Video-Based Deep Learning for Automated Assessment of Left Ventricular Ejection Fraction in Pediatric Patients

Reddy, Charitha D.; Lopez, Leo; Ouyang, David; Zou, James; He, Bryan

doi:10.1016/j.echo.2023.01.015

Cited by 19 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, from a pediatric cardiology perspective, z scores are commonly reported for LV ejection fraction, LV mass, and LV volume. However, both qualitative 49 and quantitative 39,50 cutoffs have limitations. Given the goal to externally validate the model for eventual multicenter use and validation, PHN 22 z scores were incorporated.…”

Section: Discussionmentioning

confidence: 99%

“…34,35 To date, AI has been used in pediatric cardiology primarily for image-based deep learning applications. [36][37][38][39] Analysis of ECG waveforms provides a rapid, easy-to-implement, and cost-effective application for artificial intelligence. Its use in adults has been wideranging, including prediction of ventricular dysfunction, [3][4][5][6][7] ventricular hypertrophy, 8-10 ventricular dilation, 9,11 atrial fibrillation and other arrhythmias, 17,26,40,41 and age, 42,43 sex, 42 and time to death.…”

Section: Clinical Significance and Implicationsmentioning

confidence: 99%

See 1 more Smart Citation

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

Mayourian,

La Cava,

Vaid

et al. 2024

Circulation

View full text Add to dashboard Cite

BACKGROUND: Artificial intelligence–enhanced ECG analysis shows promise to detect ventricular dysfunction and remodeling in adult populations. However, its application to pediatric populations remains underexplored. METHODS: A convolutional neural network was trained on paired ECG–echocardiograms (≤2 days apart) from patients ≤18 years of age without major congenital heart disease to detect human expert–classified greater than mild left ventricular (LV) dysfunction, hypertrophy, and dilation (individually and as a composite outcome). Model performance was evaluated on single ECG–echocardiogram pairs per patient at Boston Children’s Hospital and externally at Mount Sinai Hospital using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). RESULTS: The training cohort comprised 92 377 ECG–echocardiogram pairs (46 261 patients; median age, 8.2 years). Test groups included internal testing (12 631 patients; median age, 8.8 years; 4.6% composite outcomes), emergency department (2830 patients; median age, 7.7 years; 10.0% composite outcomes), and external validation (5088 patients; median age, 4.3 years; 6.1% composite outcomes) cohorts. Model performance was similar on internal test and emergency department cohorts, with model predictions of LV hypertrophy outperforming the pediatric cardiologist expert benchmark. Adding age and sex to the model added no benefit to model performance. When using quantitative outcome cutoffs, model performance was similar between internal testing (composite outcome: AUROC, 0.88, AUPRC, 0.43; LV dysfunction: AUROC, 0.92, AUPRC, 0.23; LV hypertrophy: AUROC, 0.88, AUPRC, 0.28; LV dilation: AUROC, 0.91, AUPRC, 0.47) and external validation (composite outcome: AUROC, 0.86, AUPRC, 0.39; LV dysfunction: AUROC, 0.94, AUPRC, 0.32; LV hypertrophy: AUROC, 0.84, AUPRC, 0.25; LV dilation: AUROC, 0.87, AUPRC, 0.33), with composite outcome negative predictive values of 99.0% and 99.2%, respectively. Saliency mapping highlighted ECG components that influenced model predictions (precordial QRS complexes for all outcomes; T waves for LV dysfunction). High-risk ECG features include lateral T-wave inversion (LV dysfunction), deep S waves in V1 and V2 and tall R waves in V5 and V6 (LV hypertrophy), and tall R waves in V4 through V6 (LV dilation). CONCLUSIONS: This externally validated algorithm shows promise to inexpensively screen for LV dysfunction and remodeling in children, which may facilitate improved access to care by democratizing the expertise of pediatric cardiologists.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Clinical Significance and Implicationsmentioning

confidence: 99%

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

Mayourian,

La Cava,

Vaid

et al. 2024

Circulation

View full text Add to dashboard Cite

show abstract

“…(34,35) As an example, a study exploring echocardiogram image analysis suggested that adult images could not be appropriately generalized to pediatric patients and vice versa. (36) A lack of transparent age reporting, therefore, risks propagating age-related algorithmic bias, with potential clinical, ethical, and societal implications on the target population. (34,37) Mitigating age bias requires a concerted effort to ensure that training and testing datasets appropriately match intended users.…”

Section: Discussionmentioning

confidence: 99%

Health Disparities and Reporting Gaps in Artificial Intelligence (AI) Enabled Medical Devices: A Scoping Review of 692 U.S. Food and Drug Administration (FDA) 510k Approvals

Muralidharan,

Adewale,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

Machine learning and artificial intelligence (AI/ML) models in healthcare may exacerbate health biases. Regulatory oversight is critical in evaluating the safety and effectiveness of AI/ML devices in clinical settings. We conducted a scoping review on the 692 FDA 510k-approved AI/ML-enabled medical devices to examine transparency, safety reporting, and sociodemographic representation. Only 3.6% of approvals reported race/ethnicity, 99.1% provided no socioeconomic data. 81.6% did not report the age of study subjects. Only 46.1% provided comprehensive detailed results of performance studies; only 1.9% included a link to a scientific publication with safety and efficacy data. Only 9.0% contained a prospective study for post-market surveillance. Despite the growing number of market-approved medical devices, our data shows that FDA reporting data remains inconsistent. Demographic and socioeconomic characteristics are underreported, exacerbating the risk of algorithmic bias and health disparity.

show abstract

“…Previous Research reported the application of Deep Learning (DL) to segment the left ventricular epicardium and endocardium. Research in [16] evaluated multiple DL methods for left ventricular endocardium segmentation and found the superiority of encoder-decoder-based architectures over non deep learning methods. Research in [17] implicated U-Net to segment the left ventricle by changing UNet architecture in MFP-U-Net.…”

Section: Previous Research Methodsmentioning

confidence: 99%

Computer Vision-based Efficient Segmentation Method for Left Ventricular Epicardium and Endocardium using Deep Learning

Saif,

Duong,

Holden

2023

IJACSA

View full text Add to dashboard Cite

Segmentation of the Left Ventricular Epicardium and Endocardium remains challenging and significant for valuable investigation of cardiac image classification. Previous research methods did not consider the flexibility of the heart area, so measurements needed to be more consistent and accurate. In addition, previous methods ignored the presence of affectability and additional parts, such as the lung organ inside the frame, during segmentation. Deep learning architectures, specifically convolutional neural networks, have become the primary choice for assessing cardiac medical images. In this context, a Convolutional Neural Network (CNN) can be an effective way to segment the left ventricular epicardium and endocardium as CNN can take data pictures, move enormity to various centers or objects in the image and have the choice to separate one from the other. This research proposes an efficient method for segmenting the left ventricular epicardium and endocardium using the InceptionV3 convolutional neural network. Rather than including fully connected layers on the head of the component maps, the proposed method considers the average of each element map, and the subsequent vector was taken care of legitimately into the SoftMax layer. Data augmentation technique was used to validate the proposed method on large number of dataset images. Besides, the proposed method was validated in publicly available MRI cardiac image datasets. Comprehensive experimental analysis was done by analyzing a large number of performance metrics, i.e., cosine similarity, log cos error, mean absolute error, mean absolute percentage error, mean squared error, mean squared logarithmic error, and root mean squared error. The proposed method depicted superior performance for localization of the left ventricular epicardium and endocardium in terms of all these performance metrics. In addition, the proposed method performed efficiently to get smooth curve for covering the region due to usage of interpolation technique to draw the curve, which made it smoother compared with previous research.

show abstract

Video-Based Deep Learning for Automated Assessment of Left Ventricular Ejection Fraction in Pediatric Patients

Cited by 19 publications

References 46 publications

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

Health Disparities and Reporting Gaps in Artificial Intelligence (AI) Enabled Medical Devices: A Scoping Review of 692 U.S. Food and Drug Administration (FDA) 510k Approvals

Computer Vision-based Efficient Segmentation Method for Left Ventricular Epicardium and Endocardium using Deep Learning

Contact Info

Product

Resources

About