Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs

Attia, Zachi I.; Friedman, Paul A.; Noseworthy, Peter A.; López-Jiménez, Francisco; Ladewig, Dorothy J.; Satam, Gaurav; Pellikka, Patricia A.; Munger, Thomas M.; Asirvatham, Samuel J.; Scott, Christopher G.; Carter, Rickey E.; Kapa, Suraj

doi:10.1161/circep.119.007284

Cited by 280 publications

(273 citation statements)

References 16 publications

Supporting

Mentioning

250

Contrasting

Unclassified

Order By: Relevance

“…Removing EOG and ECG artifacts mostly reduced performance suggesting that age-related information was present in EOG and ECG. For example, one can easily imagine that older subjects produced less blinks or showed different eye-movement patterns (Thavikulwat et al, 2015) and also cardiac activity may change across the lifespan (Attia et al, 2019).…”

Section: How Important Is Preprocessing For Cross-subject Prediction?mentioning

confidence: 99%

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Sabbagh

Ablin

Varoquaux

et al. 2019

Preprint

View full text Add to dashboard Cite

Predicting biomedical outcomes from Magnetoencephalography and Electroencephalography (M/EEG) is central to applications like decoding, brain-computer-interfaces (BCI) or biomarker development and is facilitated by supervised machine learning. Yet most of the literature is concerned with within-subject classification. Here, we focus on predicting continuous outcomes from M/EEG signal power across subjects. Considering different generative mechanisms for M/EEG signals and the biomedical outcome, we propose statistically-consistent predictive models that avoid sourcereconstruction based on the covariance as representation. Our mathematical analysis and ground truth simulations demonstrated that consistent parameter estimation can be obtained with Source Power Comodulation (SPoC) supervised spatial filtering or by embedding with Riemannian geometry. Additional simulations revealed that Riemannian methods were more robust to model violations, in particular geometric distortions induced by individual anatomy. To estimate the relative contribution of brain dynamics and anatomy to prediction performance, we propose a novel model inspection procedure based on biophysical forward modeling. Applied to cross-subject prediction, the analysis revealed that the Riemannian model better exploited anatomical information while sensitivity to brain dynamics was similar across methods. We then probed the robustness of the models across different data cleaning options. Environmental denoising was globally important but Riemannian models were strikingly robust and continued performing even without preprocessing. Our results suggest each method has its niche: SPoC is practical for within-subject prediction while the Riemannian model may enable simple end-to-end learning.

show abstract

Section: How Important Is Preprocessing For Cross-subject Prediction?mentioning

confidence: 99%

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Sabbagh

Ablin

Varoquaux

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…5,6,8 There have been several studies that challenged to predict BA or "heart age" using ECG. [9][10][11] Moreover, it has been reported that there is a discrepancy between BA estimated by ECG and the actual CA, 9 which could be related to individual physical conditions and also various cardiovascular diseases. This concept could be utilized to the simple method of screening for the patient health status, but for actual clinical use, we may have to consider the racial difference in the performance for the prediction models of BA.…”

Section: Introductionmentioning

confidence: 99%

“…11 Moreover, so far, most of the models have developed with only several representative ECG parameters by linear regression model, 10,12 and in only one report, arti cial intelligence modeling was applied. 9 In the present study, we developed a prediction model for BA with hundreds of automatically measured ECG parameters by principal component analysis (PCA) algorithm 4 using a single-center cohort in a Japanese cardiovascular hospital.…”

Section: Introductionmentioning

confidence: 99%

Prediction of biological age and all-cause mortality by 12-lead electrocardiogram in patients without structural heart disease

Hirota

Suzuki

Arita

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The 12-lead electrocardiogram (ECG) is affected by not only the cardiovascular but also the non-cardiovascular status. Whether ECG can be the determinant of biological age (BA) and the gap between chronological age (CA) and ECG-predicted BA reflect differences in prognosis are unclear. Methods: In the Shinken Database 2010 – 2017 (n = 19170), 12-lead ECG was analyzed in 13005 patients excluding those with structural heart disease or having pacing beats, atrial or ventricular tachyarrhythmia, and indeterminate axis (R axis > 180˚) on index ECG. The prediction model of BA was developed by principal component analysis with 438 ECG parameters. The gap between ECG-predicted BA and CA was calculated (AgeDiff = ECG-predicted BA − CA). Results: The ECG-predicted BA was significantly correlated with CA (r = 0.967). Patients with a positively wide AgeDiff had a higher incidence of all-cause mortality compared to those with a narrow AgeDiff or those with negative AgeDiff. The risk of AgeDiff > 0 for all-cause mortality compared with AgeDiff ≤ 0 was 1.78 (95%CI: 1.00 − 3.16), which increased according to the aging and became the highest in patients with CA of 71 − 80 years. Conclusion: Our data suggested that 12-lead ECG can be a tool to estimate BA. The gap between ECG-predicted BA and CA allowed estimation of increased risk of all-cause mortality in patients without structural heart disease.

show abstract

“…Hand motion recognition [9][10][11][12][13][14][15][16][17], Muscle activity recognition [18][19][20][21][22][23] ECG Heartbeat signal classification , Heart disease classification [49][50][51][52][53][54][55][56][57][58][59][60][61][62][63], Sleep-stage classification [64][65][66][67][68], Emotion classification [69], age and gender prediction [70] EEG Brain functionality classification , Brain disease classification , Emotion classification [122][123][124][125][126][127][128][129], Sleep-stage classification [130][131][132][133]…”

Section: Emgmentioning

confidence: 99%

Deep Learning in Physiological Signal Data: A Survey

Rim

Sung

Min

et al. 2020

Sensors

172

View full text Add to dashboard Cite

Deep Learning (DL), a successful promising approach for discriminative and generative tasks, has recently proved its high potential in 2D medical imaging analysis; however, physiological data in the form of 1D signals have yet to be beneficially exploited from this novel approach to fulfil the desired medical tasks. Therefore, in this paper we survey the latest scientific research on deep learning in physiological signal data such as electromyogram (EMG), electrocardiogram (ECG), electroencephalogram (EEG), and electrooculogram (EOG). We found 147 papers published between January 2018 and October 2019 inclusive from various journals and publishers. The objective of this paper is to conduct a detailed study to comprehend, categorize, and compare the key parameters of the deep-learning approaches that have been used in physiological signal analysis for various medical applications. The key parameters of deep-learning approach that we review are the input data type, deep-learning task, deep-learning model, training architecture, and dataset sources. Those are the main key parameters that affect system performance. We taxonomize the research works using deep-learning method in physiological signal analysis based on: (1) physiological signal data perspective, such as data modality and medical application; and (2) deep-learning concept perspective such as training architecture and dataset sources.

show abstract

Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs

Abstract: Supplemental Digital Content is available in the text.

Cited by 280 publications

References 16 publications

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Prediction of biological age and all-cause mortality by 12-lead electrocardiogram in patients without structural heart disease

Deep Learning in Physiological Signal Data: A Survey

Contact Info

Product

Resources

About