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

Advanced electrocardiography heart age: a prognostic, explainable machine learning approach applicable to sinus and non-sinus rhythms

Aims

An explainable advanced electrocardiography (A-ECG) Heart Age gap is the difference between A-ECG Heart Age and chronological age. This gap is an estimate of accelerated cardiovascular aging expressed in years of healthy human aging, and can intuitively communicate cardiovascular risk to the general population. However, existing A-ECG Heart Age requires sinus rhythm. We aim to develop and prognostically validate a revised, explainable A-ECG Heart Age applicable to both sinus and non-sinus rhythms.

Methods and results

An A-ECG Heart Age excluding P-wave measures was derived from the 10-s 12-lead ECG in a derivation cohort using multivariable regression machine learning with Bayesian 5-min 12-lead A-ECG Heart Age as reference. The Heart Age was externally validated in a separate cohort of patients referred for cardiovascular magnetic resonance imaging by describing its association with heart failure hospitalization or death using Cox regression, and its association with comorbidities. In the derivation cohort (n = 2771), A-ECG Heart Age agreed with the 5-min Heart Age (R 2 = 0.91, bias 0.0 ± 6.7 years), and increased with increasing comorbidity. In the validation cohort [n = 731, mean age 54 ± 15 years, 43% female, n = 139 events over 5.7 (4.8-6.7) years follow-up], increased A-ECG Heart Age gap (≥10 years) associated with events [hazard ratio, HR (95% confidence interval, CI) 2.04 (1.38-3.00), C-statistic 0.58 (0.54-0.62)], and the presence of hypertension, diabetes mellitus, hypercholesterolaemia, and heart failure (P ≤ 0.009 for all).

Conclusion

An explainable A-ECG Heart Age gap applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival.

Clinical biomarker-based biological age predicts deaths in Brazilian adults: the ELSA-Brasil study

Biological age is a construct that seeks to evaluate the biological wear and tear process of the organism that cannot be observed by chronological age. We estimate individuals' biological age based on biomarkers from multiple systems and validate it through its association with mortality from natural causes. Biological age was estimated in 12,109 participants (6621 women and 5488 men) from the first visit of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) who had valid data for the biomarkers used in the analyses. Biological age was estimated using the Klemera and Doubal method. The difference between chronological age and biological age (Δage) was computed. Cox proportional hazard models stratified by sex were used to assess whether Δage was associated with mortality risk after a median follow-up of 9.1 years. The accuracy of the models was estimated by the area under the curve (AUC). Δage had equal mean for men and women, with greater variability for men. Cox models showed that every 1-year increase in Δage was associated with increased mortality in men (HR (95% CI) 1.21; 1.17-1.25) and women (HR (95% CI) 1.24; 1.15-1.34), independently of chronological age. Results of the AUC demonstrated that the predictive power of models that only included chronological age (AUC chronological age = 0.7396) or Δage (AUC Δage = 0.6842) was lower than those that included both, chronological age and Δage (AUC chronological age + Δage = 0.802), in men. This difference was not observed in women. We demonstrate that biological age is strongly related to mortality in both genders and is a valid predictor of death in Brazilian adults, especially among men.

Image-based ECG analyzing deep-learning algorithm to predict biological age and mortality risks: interethnic validation

BACKGROUND

Cardiovascular risk assessment is a critical component of healthcare, guiding preventive and therapeutic strategies. In this study, we developed and evaluated an image-based electrocardiogram (ECG) analyzing an artificial intelligence (AI) model that estimates biological age and mortality risk.

METHODS

Using a dataset of 978 319 ECGs from 250 145 patients at Seoul National University Bundang Hospital, we developed a deep-learning model utilizing printed 12-lead ECG images to estimate patients' age (ECG-Age) and 1- and 5-year mortality risks. The model was validated externally using the CODE-15% dataset from Brazil.

RESULTS

The ECG-Age showed a high correlation with chronological age in both the internal and external validation datasets (Pearson's R = 0.888 and 0.852, respectively). In the internal validation, the direct mortality risk prediction models showed area under the curves (AUCs) of 0.843 and 0.867 for 5- and 1-year all-cause mortality, respectively. For 5- and 1-year cardiovascular mortality, the AUCs were 0.920 and 0.916, respectively. In the CODE-15%, the mortality risk predictions showed AUCs of 0.818 and 0.836 for the prediction of 5- and 1-year all-cause mortality, respectively. Compared to the neutral Delta-Age (ECG-Age - chronological age) group, hazard ratios for deaths were 1.88 [95% confidence interval (CI): 1.14-3.92], 2.12 (95% CI: 1.15-3.92), 4.46 (95% CI: 2.22-8.96) and 7.68 (95% CI: 3.32-17.76) for positive Delta-Age groups (5-10, 10-15, 15-20, >20), respectively.

CONCLUSION

An image-based AI-ECG model is a feasible tool for estimating biological age and assessing all-cause and cardiovascular mortality risks, providing a practical approach for utilizing standardized ECG images in predicting long-term health outcomes.

EchoAGE: Echocardiography-based Neural Network Model Forecasting Heart Biological Age

Biological age is a personalized measure of the health status of an organism, organ, or system, as opposed to simply accounting for chronological age. To date, there have been known attempts to create estimators of biological age based on various biomedical data. In this work, we focused on developing an approach for assessing heart biological age using echocardiographic data. The current study included echocardiographic data from more than 5,000 different cases. As a result, we created EchoAGE - neural network model to determine heart biological age, that was tested on echocardiographic data from patients with age-related diseases, patients with multimorbidity, children with progeria syndrome, and diachronic data series. The model estimates biological age with a Mean Absolute Error of approximately 3.5 years, an R-squared value of around 0.88, and a Spearman's rank correlation coefficient greater than 0.9 in men and women. EchoAGE uses indicators such as E/A ratio of maximum flow rates in the first and second phases, thicknesses of the interventricular septum and the posterior left ventricular wall, cardiac output, and relative wall thickness. In addition, we have applied an AI explanation algorithm to improve understanding of how the model performs an assessment.

Enhancing ECG-based heart age: impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions

Electrocardiogram (ECG) is a non-invasive approach to capture the overall electrical activity produced by the contraction and relaxation of the cardiac muscles. It has been established in the literature that the difference between ECG-derived age and chronological age represents a general measure of cardiovascular health. Elevated ECG-derived age strongly correlates with cardiovascular conditions (e.g., atherosclerotic cardiovascular disease). However, the neural networks for ECG age estimation are yet to be thoroughly evaluated from the perspective of ECG acquisition parameters. Additionally, deep learning systems for ECG analysis encounter challenges in generalizing across diverse ECG morphologies in various ethnic groups and are susceptible to errors with signals that exhibit random or systematic distortions To address these challenges, we perform a comprehensive empirical study to determine the threshold for the sampling rate and duration of ECG signals while considering their impact on the computational cost of the neural networks. To tackle the concern of ECG waveform variability in different populations, we evaluate the feasibility of utilizing pre-trained and fine-tuned networks to estimate ECG age in different ethnic groups. Additionally, we empirically demonstrate that finetuning is an environmentally sustainable way to train neural networks, and it significantly decreases the ECG instances required (by more than 100 × ) for attaining performance similar to the networks trained from random weight initialization on a complete dataset. Finally, we systematically evaluate augmentation schemes for ECG signals in the context of age estimation and introduce a random cropping scheme that provides best-in-class performance while using shorter-duration ECG signals. The results also show that random cropping enables the networks to perform well with systematic and random ECG signal corruptions.

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography

Background: We developed a convolutional neural network (CNN) model to detect atrial fibrillation (AF) using the sinus rhythm ECG (SR-ECG). However, the diagnostic performance of the CNN model based on different ECG leads remains unclear. Methods and Results: In this retrospective analysis of a single-center, prospective cohort study, we identified 616 AF cases and 3,412 SR cases for the modeling dataset among new patients (n=19,170). The modeling dataset included SR-ECGs obtained within 31 days from AF-ECGs in AF cases and SR cases with follow-up ≥1,095 days. We evaluated the CNN model's performance for AF detection using 8-lead (I, II, and V1-6), single-lead, and double-lead ECGs through 5-fold cross-validation. The CNN model achieved an area under the curve (AUC) of 0.872 (95% confidence interval (CI): 0.856-0.888) and an odds ratio of 15.24 (95% CI: 12.42-18.72) for AF detection using the eight-lead ECG. Among the single-lead and double-lead ECGs, the double-lead ECG using leads I and V1 yielded an AUC of 0.871 (95% CI: 0.856-0.886) with an odds ratio of 14.34 (95% CI: 11.64-17.67). Conclusions: We assessed the performance of a CNN model for detecting AF using eight-lead, single-lead, and double-lead SR-ECGs. The model's performance with a double-lead (I, V1) ECG was comparable to that of the 8-lead ECG, suggesting its potential as an alternative for AF screening using SR-ECG.

Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decade

Twelve lead electrocardiogram signals capture unique fingerprints about the body's biological processes and electrical activity of heart muscles. Machine learning and deep learning-based models can learn the embedded patterns in the electrocardiogram to estimate complex metrics such as age and gender that depend on multiple aspects of human physiology. ECG estimated age with respect to the chronological age reflects the overall well-being of the cardiovascular system, with significant positive deviations indicating an aged cardiovascular system and a higher likelihood of cardiovascular mortality. Several conventional, machine learning, and deep learning-based methods have been proposed to estimate age from electronic health records, health surveys, and ECG data. This manuscript comprehensively reviews the methodologies proposed for ECG-based age and gender estimation over the last decade. Specifically, the review highlights that elevated ECG age is associated with atherosclerotic cardiovascular disease, abnormal peripheral endothelial dysfunction, and high mortality, among many other cardiovascular disorders. Furthermore, the survey presents overarching observations and insights across methods for age and gender estimation. This paper also presents several essential methodological improvements and clinical applications of ECG-estimated age and gender to encourage further improvements of the state-of-the-art methodologies.

Heart age gap estimated by explainable advanced electrocardiography is associated with cardiovascular risk factors and survival

Aims

Deep neural network artificial intelligence (DNN-AI)-based Heart Age estimations have been presented and used to show that the difference between an electrocardiogram (ECG)-estimated Heart Age and chronological age is associated with prognosis. An accurate ECG Heart Age, without DNNs, has been developed using explainable advanced ECG (A-ECG) methods. We aimed to evaluate the prognostic value of the explainable A-ECG Heart Age and compare its performance to a DNN-AI Heart Age.

Methods and results

Both A-ECG and DNN-AI Heart Age were applied to patients who had undergone clinical cardiovascular magnetic resonance imaging. The association between A-ECG or DNN-AI Heart Age Gap and cardiovascular risk factors was evaluated using logistic regression. The association between Heart Age Gaps and death or heart failure (HF) hospitalization was evaluated using Cox regression adjusted for clinical covariates/comorbidities. Among patients [n = 731, 103 (14.1%) deaths, 52 (7.1%) HF hospitalizations, median (interquartile range) follow-up 5.7 (4.7-6.7) years], A-ECG Heart Age Gap was associated with risk factors and outcomes [unadjusted hazard ratio (HR) (95% confidence interval) (5 year increments): 1.23 (1.13-1.34) and adjusted HR 1.11 (1.01-1.22)]. DNN-AI Heart Age Gap was associated with risk factors and outcomes after adjustments [HR (5 year increments): 1.11 (1.01-1.21)], but not in unadjusted analyses [HR 1.00 (0.93-1.08)], making it less easily applicable in clinical practice.

Conclusion

A-ECG Heart Age Gap is associated with cardiovascular risk factors and HF hospitalization or death. Explainable A-ECG Heart Age Gap has the potential for improving clinical adoption and prognostic performance compared with existing DNN-AI-type methods.

Predicting Future Incidences of Cardiac Arrhythmias Using Discrete Heartbeats from Normal Sinus Rhythm ECG Signals via Deep Learning Methods

This study aims to compare the effectiveness of using discrete heartbeats versus an entire 12-lead electrocardiogram (ECG) as the input for predicting future occurrences of arrhythmia and atrial fibrillation using deep learning models. Experiments were conducted using two types of inputs: a combination of discrete heartbeats extracted from 12-lead ECG and an entire 12-lead ECG signal of 10 s. This study utilized 326,904 ECG signals from 134,447 patients and categorized them into three groups: true-normal sinus rhythm (T-NSR), atrial fibrillation-normal sinus rhythm (AF-NSR), and clinically important arrhythmia-normal sinus rhythm (CIA-NSR). The T-NSR group comprised patients with at least three normal rhythms in a year and no atrial fibrillation or arrhythmias history. Clinically important arrhythmia included atrial fibrillation, atrial flutter, atrial premature contraction, atrial tachycardia, ventricular premature contraction, ventricular tachycardia, right and left bundle branch block, and atrioventricular block over the second degree. The AF-NSR group included normal sinus rhythm paired with atrial fibrillation or atrial flutter within 14 days, and the CIA-NSR group comprised normal sinus rhythm paired with CIA occurring within 14 days. Three deep learning models, ResNet-18, LSTM, and Transformer-based models, were utilized to distinguish T-NSR from AF-NSR and T-NSR from CIA-NSR. The experiments demonstrated the potential of using discrete heartbeats in predicting future arrhythmia and atrial fibrillation incidences extracted from 12-lead electrocardiogram (ECG) signals alone, without any additional patient information. The analysis reveals that these discrete heartbeats contain subtle patterns that deep learning models can identify. Focusing on discrete heartbeats may lead to more timely and accurate diagnoses of these conditions, improving patient outcomes and enabling automated diagnosis using ECG signals as a biomarker.

The NHANES Biological Age Index demonstrates accelerated aging in MS patients

BACKGROUND

Chronological age is associated with disability accumulation in multiple sclerosis (MS). Biological age may give more precise estimates of aging pathways associations with MS severity. Both normal aging and accelerated aging from MS may negatively impact disease course. Multi-marker indices of aging, such as the NHANES biological age index (BAI), may be more robust than single biomarkers in capturing biological age and are strongly associated with mortality risk and aging-related diseases.

OBJECTIVE

We sought to investigate whether the NHANES BAI, utilizing readily available measures in the clinic, captures accelerating aging and correlates with disability in MS participants.

METHODS

We conducted a prospective, cross-sectional case-control pilot study. Consecutive patients who met the 2017 McDonald's Criteria for MS were recruited from May 2020 to May 2022 along with age-similar healthy controls. BAI components included blood pressure, FEV1, serum creatinine, C-reactive protein, blood-urea nitrogen, albumin, alkaline phosphatase, cholesterol, CMV IgG, and hemoglobin A1c. The index was calculated using the Klemara and Doubal method. Spearman correlation and multivariable linear regression models were used to assess the association between BAI and MS clinical outcomes.

RESULTS

A total of 51 MS (68.6% female) and 38 control (68.4% female) participants were recruited. BAI correlated with chronological age (CA) in MS (r2=0.90,p<0.0001) and control participants (r2 =0.87,p<0.0001). The mean BAI was 1.4 years older than CA in MS participants (range +15 to -10.5 years) and 2.2 years younger in control participants (range +11.2 to -14.1 years). In unadjusted Spearman analyses, BAI correlated with the timed 25-foot walk (T25FW, rhos=0.31, p = 0.045) and symbol digit modalities test (SDMT rhos = 0.35, p = 0.018). In a multivariable regression model, a 5-year older BAI was associated with a 1.2-point lower score on SDMT (95%CI -2.2 to -0.25, p = 0.014).

CONCLUSIONS

MS participants were biologically older than their own chronological age and age-similar controls. In this modest-sized pilot sample, there was strongest correlation for MS outcome measures between BAI and the SDMT. These results support further study of the BAI as a marker of biological age variability in MS.

Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms

Background

There is increasing evidence that 12-lead electrocardiograms (ECG) can be used to predict biological age, which is associated with cardiovascular events. However, the utility of artificial intelligence (AI)-predicted age using ECGs remains unclear.

Methods

Using a single-center database, we developed an AI-enabled ECG using 17 042 sinus rhythm ECGs (SR-ECG) to predict chronological age (CA) with a convolutional neural network that yields AI-predicted age. Using the 5-fold cross validation method, AI-predicted age deriving from the test dataset was yielded for all ECGs. The incidence by AgeDiff and the areas under the curve by receiver operating characteristic curve with AI-predicted age for cardiovascular events were analyzed.

Results

During the mean follow-up period of 460.1 days, there were 543 cardiovascular events. The annualized incidence of cardiovascular events was 2.24 %, 2.44 %, and 3.01 %/year for patients with AgeDiff < -6, -6 to ≤6, and >6 years, respectively. The areas under the curve for cardiovascular events with CA and AI-predicted age, respectively, were 0.673 and 0.679 (Delong's test, P = 0.388) for all patients; 0.642 and 0.700 (P = 0.003) for younger patients (CA < 60 years); and 0.584 and 0.570 (P = 0.268) for older patients (CA ≥ 60 years).

Conclusions

AI-predicted age using 12-lead ECGs showed superiority in predicting cardiovascular events compared with CA in younger patients, but not in older patients.

Mortality risk prediction of the electrocardiogram as an informative indicator of cardiovascular diseases

Background

The electrocardiogram (ECG) may be the most popular test in the management of cardiovascular disease (CVD). Although wide applications of artificial intelligence (AI)-enabled ECG have been developed, an integrating indicator for CVD risk stratification was not investigated. Since mortality may be the most important global outcome, this study aimed to develop a survival deep learning model (DLM) to establish a critical ECG value and explore the associations with various CVD events.

Methods

We trained a DLM with 451,950 12-lead resting ECGs obtained from 210,552 patients, for whom 23,592 events occurred. The internal validation set included 27,808 patients with one ECG for each patient. The external validations were performed in a community hospital with 33,047 patients and two transnational data sets with 233,647 and 1631 ECGs. We distinguished the cause of mortality and additionally investigated CVD-related outcomes, including new-onset acute myocardial infarction (AMI), stroke (STK), and heart failure (HF).

Results

The DLM achieved C-indices of 0.858/0.836 in internal/external validation sets by using ECG over a 10-year period. The high-mortality-risk group identified by the proposed DLM presented a hazard ratio (HR) of 14.16 (95% confidence interval (CI): 11.33-17.70) compared to the low-risk group in the internal validation and presented a higher risk of cardiovascular (CV) mortality (HR: 18.50, 95% CI: 9.82-34.84), non-CV mortality (HR: 13.68, 95% CI: 10.76-17.38), AMI (HR: 4.01, 95% CI: 2.24-7.17), STK (HR: 2.15, 95% CI: 1.70-2.72), and HF (HR: 6.66, 95% CI: 4.54-9.77), which was consistent in an independent community hospital. The transnational validation also revealed HRs of 4.91 (95% CI: 2.63-9.16) and 2.29 (95% CI: 2.15-2.44) for all-cause mortality in the SaMi-Trop and Clinical Outcomes in Digital Electrocardiography 15% (CODE15) cohorts.

Conclusions

The mortality risk by AI-enabled ECG may be applied in passive electronic-health-record-based CVD risk screening, which may identify more asymptomatic and unaware high-risk patients.

QT interval is correlated with and can predict the comorbidity of depression and anxiety: A cross-sectional study on outpatients with first-episode depression

OBJECT

Patients with depression are at an increased risk for developing cardiovascular diseases. The associations between electrocardiogram (ECG) abnormalities and the severity of psychiatric disorders, such as depression and anxiety, have not been clearly elucidated. The present study aims to investigate the associations between depression and anxiety symptoms with ECG indices, and to predict the severity of depression and anxiety using ECG indicators.

METHODS

61 outpatients with first-episode depression from the Shanghai Pudong New Area Mental Health Center were selected and met the diagnostic criteria of DSM-IV. All participants provided self-reported scores on the Zung Self-Rating Depression Scale (SDS) and Zung Self-Rating Anxiety Scale (SAS) and underwent the standard 12-lead ECG assessment.

RESULTS

Among the 61 included outpatients (mean [standard deviation, SD] age: 37.84 [13.82] years; 41[67.2%] were female), there were 2 (3.3%) outpatients without depression symptoms, 16 (26.2%) with mild depression, 19 (31.1%) with moderate depression, and 24 (39.3%) with severe depression. Ten (16.4%) outpatients did not have anxiety symptoms, 19 (31.1%) exhibited mild anxiety, 20 (32.8%) exhibited moderate anxiety, and 12 (19.7%) exhibited severe anxiety. Only 1 (1.6%) outpatient exhibited neither depression nor anxiety, 9 (14.8%) and 1 (1.6%) outpatients only exhibited depression and anxiety, respectively, and most outpatients (50 [82.0%]) had comorbid depression and anxiety symptoms. In the correlation analysis, depression and anxiety severity levels were significantly positively correlated (r = 0.717, p < 0.01). Moreover, categorical anxiety significantly differs in QT interval (p = 0.022), and continuous SAS scores were significantly correlated with QT interval (r = 0.263, p = 0.04). In addition, the correlations between ECG measurements and both categorical depression and continuous SDS scores were not statistically significant. The comorbidity of anxiety and depression was significantly correlated with heart rate (p = 0.039) and QT interval (p = 0.002). Disorder status significantly differed with different QT intervals (p = 0.021). In the prediction analysis, QT interval was the only significant predictor (p = 0.01, b = 0.058, Odds Ratio = 1.059) for comorbid anxiety and depression symptoms.

CONCLUSION

This study found that comorbid symptoms of depression and anxiety were significantly associated with QT interval and heart rate. Additionally, QT interval could predict the comorbidity of these two psychiatric disorders. Further prospective research in a larger and high-risk population is needed.

Heart age estimated using explainable advanced electrocardiography

Electrocardiographic (ECG) Heart Age conveying cardiovascular risk has been estimated by both Bayesian and artificial intelligence approaches. We hypothesised that explainable measures from the 10-s 12-lead ECG could successfully predict Bayesian 5-min ECG Heart Age. Advanced analysis was performed on ECGs from healthy subjects and patients with cardiovascular risk or proven heart disease. Regression models were used to predict patients' Bayesian 5-min ECG Heart Ages from their standard, resting 10-s 12-lead ECGs. The difference between 5-min and 10-s ECG Heart Ages were analyzed, as were the differences between 10-s ECG Heart Age and the chronological age (the Heart Age Gap). In total, 2,771 subjects were included (n = 1682 healthy volunteers, n = 305 with cardiovascular risk factors, n = 784 with cardiovascular disease). Overall, 10-s Heart Age showed strong agreement with the 5-min Heart Age (R2 = 0.94, p < 0.001, mean ± SD bias 0.0 ± 5.1 years). The Heart Age Gap was 0.0 ± 5.7 years in healthy individuals, 7.4 ± 7.3 years in subjects with cardiovascular risk factors (p < 0.001), and 14.3 ± 9.2 years in patients with cardiovascular disease (p < 0.001). Heart Age can be accurately estimated from a 10-s 12-lead ECG in a transparent and explainable fashion based on known ECG measures, without deep neural network-type artificial intelligence techniques. The Heart Age Gap increases markedly with cardiovascular risk and disease.

All-Subset Analysis Improves the Predictive Accuracy of Biological Age for All-Cause Mortality in Chinese and U.S. Populations

BACKGROUND

Klemera-Doubal's method (KDM) is an advanced and widely applied algorithm for estimating biological age (BA), but it has no uniform paradigm for biomarker processing. This article proposed all subsets of biomarkers for estimating BAs and assessed their association with mortality to determine the most predictive subset and BA.

METHODS

Clinical biomarkers, including those from physical examinations and blood assays, were assessed in the China Health and Nutrition Survey (CHNS) 2009 wave. Those correlated with chronological age (CA) were combined to produce complete subsets, and BA was estimated by KDM from each subset of biomarkers. A Cox proportional hazards regression model was used to examine and compare each BA's effect size and predictive capacity for all-cause mortality. Validation analysis was performed in the Chinese Longitudinal Healthy Longevity Survey (CLHLS) and National Health and Nutrition Examination Survey (NHANES). KD-BA and Levine's BA were compared in all cohorts.

RESULTS

A total of 130 918 panels of BAs were estimated from complete subsets comprising 3-17 biomarkers, whose Pearson coefficients with CA varied from 0.39 to 1. The most predictive subset consisted of 5 biomarkers, whose estimated KD-BA had the most predictive accuracy for all-cause mortality. Compared with Levine's BA, the accuracy of the best-fitting KD-BA in predicting death varied among specific populations.

CONCLUSION

All-subset analysis could effectively reduce the number of redundant biomarkers and significantly improve the accuracy of KD-BA in predicting all-cause mortality.

Electrocardiogram-Based Heart Age Estimation by a Deep Learning Model Provides More Information on the Incidence of Cardiovascular Disorders

OBJECTIVE

The biological age progression of the heart varies from person to person. We developed a deep learning model (DLM) to predict the biological age via ECG to explore its contribution to future cardiovascular diseases (CVDs).

METHODS

There were 71,741 cases ranging from 20 to 80 years old recruited from the health examination center. The development set used 32,707 cases to train the DLM for estimating the ECG-age, and 8,295 cases were used as the tuning set. The validation set included 30,469 ECGs to follow the outcomes, including all-cause mortality, cardiovascular-cause mortality, heart failure (HF), diabetes mellitus (DM), chronic kidney disease (CKD), acute myocardial infarction (AMI), stroke (STK), coronary artery disease (CAD), atrial fibrillation (AF), and hypertension (HTN). Two independent external validation sets (SaMi-Trop and CODE15) were also used to validate our DLM.

RESULTS

The mean absolute errors of chronologic age and ECG-age was 6.899 years (r = 0.822). The higher difference between ECG-age and chronological age was related to more comorbidities and abnormal ECG rhythm. The cases with the difference of more than 7 years had higher risk on the all-cause mortality [hazard ratio (HR): 1.61, 95% CI: 1.23-2.12], CV-cause mortality (HR: 3.49, 95% CI: 1.74-7.01), HF (HR: 2.79, 95% CI: 2.25-3.45), DM (HR: 1.70, 95% CI: 1.53-1.89), CKD (HR: 1.67, 95% CI: 1.41-1.97), AMI (HR: 1.76, 95% CI: 1.20-2.57), STK (HR: 1.65, 95% CI: 1.42-1.92), CAD (HR: 1.24, 95% CI: 1.12-1.37), AF (HR: 2.38, 95% CI: 1.86-3.04), and HTN (HR: 1.67, 95% CI: 1.51-1.85). The external validation sets also validated that an ECG-age >7 years compare to chronologic age had 3.16-fold risk (95% CI: 1.72-5.78) and 1.59-fold risk (95% CI: 1.45-1.74) on all-cause mortality in SaMi-Trop and CODE15 cohorts. The ECG-age significantly contributed additional information on heart failure, stroke, coronary artery disease, and atrial fibrillation predictions after considering all the known risk factors.

CONCLUSIONS

The ECG-age estimated via DLM provides additional information for CVD incidence. Older ECG-age is correlated with not only on mortality but also on other CVDs compared with chronological age.