Three-dimensional echocardiography in evaluation of left ventricular indices

Detection of Right and Left Ventricular Dysfunction in Pediatric Patients Using Artificial Intelligence-Enabled ECGs

BACKGROUND

Early detection of left and right ventricular systolic dysfunction (LVSD and RVSD respectively) in children can lead to intervention to reduce morbidity and death. Existing artificial intelligence algorithms can identify LVSD and RVSD in adults using a 12-lead ECG; however, its efficacy in children is uncertain. We aimed to develop novel artificial intelligence-enabled ECG algorithms for LVSD and RVSD detection in pediatric patients.

METHODS AND RESULTS

We identified 10 142 unique pediatric patients (age≤18) with a 10-second, 12-lead surface ECG within 14 days of a transthoracic echocardiogram, performed between 2002 and 2022. LVSD was defined quantitatively by left ventricular ejection fraction (LVEF). RVSD was defined semiquantitatively. Novel pediatric models for LVEF ≤35% and LVEF <50% achieved excellent test areas under the curve of 0.93 (95% CI, 0.89-0.98) and 0.88 (95% CI, 0.83-0.94) respectively. The model to detect LVEF <50% had a sensitivity of 0.85, specificity of 0.80, positive predictive value of 0.095, and negative predictive value of 0.995. In comparison, the previously validated adult data-derived model for LVEF <35% achieved an area under the curve of 0.87 (95% CI, 0.84-0.90) for LVEF ≤35% in children. A novel pediatric model for any RVSD detection reached a test area under the curve of 0.90 (0.87-0.94).

CONCLUSIONS

An artificial intelligence-enabled ECG demonstrates accurate detection of both LVSD and RVSD in pediatric patients. While adult-trained models offer good performance, improvements are seen when training pediatric-specific models.

Enhancing convolutional neural network predictions of electrocardiograms with left ventricular dysfunction using a novel sub-waveform representation

Background

Electrocardiogram (ECG) deep learning (DL) has promise to improve the outcomes of patients with cardiovascular abnormalities. In ECG DL, researchers often use convolutional neural networks (CNNs) and traditionally use the full duration of raw ECG waveforms that create redundancies in feature learning and result in inaccurate predictions with large uncertainties.

Objective

For enhancing these predictions, we introduced a sub-waveform representation that leverages the rhythmic pattern of ECG waveforms (data-centric approach) rather than changing the CNN architecture (model-centric approach).

Results

We applied the proposed representation to a population with 92,446 patients to identify left ventricular dysfunction. We found that the sub-waveform representation increases the performance metrics compared to the full-waveform representation. We observed a 2% increase for area under the receiver operating characteristic curve and 10% increase for area under the precision-recall curve. We also carefully examined three reliability components of explainability, interpretability, and fairness. We provided an explanation for enhancements obtained by heartbeat alignment mechanism. By developing a new scoring system, we interpreted the clinical relevance of ECG features and showed that sub-waveform representation further pushes the scores towards clinical predictions. Finally, we showed that the new representation significantly reduces prediction uncertainties within subgroups that contributes to individual fairness.

Conclusion

We expect that this added control over the granularity of ECG data will improve the DL modeling for new artificial intelligence technologies in the cardiovascular space.

Artificial Intelligence Algorithm for Screening Heart Failure with Reduced Ejection Fraction Using Electrocardiography

Although heart failure with reduced ejection fraction (HFrEF) is a common clinical syndrome and can be modified by the administration of appropriate medical therapy, there is no adequate tool available to perform reliable, economical, early-stage screening. To meet this need, we developed an interpretable artificial intelligence (AI) algorithm for HFrEF screening using electrocardiography (ECG) and validated its performance. This retrospective cohort study included two hospitals. An AI algorithm based on a convolutional neural network was developed using 39,371 ECG results from 17,127 patients. The internal validation included 3,470 ECGs from 2,908 patients. Furthermore, we conducted external validation using 4,362 ECGs from 4,176 patients from another hospital to verify the applicability of the algorithm across different centers. The end-point was to detect HFrEF, defined as an ejection fraction <40%. We also visualized the regions in 12 lead ECG that affected HFrEF detection in the AI algorithm and compared this to the previously documented literature. During the internal and external validation, the areas under the curves of the AI algorithm using a 12 lead ECG for detecting HFrEF were 0.913 (95% confidence interval, 0.902-0.925) and 0.961 (0.951-0.971), respectively, and the areas under the curves of the AI algorithm using a single-lead ECG were 0.874 (0.859-0.890) and 0.929 (0.911-0.946), respectively. The deep learning-based AI algorithm performed HFrEF detection well using not only a 12 lead but also a single-lead ECG. These results suggest that HFrEF can be screened not only using a 12 lead ECG, as is typical of a conventional ECG machine, but also with a single-lead ECG performed by a wearable device employing the AI algorithm, thereby preventing irreversible disease progression and mortality.

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram

Asymptomatic left ventricular dysfunction (ALVD) is present in 3-6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found^1-4. An inexpensive, noninvasive screening tool for ALVD in the doctor's office is not available. We tested the hypothesis that application of artificial intelligence (AI) to the electrocardiogram (ECG), a routine method of measuring the heart's electrical activity, could identify ALVD. Using paired 12-lead ECG and echocardiogram data, including the left ventricular ejection fraction (a measure of contractile function), from 44,959 patients at the Mayo Clinic, we trained a convolutional neural network to identify patients with ventricular dysfunction, defined as ejection fraction ≤35%, using the ECG data alone. When tested on an independent set of 52,870 patients, the network model yielded values for the area under the curve, sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7%, respectively. In patients without ventricular dysfunction, those with a positive AI screen were at 4 times the risk (hazard ratio, 4.1; 95% confidence interval, 3.3 to 5.0) of developing future ventricular dysfunction compared with those with a negative screen. Application of AI to the ECG-a ubiquitous, low-cost test-permits the ECG to serve as a powerful screening tool in asymptomatic individuals to identify ALVD.

Evaluation of Left Ventricular Systolic Function and Mass in Primary Hypertensive Patients by Echocardiography

Hypertension is an independent risk factor for cardiovascular diseases. The accurate evaluation of cardiovascular risk is of paramount importance in the management of hypertensive patients. Conventional echocardiographic methods have provided the assessment of left ventricular systolic function and mass for many years. Tissue Doppler imaging, 3-dimensional echocardiography, and speckle tracking echocardiography are newer echocardiographic modalities for the left ventricular systolic function and mass quantification. The major emphasis of this review is to evaluate the left ventricular systolic function and mass by conventional and newly developed echocardiographic in hypertensive patients.

Reference Values for Real Time Three-Dimensional Echocardiography-Derived Left Ventricular Volumes and Ejection Fraction: Review and Meta-Analysis of Currently Available Studies

INTRODUCTION

Current guidelines recommend three-dimensional echocardiography (3DE) as the reference technique to assess left ventricular (LV) volumes and ejection fraction (EF). We performed a meta-analysis to identify normative reference values by real time 3DE in healthy subjects.

METHODS

We searched MEDLINE and the Cochrane Library databases using the key search terms three-dimensional echocardiography, volumes, and healthy. Data were pooled using random-effects meta-analysis, and source of variation was investigated using meta-regression. After selection, 13 articles were included (2806 subjects). Four studies were conducted in children and young adolescents; one study provided data in an independent pediatric subgroup.

RESULTS

In adults, pooled mean value for LV EDV was 98.4 mL (95%CI, 87-110 mL), while LV ESV mean value was 37.0 mL (95%CI, 32-42 mL). LV EF mean value was 62.9% (95%CI 61.7-64.2%). Male subjects showed a significant increase in both LV EDV index (mean difference 5.3 mL/m(2) ; P < 0.001) and LV ESV index (mean difference 3.3 mL/m(2) ; P < 0.001). LV EF was significantly higher in female subjects (P = 0.003). In pediatric studies, LV EDV pooled mean value was 53.1 mL (95%CI, 38.1-68 mL), while for LV ESV, it was 19.8 mL (95%CI, 14.8-24.8 mL); LV EF mean value was 63.3% (95%CI, 61.6-65%). Significant heterogeneity and inconsistency were noted among studies. Age, systolic blood pressure, and heart rate were identified as a source of between-studies variation for LV volumes. Body surface area was a predictor of nonindexed LV volumes.

CONCLUSIONS

Data from available studies of normative values for 3DE were summarized. Our findings may increase the generalizability of LV normative data by 3DE.

Left Ventricular Dyssynchrony by Three-Dimensional Echocardiography: Current Understanding and Potential Future Clinical Applications

Left ventricular mechanical dyssynchrony is an important prognostic factor for patients with symptomatic systolic heart failure and has emerged as a therapeutic target for cardiac resynchronization therapy (CRT). However, approximately one-third of patients fail to improve after CRT based on current guideline recommendations and electrocardiographic criteria. Two-dimensional echocardiography and tissue Doppler-based techniques have shown variable results in assessment of left ventricular (LV) dyssynchrony and have limited value in clinical practice. Three-dimensional echocardiography (3DE) is an appealing novel imaging modality that has been recently used in quantitative evaluation of global and regional LV function. There is accumulating evidence that 3DE measurement of LV systolic dyssynchrony index may potentially play a role in predicting the short- and long-term response to CRT and further improve patient selection for CRT. New developments in 3DE speckle tracking technique and strain analysis may further improve the accuracy of LV mechanical dyssynchrony assessment in this population. In addition, recent studies suggest that mechanical dyssynchrony is present in patients with LV hypertrophy and diastolic heart failure. Three-dimensional echocardiographic assessment of dyssynchrony may aid in diagnosis and in predicting long-term outcome in these patients. We will summarize current understanding of 3DE techniques and parameters in assessment of LV mechanical dyssynchrony in the population of patients with systolic heart failure, LV hypertrophy, and diastolic heart failure. A number of the novel 3DE techniques described in this review are early in their stage of development, and they will continue to evolve and need further testing in large multicenter studies.

The Effect of Habitual Physical Training on Left Ventricular Function During Exercise Assessed by Three-Dimensional Echocardiography

BACKGROUND

Stroke volume (SV) in trained athletes continuously increases with progressive exercise intensity. We studied whether physical training affected left ventricle (LV) function response to exercise using 3D echocardiography and tissue Doppler imaging (TDI).

METHODS

Eleven male university athletes and 12 male university nonathletes were enrolled in this study. After baseline data were collected, subjects performed a symptom-limited supine bicycle ergometer exercise test. Initial workload was 25 Watts (W) and increased 25 W every 3 minutes. At rest and every exercise stage, LV end-systolic and diastolic volume index (LVEDVI and LVESVI), SV index (SVI), cardiac index (CI), LV ejection fraction (LVEF), and early lateral mitral flow velocity (Ea) were evaluated. Heart rate (HR), and systolic and diastolic blood pressure (SBP and DBP) were continuously recorded.

RESULTS

Nonathletes showed a slow increase in CI, and SVI reached a plateau value at a HR of 90 beats per minute (bpm). In contrast, CI and SVI increased progressively and continuously in athletes. Both CI and SVI were significantly higher in athletes than in nonathletes at HRs of 100, 110, and 120 bpm. LVEDVI kept increasing in athletes while it plateaued in nonathletes. In contrast, LVESV decreased continuously during exercise in both groups. There was no significant difference in LVEF, Ea, SBP, or DBP at rest and during exercise between the two groups.

CONCLUSION

LV responses to exercise in athletes were different from those of in nonathletes; thus, habitual physical training may play an important role in the increase in both SVI and CI in young individuals.

Left ventricular ejection fraction and volumes: it depends on the imaging method

Background and Methods

In order to provide guidance for using measurements of left ventricular (LV) volume and ejection fraction (LVEF) from different echocardiographic methods a PubMed review was performed on studies that reported reference values in normal populations for two-dimensional (2D ECHO) and three-dimensional (3D ECHO) echocardiography, nuclear imaging, cardiac computed tomography, and cardiac magnetic resonance imaging (CMR). In addition all studies (2 multicenter, 16 single center) were reviewed, which included at least 30 patients, and the results compared of noncontrast and contrast 2D ECHO, and 3D ECHO with those of CMR.

Results

The lower limits for normal LVEF and the normal ranges for end-diastolic (EDV) and end-systolic (ESV) volumes were different in each method. Only minor differences in LVEF were found in studies comparing CMR and 2D contrast echocardiography or noncontrast 3D echocardiography. However, EDV and ESV measured with all echocardiographic methods were smaller and showed greater variability than those derived from CMR. Regarding agreement with CMR and reproducibility, all studies showed superiority of contrast 2D ECHO over noncontrast 2D ECHO and 3D ECHO over 2D ECHO. No final judgment can be made about the comparison between contrast 2D ECHO and noncontrast or contrast 3D ECHO.

Conclusion

Contrast 2D ECHO and noncontrast 3D ECHO show good reproducibility and good agreement with CMR measurements of LVEF. The agreement of volumes is worse. Further studies are required to assess the clinical value of contrast 3D ECHO as noncontrast 3D ECHO is only reliable in patients with good acoustic windows.

A Critical Reappraisal of the Current Clinical Indications to Cardiac Resynchronisation Therapy

Cardiac resynchronisation therapy (CRT) is a well-established non-pharmacological treatment option for patients with refractory symptomatic heart failure (HF) already under optimal medical therapy. CRT is founded on the principle that interventricular conduction disturbances and more in particular left bundle branch block (LBBB) are deleterious to cardiac performance, and may contribute to the systolic and diastolic incompetency typical of patients with HF. Although CRT is associated with a not negligible percentage of non-response, all the international guidelines on chronic HF have extended their indications to CRT, also to patients with less symptomatic HF who are already showing signs of systolic dysfunction and interventricular dyssynchrony, without giving any substantial advice to reduce the number of failures of this therapy. This review seeks to point out the potential issues linked to CRT, with the aim of making a reappraisal of the clinical evidences supporting the current indications to CRT, and to figure out which type of research should be warranted in the field for the future to reduce the percentage of non-responders to this therapy.