OBJECTIVES

We investigated the clinical, electrocardiographic, and echocardiographic determinants of the cardiac status in nonagenarian patients.

METHODS

We consecutively examined 654 Caucasian patients (232 males and 422 females) aged ≥90 years. All patients underwent clinical examination, ECG, and transthoracic echocardiography.

RESULTS

Their average age was 92.5 ± 2.5 years. Patients were predominately female of older age (p < 0.0001 and p = 0.02, respectively). A history of cardiovascular disease was present in 78.4% of the participants. One third of the patients was hospitalized for cardiovascular causes, with females being twice as many (p < 0.0001). Females showed higher levels of serum cholesterol, triglycerides, and glycemia (p < 0.0001, p< 0.0001, and p = 0.04 respectively). Sinus rhythm was detected in 65%, and atrial fibrillation in 31% of the overall population. Heart rate, PR and corrected QT (QTc) intervals, right bundle branch block (RBBB) and RBBB associated with left anterior fascicular block (LAFB) were higher in males (p < 0.0001, p = 0.036, p = 0.009, p = 0.001, and p = 0.004, respectively). Aortic root dimension, left ventricular (LV) mass index, and indexed LV systolic-diastolic volumes were higher in males (p < 0.001, p < 0.0001, p < 0.001, and p < 0.0001, respectively). Women showed fewer LV segmental kinetic disorders (p = 0009) and higher LV ejection fraction (LVEF; p< 0.0001). Hyperuricemia was positively associated with a history of cardiovascular disease (r = 0.15), glycemia (r = 19), creatininemia (r = 0.50), uremia (r = 0.51), triglycerides (r = 0.19), PR interval (r = 0.14), and left bundle branch block (r = 0.11), and inversely associated with sinus rhythm (r = -0.14) and LVEF (r = -0.17). Diabetes was positively correlated with PR and QTc intervals (r = 0.14 and r = 0.10, respectively), and RBBB with LFAB (r = 0.10), and inversely correlated with LVEF (r = -0.10).

CONCLUSIONS

We found a remarkable presence of cardiovascular risk factors, ECG, and structural alterations in hospitalized nonagenarians, which presents more commonly in males.

Outcome of resynchronization therapy on superficial and endocardial electrophysiological findings

Cardiac resynchronization therapy (CRT) has proven efficacious in the treatment of patients with heart failure and dyssynchronous activation. Currently, we select suitable CRT candidates based on the QRS complex duration (QRSd) and morphology with left bundle branch block being the optimal substrate for resynchronization. To improve CRT response rates, recommendations emphasize attention to electrical parameters both before implant and after it. Therefore, we decided to study activation times before and after CRT on the body surface potential maps (BSPM) and to compare thus obtained results with data from electroanatomical mapping using the CARTO system. Total of 21 CRT recipients with symptomatic heart failure (NYHA II-IV), sinus rhythm, and QRSd >/=150 ms and 7 healthy controls were studied. The maximum QRSd and the longest and shortest activation times (ATmax and ATmin) were set in the BSPM maps and their locations on the chest were compared with CARTO derived time interval and site of the latest (LATmax) and earliest (LATmin) ventricular activation. In CRT patients, all these parameters were measured during both spontaneous rhythm and biventricular pacing (BVP) and compared with the findings during the spontaneous sinus rhythm in the healthy controls. QRSd was 169.7+/-12.1 ms during spontaneous rhythm in the CRT group and 104.3+/-10.2 ms after CRT (p<0.01). In the control group the QRSd was significantly shorter: 95.1+/-5.6 ms (p<0.01). There was a good correlation between LATmin(CARTO) and ATmin(BSPM). Both LATmin and ATmin were shorter in the control group (LATmin(CARTO) 24.8+/-7.1 ms and ATmin(BSPM) 29.6+/-11.3 ms, NS) than in CRT group (LATmin(CARTO) was 48.1+/-6.8 ms and ATmin(BSPM) 51.6+/-10.1 ms, NS). BVP produced shortening compared to the spontaneous rhythm of CRT recipients (LATmin(CARTO) 31.6+/-5.3 ms and ATmin(BSPM) 35.2+/-12.6 ms; p<0.01 spontaneous rhythm versus BVP). ATmax exhibited greater differences between both methods with higher values in BSPM: in the control group LATmax(CARTO) was 72.0+/-4.1 ms and ATmax (BSPM) 92.5+/-9.4 ms (p<0.01), in the CRT candidates LATmax(CARTO) reached only 106.1+/-6.8 ms whereas ATmax(BSPM) 146.0+/-12.1 ms (p<0.05), and BVP paced rhythm in CRT group produced improvement with LATmax(CARTO) 92.2+/-7.1 ms and ATmax(BSPM) 130.9+/-11.0 ms (p<0.01 before and during BVP). With regard to the propagation of ATmin and ATmax on the body surface, earliest activation projected most often frontally in all 3 groups, whereas projection of ATmax on the body surface was more variable. Our results suggest that compared to invasive electroanatomical mapping BSPM reflects well time of the earliest activation, however provides longer time-intervals for sites of late activation. Projection of both early and late activated regions of the heart on the body surface is more variable than expected, very likely due to changed LV geometry and interposed tissues between the heart and superficial ECG electrode.