Electrocardiographic predictors of cardiovascular events in patients at high cardiovascular risk: a multicenter study

Determinants of artificial intelligence electrocardiogram-derived age and its association with cardiovascular events and mortality: a systematic review and meta-analysis

Artificial intelligence (AI)-ECG-derived age (AI-ECG age) and Heart Delta Age (HDA)-the difference between AI-ECG and chronological age-are emerging tools for assessing cardiovascular health. We systematically searched PubMed, Embase, Web of Science, and Scopus from inception through September 2024. Seventeen original studies utilizing AI algorithms to measure HDA and cardiovascular risk factors, outcomes, or mortality were included. Data were pooled using random- and fixed-effects models for meta-analysis. Hypertension and diabetes mellitus emerged as the most prevalent factors contributing to higher HDA, while cardiac diseases including myocardial infarction and heart failure demonstrated the most significant impact. Pooled analysis revealed a significant association between elevated HDA and increased risks of all-cause mortality (hazard ratio [HR] 1.62, 95% confidence interval [CI] 1.49-1.77) and cardiovascular mortality (HR 2.12, 95% CI 1.71-2.63). HDA could enhance existing risk models and play a critical role in primary healthcare prevention.

Association of Cardiovascular Risk Factors With Major and Minor Electrocardiographic Abnormalities: A Report From the Cross-Sectional Phase of Tehran Cohort Study

Background and Aims

In the current study, we aimed to identify the association between major and minor electrocardiographic abnormalities and cardiovascular risk factors.

Methods

We used the Tehran cohort study baseline data, an ongoing multidisciplinary, longitudinal study designed to identify cardiovascular disease risk factors in the adult population of Tehran. The electrocardiograms (ECGs) of 7630 Iranian adults aged 35 years and above were analyzed. ECG abnormalities were categorized into major or minor groups based on their clinical importance. Results were obtained by multivariable logistic regression and are expressed as odds ratios (ORs).

Results

A total of 756 (9.9%) participants had major ECG abnormalities, while minor abnormalities were detected in 2526 (33.1%). Males comprised 45.8% of the total population, and 41.8% of them had minor abnormalities. Individuals with older age, diabetes (OR = 1.35; 95% CI: 1.11-1.64), and hypertension (OR = 2.21; 95% CI: 1.82-2.68) had an increased risk of major ECG abnormalities. In contrast, intermediate (OR = 0.69; 95% CI: 0.57-0.84) and high physical activity levels (OR = 0.66; 95% CI: 0.51-0.86) were associated with a lower prevalence of major abnormalities. Male sex, older age, hypertension, and current smoking were also associated with an increased prevalence of ECG abnormalities combined (major or minor).

Conclusion

Major and minor ECG abnormalities are linked with important cardiovascular risk factors such as diabetes and hypertension. Since these abnormalities have been associated with poor outcomes, screening patients with cardiovascular risk factors with an ECG may distinguish high-risk individuals who require appropriate care and follow-up.

Prediction of major adverse cardiovascular events following acute myocardial infarction using electrocardiogram DETERMINE score

BACKGROUND

Acute myocardial infarction (AMI) remains a major cause of mortality and morbidity globally, with a high incidence of major adverse cardiovascular events (MACE) post-primary percutaneous coronary intervention (PPCI). The DETERMINE score, derived from electrocardiographic (ECG) markers, has shown promise as a predictor of adverse outcomes, but its clinical utility requires further validation.

OBJECTIVE

To evaluate the predictive value of the DETERMINE score for MACE and provide early clinical warnings for high-risk patients.

METHODS

This bidirectional cohort study included AMI patients from the Second Affiliated Hospital of Anhui Medical University between 2019 and 2023. The training cohort comprised 545 patients between January 2019 and January 2023, while the validation cohort consisted of 122 patients between February 2023 and July 2023. The primary endpoint was MACE within one-year post-PPCI. The relationship between the DETERMINE score and MACE was analyzed using Cox regression, trend tests, and restricted cubic splines to assess linear and nonlinear associations. Patients were stratified into risk groups based on tertiles or optimal cutoffs, and Kaplan-Meier survival curves compared MACE incidence across groups. Predictive accuracy was evaluated through time-dependent C-index, ROC curves, decision curve analysis, and calibration, and compared to other prognostic scores, including the Selvester, GRACE, and SYNTAX scores, as well as left ventricular ejection fraction (LVEF). Subgroup analyses by sex, age, and culprit artery involvement were also conducted.

RESULTS

Cox multivariate regression indicated that the DETERMINE score was an independent risk factor for MACE (HR = 1.56, 95% CI 1.38-1.75, P < 0.001). Trend test and RCS showed a positive correlation and non-linear relationship between the DETERMINE score and MACE (P-trend < 0.001, P-overall < 0.001, P-nonlinear: 0.003). Kaplan-Meier survival analysis revealed that, in both the training and validation datasets, groups with a higher DETERMINE score showed a higher cumulative risk of MACE. The DETERMINE score outperformed traditional prognostic scores (Selvester, GRACE, SYNTAX) in terms of predictive accuracy, with an AUROC of 0.840 at 12 months in the training cohort. The score also provided a substantial clinical net benefit, particularly over longer follow-up periods. Subgroup analyses confirmed its predictive power across different demographics and clinical presentations.

CONCLUSION

The DETERMINE score has outstanding predictive power for MACE post-PPCI, which can guide the early identification of high-risk patients with poor prognosis of AMI in clinical practice.

Association of major and minor ECG abnormalities with traditional cardiovascular risk factors in the general population: a large scale study

Cardiovascular disease (CVD) can be determined and quantified using the electrocardiogram (ECG) analysis. Identification of the risk factors associated with ECG abnormalities may advise prevention approaches to decrease CVD burden. In this study we aimed to investigate the association between CVD risk factors and minor and major ECG abnormalities in a general Iranian adult population. This study was conducted in 2010 and covered a population of 9035 males and females aged 35 to 65 years recruiting from the phase I of Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) cohort study. The participants were drawn by a stratified cluster random sampling technique. The Bivariate and multinomial logistic regression analysis were conducted considering gender stratification to explore the association of ECG abnormalities with traditional cardiovascular risk factors. There was a significant association between minor and major ECG abnormalities and hypertension (HTN), type 2 diabetes (T2DM), smoking, and physical activity (p < 0.005). There was a significant trend, in both genders, for increasing major abnormalities as the number of CVD risk factors increased. But, only in women, the minor abnormalities increase in frequency as the number of CVD risk factors increased. The results of multinomial logistic regression showed that men with HTN [ARRR = 1.25, 95% CI 0.99, 1.57] and T2DM [ARRR = 1.31, 95% CI 0.99, 1.74] had the highest likelihood to have major abnormalities, although these are not statistically significant. For women, those with HTN had the highest likelihood to have major [ARRR = 1.36, 95% CI 1.13, 1.63] and minor [ARRR = 1.35, 95% CI 1.15, 1.58] abnormalities. Also, women aged > 60 years were more likely to have major [ARRR = 2.01, 95% CI 1.49, 2.74] and minor [ARRR = 1.59, 95% CI 1.20, 2.10] abnormalities compared to women aged < 45 years. Age and HTN were significantly associated with major and minor ECG abnormalities in women, and, on the other hand, HTN and T2DM were associated with major abnormalities in men. Taken together, these findings suggest that healthcare providers should advise preventive approaches to the asymptomatic adults with both major and minor electrocardiographic abnormalities that may predict cardiovascular risk.

Association of T-wave electrocardiogram changes and type 2 diabetes: a cross-sectional sub-analysis of the MASHAD cohort population using the Minnesota coding system

BACKGROUND

Type 2 Diabetes Mellitus (T2DM) has become a major health concern with an increasing prevalence and is now one of the leading attributable causes of death globally. T2DM and cardiovascular disease are strongly associated and T2DM is an important independent risk factor for ischemic heart disease. T-wave abnormalities (TWA) on electrocardiogram (ECG) can indicate several pathologies including ischemia. In this study, we aimed to investigate the association between T2DM and T-wave changes using the Minnesota coding system.

METHODS

A cross-sectional study was conducted on the MASHAD cohort study population. All participants of the cohort population were enrolled in the study. 12-lead ECG and Minnesota coding system (codes 5-1 to 5-4) were utilized for T-wave observation and interpretation. Regression models were used for the final evaluation with a level of significance being considered at p < 0.05.

RESULTS

A total of 9035 participants aged 35-65 years old were included in the study, of whom 1273 were diabetic. The prevalence of code 5-2, 5-3, major and minor TWA were significantly higher in diabetics (p < 0.05). However, following adjustment for age, gender, and hypertension, the presence of TWAs was not significantly associated with T2DM (p > 0.05). Hypertension, age, and body mass index were significantly associated with T2DM (p < 0.05).

CONCLUSIONS

Although some T-wave abnormalities were more frequent in diabetics, they were not statistically associated with the presence of T2DM in our study.

Genetic analyses of the electrocardiographic QT interval and its components identify additional loci and pathways

The QT interval is an electrocardiographic measure representing the sum of ventricular depolarization and repolarization, estimated by QRS duration and JT interval, respectively. QT interval abnormalities are associated with potentially fatal ventricular arrhythmia. Using genome-wide multi-ancestry analyses (>250,000 individuals) we identify 177, 156 and 121 independent loci for QT, JT and QRS, respectively, including a male-specific X-chromosome locus. Using gene-based rare-variant methods, we identify associations with Mendelian disease genes. Enrichments are observed in established pathways for QT and JT, and previously unreported genes indicated in insulin-receptor signalling and cardiac energy metabolism. In contrast for QRS, connective tissue components and processes for cell growth and extracellular matrix interactions are significantly enriched. We demonstrate polygenic risk score associations with atrial fibrillation, conduction disease and sudden cardiac death. Prioritization of druggable genes highlight potential therapeutic targets for arrhythmia. Together, these results substantially advance our understanding of the genetic architecture of ventricular depolarization and repolarization.

Red Blood Cell Distribution Width as Novel Biomarker in Cardiovascular Diseases: A Literature Review

Red blood cell distribution width (RDW) is a measure of the change in size of red blood cells and it is used in combination with other hematological parameters for the differential diagnosis of anemias. Recent evidence suggested that the change in RDW level may be a predictive biomarker of morbidity and mortality in cardiovascular diseases (CVDs). Cardiovascular diseases are the most common cause of death globally as compared to cancer and communicable diseases. Early diagnosis and prompt intervention of these diseases are very important to minimize their complications. Nowadays, the diagnosis of most cardiovascular diseases majorly depends on clinical judgment, electrocardiography and biochemical parameters. Red blood cell distribution width as a new predictive biomarker may play a pivotal role in assessing the severity and progression of CVDs. However, the underlying mechanisms for the association between RDW and CVDs are not clear. A deeper understanding of their association could help the physicians in more careful identification, early prevention, intervention, and treatment to prevent adverse cardiovascular events. This review aims to elaborate on the recent knowledge on the association between RDW and cardiovascular diseases and some possible pathophysiological mechanisms.

Electrocardiography in Hypertensive Patients without Cardiovascular Events: A Valuable Predictor Tool?

Background

Hypertension is an important risk factor of cardiovascular (CV) disease. An early diagnosis of target organ damage could prevent major CV events. Electrocardiography (ECG) is a valuable clinical technique, with wide availability and high specificity, used in evaluation of hypertensive patients. However, the use of ECG as a predictor tool is controversial given its low sensitivity. This study aims to characterise ECG features in a hypertensive population and identify ECG abnormalities that could predict CV events.

Methods

We studied 175 hypertensive patients without previous CV events during a follow-up mean of 4.0 ± 2.20 years. ECGs and pulse wave velocity were performed in all patients. Clinical characteristics and ECG abnormalities were evaluated and compared between the patients as they presented CV events.

Results

Considering the 175 patients (53.14% male), the median age was 62 years. Median systolic blood pressure was 140  mmHg and diastolic blood pressure was 78 mmHg. Median PWV was 9.8 m/s. Of the patients, 39.4% were diabetic, 78.3% had hyperlipidaemia, and 16.0% had smoking habits. ECG identified left ventricular (LV) hypertrophy in 29.71% of the patients, and a LV strain pattern was present in 9.7% of the patients. Twenty-nine patients (16.57%) had a CV event. Comparative analyses showed statistical significance for the presence of a LV strain pattern in patients with CV events (p=0.01). Univariate and multivariate analysis confirmed that a LV strain pattern was an independent predictor of CV event (HR 2.66, 95% IC 1.01-7.00). In the survival analysis, the Kaplan-Meier curve showed a worse prognosis for CV events in patients with a LV strain pattern (p=0.014).

Conclusion

ECG is a useful daily method to identify end-organ damage in hypertensive patients. In our study, we also observed that it may be a valuable tool for the prediction of CV events.

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.

Clinical values of resting electrocardiography in patients with known or suspected chronic coronary artery disease: a stress perfusion cardiac MRI study

Background

Electrocardiography (ECG) is an essential investigation in patients with chronic coronary artery disease (CAD). However, evidence regarding the diagnostic and prognostic value of ECG in this population is limited. Therefore, we sought to determine whether baseline ECG abnormalities were associated with myocardial ischemia and cardiac events in patients with known or suspected chronic CAD.

Methods

Consecutive patients with known (n = 146) or suspected chronic CAD (n = 349) referred for adenosine stress cardiac magnetic resonance (CMR) between 2011 and 2014 were enrolled. Resting ECGs were classified as major, minor, and no abnormalities. Predictors of myocardial ischemia on CMR and major adverse cardiac events (MACE) including cardiac death, nonfatal myocardial infarction, hospitalization for heart failure and late revascularization (> 180 days after CMR) were evaluated.

Results

Average age was 69 ± 11 years (51% men). One hundred and eighty-five patients (37.4%) had major and 154 (31.1%) had minor ECG abnormalities. In patients with suspected CAD, myocardial ischemia was presented in 83 patients (23.8%). Multivariable analysis demonstrated major ECG abnormality as the strongest predictor of myocardial ischemia (HR 2.51; 95% CI 1.44–4.36; p = 0.001). Adding ECG to clinical pretest probability models improved the prediction of myocardial ischemia in ROC analyses (p = 0.04). In the whole cohort (n = 495), 91 MACE occurred during the median follow-up period of 4.8 years. Multivariable analysis showed that diabetes mellites, history of heart failure, prior revascularization, left ventricular ejection fraction, ischemia, and major ECG abnormality were independent predictors of MACE.

Conclusion

Abnormal resting ECG is common in patients with known or suspected chronic CAD. ECG had important diagnostic and prognostic values in this population.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12872-021-02440-5.

De novo electrocardiographic abnormalities in persons living with HIV

Persons living with HIV (PLWH) may have increased incidence of cardiovascular events and longer QTc intervals than uninfected persons. We aimed to investigate the incidence and risk factors of de novo major electrocardiogram (ECG) abnormalities and QTc prolongation in well-treated PLWH. We included virologically suppressed PLWH without major ECG abnormalities, who attended the 2-year follow-up in the Copenhagen comorbidity in HIV infection (COCOMO) study. ECGs were categorized according to Minnesota Code Manual. We defined de novo major ECG abnormalities as new major Minnesota Code Manual abnormalities. Prolonged QTc was defined as QTc > 460 ms in females and QTc > 450 ms in males. Of 667 PLWH without major ECG abnormalities at baseline, 34 (5%) developed de novo major ECG abnormalities after a median of 2.3 years. After adjustment, age (RR: 1.57 [1.08-2.28] per decade older), being underweight (RR: 5.79 [1.70-19.71]), current smoking (RR: 2.34 [1.06-5.16]), diabetes (RR: 3.89 [1.72-8.80]) and protease inhibitor use (RR: 2.45 [1.27-4.74) were associated with higher risk of getting de novo major ECG abnormalities. Of PLWH without prolonged QTc at baseline, only 11 (1.6%) participants developed de novo prolonged QTc. Five percent of well-treated PLWH acquired de novo major ECG abnormalities and protease inhibitor use was associated with more than twice the risk of de novo major ECG abnormalities. De novo prolonged QTc was rare and did not seem to constitute a problem in well-treated PLWH.

Electrocardiographic Findings and In-Hospital Mortality of COVID-19 Patients; a Retrospective Cohort Study

Background:

Although current evidence points to the possible prognostic value of electrocardiographic (ECG) findings for in-hospital mortality of COVID-19 patients, most of these studies have been performed on a small sample size. In this study, our aim was to investigate the ECG changes as prognostic indicators of in-hospital mortality.

Methods:

In a retrospective cohort study, the findings of the first and the second ECGs of COVID-19 patients were extracted and changes in the ECGs were examined. Any abnormal finding in the second ECG that wasn’t present in the initial ECG at the time of admission was defined as an ECG change. ECGs were interpreted by a cardiologist and the prognostic value of abnormal ECG findings for in-hospital mortality of COVID-19 patients was evaluated using multivariate analysis and the report of the relative risk (RR).

Results:

Data of the ECGs recorded at the time of admission were extracted from the files of 893 patients; likewise, the second ECGs could be extracted from the records of 328 patients who had an initial ECG. The presence of sinus tachycardia (RR = 2.342; p <0.001), supraventricular arrhythmia (RR = 1.688; p = 0.001), ventricular arrhythmia (RR = 1.854; p = 0.011), interventricular conduction delays (RR = 1.608; p = 0.009), and abnormal R wave progression (RR = 1.766; p = 0.001) at the time of admission were independent prognostic factors for in-hospital mortality. In the second ECG, sinus tachycardia (RR = 2.222; p <0.001), supraventricular arrhythmia (RR = 1.632; p <0.001), abnormal R wave progression (RR = 2.151; p = 0.009), and abnormal T wave (RR = 1.590; p = 0.001) were also independent prognostic factors of in-hospital mortality. Moreover, by comparing the first and the second ECGs, it was found that the incidence of supraventricular arrhythmia (RR = 1.973; p = 0.005) and ST segment elevation/depression (RR = 2.296; p <0.001) during hospitalization (ECG novel changes) are two independent prognostic factors of in-hospital mortality in COVID-19 patients.

Conclusion:

Due to the fact that using electrocardiographic data is easy and accessible and it is easy to continuously monitor patients with this tool, ECGs can be useful in identifying high-risk COVID-19 patients for mortality.

Association of T-wave abnormalities with major cardiovascular events in diabetes: the ACCORD trial

AIMS/HYPOTHESIS

T-wave abnormalities (TWA) are often found on ECG and signify abnormal ventricular repolarisation. While TWA have been shown to be associated with subclinical atherosclerosis, the relationship between TWA and hard cardiovascular endpoints is less clear and may differ in the presence of diabetes, so we sought to explore these associations in participants from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial.

METHODS

TWA were operationally defined as the presence of any Minnesota Codes 5-1 through 5-4 in any lead distribution. Multivariable Cox proportional hazards models were constructed to examine relationships between TWA and clinical cardiovascular events. Secondary analyses explored the risks conferred by major vs minor TWA, differential effects of TWA by anatomic localisation (anterolateral, inferior or anterior lead distributions), and differing associations in those with or without prevalent CVD.

RESULTS

Among 8176 eligible participants (mean 62.1 ± 6.3 SD years, 61.4% male), there were 3759 cardiovascular events, including 1430 deaths (473 of a cardiovascular aetiology), 474 heart failure events, 1452 major CHD events and 403 strokes. Participants with TWA had increased risks of all-cause mortality (HR 1.45 [95% CI 1.30, 1.62], p < 0.0001), cardiovascular mortality (HR 1.93 [1.59, 2.34], p = 0.0001), congestive heart failure (HR 2.04 [1.69, 2.48], p < 0.0001) and major CHD (HR 1.40 [1.26, 1.57], p < 0.0001), but no increased risk of stroke (HR 0.99 [0.80, 1.23], p = 0.95). Major TWA conferred a higher risk than minor TWA. When TWA were added to the UK Prospective Diabetes Study risk engine, there was improved discrimination for incident CHD events, but only for those with prevalent CVD (area under the receiver operating characteristic curve 0.5744 and 0.6030 with p = 0.0067). Adding TWA to the risk engine yielded improvements in reclassification that were of greater magnitude in those with prevalent CVD (net reclassification improvement [NRI] 0.24 [95% CI 0.16, 0.32] in those with prevalent CVD, NRI 0.14 [95% CI 0.07, 0.22] in those without prevalent CVD).

CONCLUSIONS/INTERPRETATION

The presence and magnitude of TWA are associated with increased risk of clinical cardiovascular events and mortality in individuals with diabetes and may have value in refining risk, particularly in those with prevalent CVD. Graphical abstract.