Digitized Electrocardiography Measurements Support the Biological Plausibility of the Pathological Significance of ST Segments in Athletes.

OBJECTIVE: ST segment deviations around the isoelectric line are common findings in manifest cardiovascular disease. In athletes, ST elevation is common, while ST depression is considered rare. However, clinical studies in athletes have associated ST depression with myocardial fibrosis and fatty infiltration and ST elevation with pericarditis and myocarditis. This study aims to explore the association between resting ST segment deviations and resting heart rate, an indicator of training and autonomic tone and electrocardiography (ECG) markers of exercise training effect and cardiovascular health R and T wave amplitude. DESIGN: Retrospective analysis of digitized ECG data. SETTING: Institutional setting. PARTICIPANTS: Seven thousand eight hundred thirty-six (male athletes = 4592, female athletes = 3244) healthy asymptomatic athletes (14-35 years). MAIN OUTCOME MEASURES: A series of correlations and regressions were conducted between ST depression (<0.0 µV) and ST elevation (>0.0 µV), on R and T wave amplitudes, and heart rate in leads V2, V5, and aVF. RESULTS: Positive correlations between ST elevation and R and T wave (S wave in V2) amplitudes and leads V5, V2, and aVF in male and female athletes (range of r = 0.1-0.54). In addition, there was a negative correlation between ST elevation and HR for male and female athletes. Finally, there was a negative correlation between ST depression and R wave and HR for male and female athletes in V5 ( P < 0.01). CONCLUSIONS: In athletes, ST segment elevation is correlated with R and T wave amplitudes and negatively correlated with HR. In addition, ST segment elevation is correlated with low heart rate, consistent with its higher prevalence in athletes. ST segment depression is not influenced by HR but is negatively associated with R and T wave amplitudes.

QT Corrections for Long QT Risk Assessment: Implications for the Preparticipation Examination.

BACKGROUND: Because sudden cardiac death (SCD) in the young mainly occurs in individuals with structurally normal hearts, improved screening techniques for detecting inherited arrhythmic diseases are needed. The QT interval is an important screening measurement; however, the criteria for detecting an abnormal QT interval are based on Bazett formula and older populations. OBJECTIVE: To define the normal upper limits for QT interval from the electrocardiograms (ECGs) of healthy young individuals, compare the major correction formula and propose new QT interval thresholds for detecting those at risk of SCD. METHODS: Young active individuals underwent ECGs as part of routine preparticipation physical examinations for competitive sports or community screening. This was a nonfunded study using de-identified data with no follow-up. RESULTS: There were 31 558 subjects: 2174 grade school (7%), 18 547 high school (59%), and 10 822 college (34%). Mean age was 17 (12-35 years), 45% were female, 67% white, and 11% of African descent. Bazett performed least favorably for removing the effect of heart rate (HR), whereas Fridericia performed the best. Fridericia correction also closely fit the raw data best (R of 0.65), and at percentile values applicable to screening. The recommended risk cut points using Bazetts correction identified less than half of the athletes in the 99th or 99.5th percentiles of the uncorrected QT by HR range. Use of Fridericia correction increased capture rates by over 50%. CONCLUSION: Our results support the application of the Fridericia-corrected threshold of 460 for men and 470 milliseconds for women (and 485 milliseconds for marked prolongation) rather than Bazett correction for the preparticipation examination.

International recommendations for electrocardiographic interpretation in athletes.

Sudden cardiac death (SCD) is the leading cause of mortality in athletes during sport. A variety of mostly hereditary, structural, or electrical cardiac disorders are associated with SCD in young athletes, the majority of which can be identified or suggested by abnormalities on a resting 12-lead electrocardiogram (ECG). Whether used for diagnostic or screening purposes, physicians responsible for the cardiovascular care of athletes should be knowledgeable and competent in ECG interpretation in athletes. However, in most countries a shortage of physician expertise limits wider application of the ECG in the care of the athlete. A critical need exists for physician education in modern ECG interpretation that distinguishes normal physiological adaptations in athletes from distinctly abnormal findings suggestive of underlying pathology. Since the original 2010 European Society of Cardiology recommendations for ECG interpretation in athletes, ECG standards have evolved quickly over the last decade; pushed by a growing body of scientific data that both tests proposed criteria sets and establishes new evidence to guide refinements. On 26-27 February 2015, an international group of experts in sports cardiology, inherited cardiac disease, and sports medicine convened in Seattle, Washington, to update contemporary standards for ECG interpretation in athletes. The objective of the meeting was to define and revise ECG interpretation standards based on new and emerging research and to develop a clear guide to the proper evaluation of ECG abnormalities in athletes. This statement represents an international consensus for ECG interpretation in athletes and provides expert opinion-based recommendations linking specific ECG abnormalities and the secondary evaluation for conditions associated with SCD.

International criteria for electrocardiographic interpretation in athletes: Consensus statement.

Sudden cardiac death (SCD) is the leading cause of mortality in athletes during sport. A variety of mostly hereditary, structural or electrical cardiac disorders are associated with SCD in young athletes, the majority of which can be identified or suggested by abnormalities on a resting 12-lead electrocardiogram (ECG). Whether used for diagnostic or screening purposes, physicians responsible for the cardiovascular care of athletes should be knowledgeable and competent in ECG interpretation in athletes. However, in most countries a shortage of physician expertise limits wider application of the ECG in the care of the athlete. A critical need exists for physician education in modern ECG interpretation that distinguishes normal physiological adaptations in athletes from distinctly abnormal findings suggestive of underlying pathology. Since the original 2010 European Society of Cardiology recommendations for ECG interpretation in athletes, ECG standards have evolved quickly, advanced by a growing body of scientific data and investigations that both examine proposed criteria sets and establish new evidence to guide refinements. On 26-27 February 2015, an international group of experts in sports cardiology, inherited cardiac disease, and sports medicine convened in Seattle, Washington (USA), to update contemporary standards for ECG interpretation in athletes. The objective of the meeting was to define and revise ECG interpretation standards based on new and emerging research and to develop a clear guide to the proper evaluation of ECG abnormalities in athletes. This statement represents an international consensus for ECG interpretation in athletes and provides expert opinion-based recommendations linking specific ECG abnormalities and the secondary evaluation for conditions associated with SCD.

Long-term prognosis of early repolarization with J-wave and QRS slur patterns on the resting electrocardiogram: a cohort study.

BACKGROUND: The prognostic value of early repolarization with J waves and QRS slurs remains controversial. Although these findings are more prevalent in patients with idiopathic ventricular fibrillation, their ability to predict cardiovascular death has varied across studies. OBJECTIVE: To test the hypothesis that J waves and QRS slurs on electrocardiograms (ECGs) are associated with increased risk for cardiovascular death. DESIGN: Retrospective cohort. SETTING: Veterans Affairs Palo Alto Health Care System. PATIENTS: Veterans younger than 56 years who had resting 12-lead electrocardiography, 90.5% of whom were men. MEASUREMENTS: Electrocardiograms were manually measured and visually coded using criteria of 0.1 mV or greater in at least 2 contiguous leads. J waves were measured at the peak of an upward deflection or notch at the end of QRS, and QRS slurs were measured at the top of conduction delay on the QRS downstroke. Absolute risk differences at 10 years were calculated to study the associations between J waves or QRS slurs and the primary outcome of cardiovascular death. RESULTS: Over a median follow-up of 17.5 years, 859 cardiovascular deaths occurred. Of 20 661 ECGs, 4219 (20%) had J waves or QRS slurs in the inferior and/or lateral territories; of these, 3318 (78.6%) had J waves or QRS slurs in inferior leads and 1701 (40.3%) in lateral leads. The upper bound of differences in risk for cardiovascular death from any of the J-wave or QRS slur patterns suggests that an increased risk can be safely ruled out (inferior, -0.77% [95% CI, -1.27% to -0.27%]; lateral, -1.07% [CI, -1.72% to -0.43%]). LIMITATION: The study consisted of predominantly men, and deaths could be classified as cardiovascular but not arrhythmic. CONCLUSION: J waves and QRS slurs did not exhibit a clinically meaningful increased risk for cardiovascular death in long-term follow-up. PRIMARY FUNDING SOURCE: None.

Limitations of Current AHA Guidelines and Proposal of New Guidelines for the Preparticipation Examination of Athletes.

OBJECTIVE: To examine the prevalence of athletes who screen positive with the preparticipation examination guidelines from the American Heart Association, the AHA 12-elements, in combination with 3 screening electrocardiogram (ECG) criteria. DESIGN: Observational cross-sectional study. SETTING: Stanford University Sports Medicine Clinic. PARTICIPANTS: Total of 1596 participants, including 297 (167 male; mean age, 16.2 years) high school athletes, 1016 (541 male; mean age, 18.8 years) collegiate athletes, and 283 (mean age, 26.3 years) male professional athletes. MAIN OUTCOME MEASURES: Athletes were screened using the 8 personal and family history questions from the AHA 12-elements. Electrocardiograms were obtained for all participants and interpreted using Seattle criteria, Stanford criteria, and European Society of Cardiology (ESC) recommendations. RESULTS: Approximately one-quarter of all athletes (23.8%) had at least 1 positive response to the AHA personal and family history elements. High school and college athletes had similar rates of having at least 1 positive response (25.9% vs 27.4%), whereas professional athletes had a significantly lower rate of having at least 1 positive response (8.8%, P < 0.05). Females reported more episodes of unexplained syncope (11.4% vs 7.5%, P = 0.017) and excessive exertional dyspnea with exercise (11.1% vs 6.1%, P = 0.001) than males. High school athletes had more positive responses to the family history elements when compared with college athletes (P < 0.05). The percentage of athletes who had an abnormal ECG varied between Seattle criteria (6.0%), Stanford criteria (8.8%), and ESC recommendations (26.8%). CONCLUSIONS: Many athletes screen positive under current screening recommendations, and ECG results vary widely by interpretation criteria. CLINICAL RELEVANCE: In a patient population without any adverse cardiovascular events, the currently recommended AHA 12-elements have an unacceptably high rate of false positives. Newer screening guidelines are needed, with fewer false positives and evidence-based updates.

Guide to the Female Student Athlete ECG: A Comprehensive Study of 3466 Young, Racially Diverse Athletes.

OBJECTIVES: The 12-lead electrocardiogram (ECG) is used in the preparticipation screening examination for athletes. Despite known differences in ECG findings by sex, only QTc prolongation is given a sex-specific threshold. We hypothesize that our large dataset-with diversity in age, race, and sport participation-can be utilized to improve ECG screening in female student athletes. METHODS: Computerized 12-lead ECGs were recorded and analyzed in female athletes who underwent preparticipation screening examination between June 2010 and September 2021. The quantitative, empirical 2017 international criteria for electrocardiographic interpretation were compared with either the 99th percentile in our cohort or the percentile that corresponded to the known disease prevalence. RESULTS: Of 3466 female athletes with ECGs as part of preparticipation screening examination, the 2017 international criteria classified 2.1% of athletes with at least one ECG abnormality requiring cardiological evaluation. Rates were similar across age, race/ethnicity, and sporting discipline. Using ranges based on our population, 2.7% of athletes would require additional workup. Surprisingly, ST depression up to 0.03 mV was a normal finding in this cohort. If RS voltage extremes were considered findings requiring follow-up, an additional 9.6% of the athlete population would be flagged using current definitions. This number decreases to 2.7% if using the 99th percentile in this cohort. CONCLUSION: These results highlight a difference in the reported prevalence of ECG abnormalities when comparing empirically derived thresholds to statistically derived ranges. Consideration of new metrics specific to the female athlete population has the potential to further refine athlete ECG screening.

Premature ventricular contractions (PVCs) in young athletes.

There is a growing body of literature focusing on the morphology, management, and outcomes of PVCs in athletes. This review summarizes this literature and establishes recommendations on management, treatment, and indications for specialist referral in this patient population. The sports medicine physician's responses and recommendation should be made in conjunction with the athletes wishes. Medications or ablations are not always necessary in all athletes if they are followed with regular evaluations.

A novel method for patient-specific QTc--modeling QT-RR hysteresis.

BACKGROUND: Cardiac repolarization adaptation to cycle length change is patient dependent and results in complex QT-RR hysteresis. We hypothesize that accurate patient-specific QT-RR curves and rate corrected QT values (QTc) can be derived through patient-specific modeling of hysteresis. METHOD AND RESULTS: Model development was supported by QT-RR observations from 1959 treadmill tests, allowing extensive exploration of the influences of autonomic function on QT adaptation to rate changes. The methodology quantifies and then removes patient-specific repolarization adaptation rates. The estimated average 95% QT confidence limit was approximately 1 msec for the studied population. The model was validated by comparing QT-RR curves derived from a submaximal exercise protocol with rapid exercise and recovery phases, characterized by high hysteresis, with QT-RR values derived from an incremental stepped protocol that held heart rate constant for 5 minutes at each stage of exercise and recovery. CONCLUSIONS: The underlying physiologic changes affecting QT dynamics during the transitions from rest to exercise to recovery are quite complex. Nevertheless, a simple patient-specific model, comprising only three parameters and based solely on the preceding history of RR intervals and trend, is sufficient to accurately model QT hysteresis over an entire exercise test for a diverse population. A brief recording of a resting ECG, combined with a short period of submaximal exercise and recovery, provides sufficient information to derive an accurate patient-specific QT-RR curve, eliminating QTc bias inherent in population-based correction formulas.

Cost-effectiveness of preparticipation screening for prevention of sudden cardiac death in young athletes.

BACKGROUND: Inclusion of 12-lead electrocardiography (ECG) in preparticipation screening of young athletes is controversial because of concerns about cost-effectiveness. OBJECTIVE: To evaluate the cost-effectiveness of ECG plus cardiovascular-focused history and physical examination compared with cardiovascular-focused history and physical examination alone for preparticipation screening. DESIGN: Decision-analysis, cost-effectiveness model. DATA SOURCES: Published epidemiologic and preparticipation screening data, vital statistics, and other publicly available data. TARGET POPULATION: Competitive athletes in high school and college aged 14 to 22 years. TIME HORIZON: Lifetime. PERSPECTIVE: Societal. INTERVENTION: Nonparticipation in competitive athletic activity and disease-specific treatment for identified athletes with heart disease. OUTCOME MEASURE: Incremental health care cost per life-year gained. RESULTS OF BASE-CASE ANALYSIS: Addition of ECG to preparticipation screening saves 2.06 life-years per 1000 athletes at an incremental total cost of $89 per athlete and yields a cost-effectiveness ratio of $42 900 per life-year saved (95% CI, $21 200 to $71 300 per life-year saved) compared with cardiovascular-focused history and physical examination alone. Compared with no screening, ECG plus cardiovascular-focused history and physical examination saves 2.6 life-years per 1000 athletes screened and costs $199 per athlete, yielding a cost-effectiveness ratio of $76 100 per life-year saved ($62 400 to $130 000). RESULTS OF SENSITIVITY ANALYSIS: Results are sensitive to the relative risk reduction associated with nonparticipation and the cost of initial screening. LIMITATIONS: Effectiveness data are derived from 1 major European study. Patterns of causes of sudden death may vary among countries. CONCLUSION: Screening young athletes with 12-lead ECG plus cardiovascular-focused history and physical examination may be cost-effective. PRIMARY FUNDING SOURCE: Stanford Cardiovascular Institute and the Breetwor Foundation.

Modest Gains After an 8-Week Exercise Program Correlate With Reductions in Non-traditional Markers of Cardiovascular Risk.

Background: Although engaging in physical exercise has been shown to reduce the incidence of cardiovascular events, the molecular mechanisms by which exercise mediates these benefits remain unclear. Based on epidemiological evidence, reductions in traditional risk factors only accounts for 50% of the protective effects of exercise, leaving the remaining mechanisms unexplained. The objective of this study was to determine whether engaging in a regular exercise program in a real world clinical setting mediates cardiovascular protection via modulation of non-traditional risk factors, such as those involved in coagulation, inflammation and metabolic regulation. Methods and Results: We performed a prospective, cohort study in 52 sedentary patients with cardiovascular disease or cardiovascular risk factors at two tertiary medical centers between January 1, 2016 and December 31, 2019. Prior to and at the completion of an 8-week exercise program, we collected information on traditional cardiovascular risk factors, exercise capacity, and physical activity and performed plasma analysis to measure levels of fibrinolytic, inflammatory and metabolic biomarkers to assess changes in non-traditional cardiovascular risk factors. The median weight change, improvement in physical fitness, and change in physical activity for the entire cohort were: -4.6 pounds (IQR: +2 pounds, -11.8 pounds), 0.37 METs (IQR: -0.076 METs, 1.06 METs), and 252.7 kcals/week (IQR: -119, 921.2 kcals/week). In addition to improvement in blood pressure and cholesterol, patients who lost at least 5 pounds, expended at least 1,000 additional kcals/week, and/or achieved ≥0.5 MET increase in fitness had a significant reduction in plasminogen activator inhibitor-1 [9.07 ng/mL (95% CI: 2.78-15.35 ng/mL); P = 0.026], platelet derived growth factor beta [376.077 pg/mL (95% CI: 44.69-707.46 pg/mL); P = 0.026); and angiopoietin-1 [(1104.11 pg/mL (95% CI: 2.92-2205.30 pg/mL); P = 0.049)]. Conclusion: Modest improvements in physical fitness, physical activity, and/or weight loss through a short-term exercise program was associated with decreased plasma levels of plasminogen activator inhibitor, platelet derived growth factor beta, and angiopoietin, which have been associated with impaired fibrinolysis and inflammation.

Characterizing differences in mortality at the low end of the fitness spectrum in individuals with cardiovascular disease.

BACKGROUND: A graded but nonlinear relationship exists between fitness and mortality, with the greatest mortality differences occurring between the least-fit (first, Q1) and the next-least-fit (second, Q2) quintiles of fitness. The purpose of this study was to compare clinical characteristics, exercise test responses, and physical activity (PA) patterns in Q1 versus Q2 in patients with cardiovascular disease (CVD). DESIGN: Observational retrospective study. METHODS: A total of 5101 patients with a history of CVD underwent clinical treadmill testing and were followed up for 9.1+/-5.5 years. Patients were classified into quintiles of exercise capacity measured in metabolic equivalents. Clinical characteristics, treadmill test results, and recreational PA patterns were compared between Q1 (n = 923) and Q2 (n = 929). RESULTS: Q1 had a nearly two-fold increase in age-adjusted relative risk of cardiovascular mortality compared with Q2 (hazard ratio: 3.79 vs. 2.04, P<0.05; reference: fittest quintile). Q1 patients were older, had more extensive use of medications, and were more likely to have a history of typical angina (35 vs. 28%), myocardial infarction (30 vs. 24%), chronic heart failure (25 vs. 14%), claudication (15 vs. 9%) and stroke (9 vs. 6%) compared with Q2 (all comparisons: P<0.05). Recent and lifetime recreational PA was not different between the two groups. CONCLUSION: Greater severity of disease in the least-fit versus the next-least-fit quintile likely contributes to but cannot fully explain marked differences in mortality rates in CVD patients. To achieve potential survival benefits, our results suggest that unfit CVD patients should engage in exercise programs of sufficient volume and intensity to improve fitness.

Rest premature ventricular contractions on routine ECG and prognosis in heart failure patients.

BACKGROUND: Premature ventricular contractions (PVC) at rest are frequently seen in heart failure (HF) patients but conflicting data exist regarding their importance for cardiovascular (CV) mortality. This study aims to evaluate the prognostic value of rest PVCs on an electrocardiogram (ECG) in patients with a history of clinical HF. METHODS AND RESULTS: We considered 352 patients (64 + or - 11 years; 7 females) with a history of clinical HF undergoing treadmill testing for clinical reasons at the Veterans Affairs Palo Alto Health Care System (VAPAHCS) (1987-2007). Patients with rest PVCs were defined as having > or = 1 PVC on the ECG prior to testing (n = 29; 8%). During a median follow-up period of 6.2 years, there were 178 deaths of which 76 (42.6%) were due to CV causes. At baseline, compared to patients without rest PVCs, those with rest PVCs had a lower ejection fraction (EF) (30% vs 45%) and the prevalence of EF < or = 35% was higher (75% vs 41%). They were more likely to have smoked (76% vs 55%).The all-cause and CV mortality rates were significantly higher in the rest PVCs group (72% vs 49%, P = 0.01 and 45% vs 20%, P = 0.002; respectively). After adjusting for age, beta-blocker use, rest ECG findings, resting heart rate (HR), EF, maximal systolic blood pressure, peak HR, and exercise capacity, rest PVC was associated with a 5.5-fold increased risk of CV mortality (P = 0.004). Considering the presence of PVCs during exercise and/or recovery did not affect our results. CONCLUSION: The presence of PVC on an ECG is a powerful predictor of CV mortality even after adjusting for confounding factors.

Does size matter? Clinical applications of scaling cardiac size and function for body size.

Extensive evidence is available that cardiovascular structure and function, along with other biological properties that span the range of organism size and speciation, scale with body size. Although appreciation of such factors is commonplace in pediatrics, cardiovascular measurements in the adult population, with similarly wide variation in body size, are rarely corrected for body size. In this review, we describe the critical role of body size measurements in cardiovascular medicine. Using examples, we illustrate the confounding effects of body size. Current cardiovascular scaling practices are reviewed, as are limitations and alternative relationships between body and cardiovascular dimensions. The experimental evidence, theoretical basis, and clinical application of scaling of various functional parameters are presented. Appropriately scaled parameters aid diagnostic and therapeutic decision making in specific disease states such as hypertrophic cardiomyopathy and congestive heart failure. Large-scale studies in clinical populations are needed to define normative relationships for this purpose. Lack of appropriate consideration of body size in the evaluation of cardiovascular structure and function may adversely affect recognition and treatment of cardiovascular disease states in the adult patient.

Electrocardiographic predictors of atrial fibrillation.

BACKGROUND: Atrial fibrillation (AF) is the most prevalent arrhythmia in the United States and accounts for more than 750,000 strokes per year. Noninvasive predictors of AF may help identify patients at risk of developing AF. Our objective was to identify the electrocardiographic characteristics associated with onset of AF. METHODS: This was a retrospective cohort analysis of 42,751 patients with electrocardiograms (ECGs) ordered by physician's discretion and analyzed using a computerized system. The population was followed for detection of AF on subsequent ECGs. Cox proportional hazard regression analysis was performed to test the association between these ECG characteristics and development of AF. RESULTS: For a mean follow-up of 5.3 years, 1,050 (2.4%) patients were found to have AF on subsequent ECG recordings. Several ECG characteristics, such as P-wave dispersion (the difference between the widest and narrowest P waves), premature atrial contractions, and an abnormal P axis, were predictive of AF with hazard ratio of approximately 2 after correcting for age and sex. P-wave index, the SD of P-wave duration across all leads, was one of the strongest predictors of AF with a concordance index of 0.62 and a hazard ratio of 2.7 (95% CI 2.1-3.3) for a P-wave index >35. These were among the several independently predictive markers identified on multivariate analysis. CONCLUSIONS: Several ECG markers are independently predictive of future onset of AF. The P index, a measurement of disorganized atrial depolarization, is one of the strongest predictors of AF. The ECG contains valuable prognostic information that can identify patients at risk of AF.

Statin use and ventricular arrhythmias during clinical treadmill testing.

BACKGROUND: Premature ventricular complexes (PVCs) during exercise are associated with adverse prognosis, particularly in patients with intermediate treadmill test findings. Statin use reduces the incidence of resting ventricular arrhythmias in patients with coronary artery disease; however, the relationship between statin use and exercise-induced ventricular arrhythmias has not been investigated. METHODS AND RESULTS: We evaluated the association between statin use and PVCs in 1,847 heart-failure-free patients (mean age 58, 95% male) undergoing clinical exercise treadmill testing between 1997 and 2004 in the VA Palo Alto Health Care System. PVCs were quantified in beats per minute and frequent PVCs were defined as PVC rates greater than the median value (0.43 and 0.60 PVCs per minute for exercise and recovery, respectively). Propensity-adjusted logistic regression was used to evaluate the odds of developing PVCs during exercise and recovery periods associated with statin use. There were 431 subjects who developed frequent PVCs during exercise and 284 subjects had frequent recovery PVCs. After propensity score adjustment, subjects treated with statins (n = 145) had 42% lower odds of developing frequent PVCs during exercise (odds ratio [OR] 0.58, 95% confidence interval [CI] 0.37-0.93) and 44% lower odds of developing frequent PVCs during recovery (OR 0.56, 95% CI 0.30-0.94). These effects were not modified by age, prior coronary disease, hypercholesterolemia, exercise-induced angina, or exercise capacity. CONCLUSIONS: Statin use was associated with reduced odds of frequent PVCs during and after clinical exercise testing in a manner independent of associations with coronary disease or ischemia in our study population.

Added value of a resting ECG neural network that predicts cardiovascular mortality.

BACKGROUND: The resting 12-lead electrocardiogram (ECG) remains the most commonly used test in evaluating patients with suspected cardiovascular disease. Prognostic values of individual findings on the ECG have been reported but may be of limited use. METHODS: The characteristics of 45,855 ECGs ordered by physician's discretion were first recorded and analyzed using a computerized system. Ninety percent of these ECGs were used to train an artifical neural network (ANN) to predict cardiovascular mortality (CVM) based on 132 ECG and four demographic characteristics. The ANN generated a Resting ECG Neural Network (RENN) score that was then tested in the remaining ECGs. The RENN score was finally assessed in a cohort of 2189 patients who underwent exercise treadmill testing and were followed for CVM. RESULTS: The RENN score was able to better predict CVM compared to individual ECG markers or a traditional Cox regression model in the testing cohort. Over a mean of 8.6 years, there were 156 cardiovascular deaths in the treadmill cohort. Among the patients who were classified as intermediate risk by Duke Treadmill Scoring (DTS), the third tertile of the RENN score demonstrated an adjusted Cox hazard ratio of 5.4 (95% CI 2.0-15.2) compared to the first RENN tertile. The 10-year CVM was 2.8%, 8.6% and 22% in the first, second and third RENN tertiles, respectively. CONCLUSIONS: An ANN that uses the resting ECG and demographic variables to predict CVM was created. The RENN score can further risk stratify patients deemed at moderate risk on exercise treadmill testing.