On Merging Feature Engineering and Deep Learning for Diagnosis, Risk Prediction and Age Estimation Based on the 12-Lead ECG

Zvuloni, Eran; Read, Jesse; Ribeiro, Antônio H.; Ribeiro, Antônio Luiz Pinho; Behar, Joachim A.

doi:10.1109/tbme.2023.3239527

Cited by 15 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 The hypothesis is further confirmed by studies merging traditional and deep learning features, suggesting that the traditional ECG features alone do not account for the good performance in age prediction from ECGs. 13 In the present analysis, the association of DNN-estimated ECG-age with all-cause death did not change when excluding ECGs from individuals with previous MI and AF. Previous studies have found that known ECG features that better capture the excess risk are related to low-frequency components of the ECG, usually related to P and T waves, but are not restricted to them.…”

Section: Discussionmentioning

confidence: 41%

See 1 more Smart Citation

Association Between Electrocardiographic Age and Cardiovascular Events in Community Settings: The Framingham Heart Study

Brant

Ribeiro

Pinto-Filho

et al. 2023

Circ: Cardiovascular Quality and Outcomes

View full text Add to dashboard Cite

BACKGROUND: Deep neural networks have been used to estimate age from ECGs, the electrocardiographic age (ECG-age), which predicts adverse outcomes. However, this prediction ability has been restricted to clinical settings or relatively short periods. We hypothesized that ECG-age is associated with death and cardiovascular outcomes in the long-standing community-based FHS (Framingham Heart Study). METHODS: We tested the association of ECG-age with chronological age in the FHS cohorts in ECGs from 1986 to 2021. We calculated the gap between chronological and ECG-age (Δage) and classified individuals as having normal, accelerated, or decelerated aging, if Δage was within, higher, or lower than the mean absolute error of the model, respectively. We assessed the associations of Δage, accelerated and decelerated aging with death or cardiovascular outcomes (atrial fibrillation, myocardial infarction, and heart failure) using Cox proportional hazards models adjusted for age, sex, and clinical factors. RESULTS: The study population included 9877 FHS participants (mean age, 55±13 years; 54.9% women) with 34 948 ECGs. ECG-age was correlated to chronological age (r=0.81; mean absolute error, 9±7 years). After 17±8 years of follow-up, every 10-year increase of Δage was associated with 18% increase in all-cause mortality (hazard ratio [HR], 1.18 [95% CI, 1.12–1.23]), 23% increase in atrial fibrillation risk (HR, 1.23 [95% CI, 1.17–1.29]), 14% increase in myocardial infarction risk (HR, 1.14 [95% CI, 1.05–1.23]), and 40% increase in heart failure risk (HR, 1.40 [95% CI, 1.30–1.52]), in multivariable models. In addition, accelerated aging was associated with a 28% increase in all-cause mortality (HR, 1.28 [95% CI, 1.14–1.45]), whereas decelerated aging was associated with a 16% decrease (HR, 0.84 [95% CI, 0.74–0.95]). CONCLUSIONS: ECG-age was highly correlated with chronological age in FHS. The difference between ECG-age and chronological age was associated with death, myocardial infarction, atrial fibrillation, and heart failure. Given the wide availability and low cost of ECG, ECG-age could be a scalable biomarker of cardiovascular risk.

show abstract

Section: Discussionmentioning

confidence: 41%

“…12 The model was trained to predict an individual’s age learning to detect and extract features directly from the data, not relying on traditional ECG interpretation. 12,13 The goal of the learning was to capture how aging affects ECG waveform.…”

Section: Methodsmentioning

confidence: 99%

Association Between Electrocardiographic Age and Cardiovascular Events in Community Settings: The Framingham Heart Study

Brant

Ribeiro

Pinto-Filho

et al. 2023

Circ: Cardiovascular Quality and Outcomes

View full text Add to dashboard Cite

show abstract

“…Using a multi‐modal ML approach incorporating ECG and cardiac imaging data (radiomics), Pujadas et al (2022) reported better AF prediction than models using ECG features alone. Both S. Raghunath et al (2021) and Zvuloni et al (2023) developed deep neural network models to predict new‐onset AF using 12‐lead ECG data. Through deep learning analysis of ECGs, the authors demonstrated models could successfully identify those at high future risk of AF‐related stroke.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Salvi,

Acharya,

Seoni

et al. 2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Atrial fibrillation (AF) affects more than 30 million individuals worldwide, making it the most prevalent cardiac arrhythmia on a global scale. This systematic review summarizes recent advancements in applying artificial intelligence (AI) techniques for AF detection, prediction, and guiding treatment selection and risk stratification. In adherence with the PRISMA guidelines (Preferred Reporting Items for Systematic Reviews and Meta‐Analyses), a total of 171 pertinent studies conducted between 2013 and 2023 were examined. Studies applying machine learning (ML) and deep learning (DL) to electrocardiogram (ECG), photoplethysmography (PPG), wearable data, and other sources were evaluated. For AF detection, most works employed DL (48 studies) and ML (28 studies) on ECG data. DL methods directly analyzed ECG waveforms and outperformed approaches relying on hand‐crafted features. For prediction and risk stratification, 22 studies used ML while 7 leveraged DL on ECG. An emerging trend showed the growing potential of PPG for AF screening. Overall, AI demonstrated promising capabilities across various AF‐related tasks. However, real‐world implementation faces challenges including a lack of interpretability, the need for multimodal data integration, prospective performance validation, and regulatory compliance. Future research directions involve quantifying model uncertainty, enhancing transparency, and conducting population‐based clinical trials to facilitate translation into practice.This article is categorized under: Application Areas > Health Care Application Areas > Science and Technology Technologies > Artificial Intelligence

show abstract

“…The Telehealth Network of Minas Gerais (TNMG) dataset is one of the electrocardiogram datasets extensively used for cardiac rhythm classification 9 . In this context, Zvuloni et al 10 compared the performance of Feature Engineering (FE), Deep Learning (DL), and a combined approach (FE+DL) for ECG classification. The FE approach involves initial signal analysis using feature engineering methods to extract features, followed by feature selection using Minimum Redundancy Maximum Relevance (mRMR).…”

Section: A Backgroundmentioning

confidence: 99%

Cardiac abnormality detection with a tiny diagonal state space model based on sequential liquid neural processing units

Huang,

Leung,

Cui

et al. 2023

Preprint

View full text Add to dashboard Cite

This manuscript presents and studies the performance of the Diagonal State Space Sequence (S4D) model based on the Closed-form Continuous-time (CfC) network in order to achieve a high-performing cardiac abnormality detection method that is robust, generalizable, and tiny in size. Our S4D-CfC model is evaluated on 12- and 1-lead electrocar-diogram (ECG) data from over 20,000 patients. The system exhibits validation results with strong average F1 score and average AUROC value of 0.88 and 98%, respectively. To demonstrate the tiny machine learning (tinyML) of our 242 KB size model, we deployed the system on relatively resource-constrained hardware to evaluate its training performance on the edge. Such on-device fine-tuning can enhance personalized solutions in this context, allowing the system to learn each patient’s data features. A comparison with a structured 2D Convolutional LSTM (ConvLSTM2D) CfC model (ConvCfC) demonstrates the S4D-CfC model’s superior performance. The size of the proposed model is also significantly small (25 KB) while maintaining reasonable performance on 2.5s data, 75% shorter than the original 10s data, making it suitable for resource-constrained hardware and reducing latency. In summary, the S4D-CfC model represents a groundbreaking advancement in cardiac abnormality detection, offering robustness, generalization, and practicality with the potential for efficient deployment on limited-resource platforms, revolutionizing healthcare technology.

show abstract

On Merging Feature Engineering and Deep Learning for Diagnosis, Risk Prediction and Age Estimation Based on the 12-Lead ECG

Cited by 15 publications

References 29 publications

Association Between Electrocardiographic Age and Cardiovascular Events in Community Settings: The Framingham Heart Study

Association Between Electrocardiographic Age and Cardiovascular Events in Community Settings: The Framingham Heart Study

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Cardiac abnormality detection with a tiny diagonal state space model based on sequential liquid neural processing units

Contact Info

Product

Resources

About