RESUMEN

AIMS: To leverage deep learning on the resting 12-lead electrocardiogram (ECG) to estimate peak oxygen consumption (V˙O2peak) without cardiopulmonary exercise testing (CPET). METHODS AND RESULTS: V ˙ O 2 peak estimation models were developed in 1891 individuals undergoing CPET at Massachusetts General Hospital (age 45 ± 19 years, 38% female) and validated in a separate test set (MGH Test, n = 448) and external sample (BWH Test, n = 1076). Three penalized linear models were compared: (i) age, sex, and body mass index ('Basic'), (ii) Basic plus standard ECG measurements ('Basic + ECG Parameters'), and (iii) basic plus 320 deep learning-derived ECG variables instead of ECG measurements ('Deep ECG-V˙O2'). Associations between estimated V˙O2peak and incident disease were assessed using proportional hazards models within 84 718 primary care patients without CPET. Inference ECGs preceded CPET by 7 days (median, interquartile range 27-0 days). Among models, Deep ECG-V˙O2 was most accurate in MGH Test [r = 0.845, 95% confidence interval (CI) 0.817-0.870; mean absolute error (MAE) 5.84, 95% CI 5.39-6.29] and BWH Test (r = 0.552, 95% CI 0.509-0.592, MAE 6.49, 95% CI 6.21-6.67). Deep ECG-V˙O2 also outperformed the Wasserman, Jones, and FRIEND reference equations (P < 0.01 for comparisons of correlation). Performance was higher in BWH Test when individuals with heart failure (HF) were excluded (r = 0.628, 95% CI 0.567-0.682; MAE 5.97, 95% CI 5.57-6.37). Deep ECG-V˙O2 estimated V˙O2peak <14 mL/kg/min was associated with increased risks of incident atrial fibrillation [hazard ratio 1.36 (95% CI 1.21-1.54)], myocardial infarction [1.21 (1.02-1.45)], HF [1.67 (1.49-1.88)], and death [1.84 (1.68-2.03)]. CONCLUSION: Deep learning-enabled analysis of the resting 12-lead ECG can estimate exercise capacity (V˙O2peak) at scale to enable efficient cardiovascular risk stratification.

---

Researchers here present data describing a method of estimating exercise capacity from the resting electrocardiogram. Electrocardiogram estimation of exercise capacity was accurate and was found to predict the onset of the wide range of cardiovascular diseases including heart attacks, heart failure, arrhythmia, and death.This approach offers the ability to estimate exercise capacity without dedicated exercise testing and may enable efficient risk stratification of cardiac patients at scale.

Asunto(s)

Electrocardiografía , Insuficiencia Cardíaca , Humanos , Femenino , Adulto , Persona de Mediana Edad , Masculino , Pronóstico , Prueba de Esfuerzo/métodos , Consumo de Oxígeno

RESUMEN

OBJECTIVE: This study aimed to understand the long-term transition of exercise tolerance in patients on phase III cardiac rehabilitation (CR) and clarify the characteristics of patients with a high risk of declined exercise tolerance during the first emergency declaration. METHODS: Patients who participated in phase III outpatient CR before the first emergency declaration and those who performed cardiopulmonary exercise testing were at ≥2-time points: before and at 3 or 12 months post-emergency declaration. Exercise tolerance transition at 3-time points was analyzed, and whether different social background factors affected the peak oxygen uptake (V̇O2) transition method remains to be examined. RESULTS: A total of 101 (median age 74.0 years, 69% men), and both peak V̇O2 and anaerobic threshold (AT) significantly declined from pre-declaration to 3 months post-declaration but recovered to levels likely similar from pre-declaration at 12 months (peak V̇O2: from 17.3 to 16.7 to 18.7 mL/min/kg; AT: from 11.8 to 11.2 to 11.6 mL/min/kg). Further, patients with multiple comorbidities at pre-declaration had a significantly lower peak V̇O2 at 3 months (-1.0 mL/min/kg, p = 0.025) and it remained significantly low in those with a slower gait speed at 12 months after lifting the emergency declaration (-2.5 mL/min/kg, p = 0.009). CONCLUSION: The emergency declaration declined the exercise tolerance in patients on phase III CR but improved to pre- declaration levels over time, but more likely declined in patients with multiple comorbidities during pre-declaration and those with low-gait speeds were less likely to improve their declined exercise tolerance.

RESUMEN

Background/Hypothesis: Cardiopulmonary exercise testing (CPET) is used in the assessment of function and prognosis of cardiopulmonary health in children with cardiac and pulmonary diseases. Techniques, such as cardiac MRi, and PET-scan, can be performed simultaneously with exercise testing. Thus, it is desirable to have a broader knowledge about children's normal cardiopulmonary function in different body postures and exercise modalities. The aim of this study was to investigate the effect of different body positions on cardiopulmonary function in healthy subjects performing CPETs. Materials and Methods: Thirty-one healthy children aged 9, 12, and 15 years did four CPETs: one treadmill test with a modified Bruce protocol and three different bicycle tests with different body postures, sitting, tilted 45°, and lying flat (0°). For the bicycle tests, a 20-watt ramp protocol with a pedal frequency of 60 ± 5 rotations per minute was used. Continous ECG and breath-by-breath V . O 2 measurements was done throughout the tests. Cardiac structure and function including aortic diameter were evaluated by transthoracic echocardiography prior to the tests. Doppler measurements of the blood velocity in the ascending aorta were measured prior to and during the test. Prior to every test, the participants performed pulmonary function tests with maximum voluntary ventilation test. Results: There is a significantly (p < 0.05) lower peak V . O 2 in all bicycle tests compared with the treadmill test. There is lower corrected peak V . O 2 (ml kg-0.67 min-1), but not relative peak V . O 2 (ml kg-1 min-1), in the supine compared with the upright bicycle test. There are no differences in peak stroke volume or cardiac output between the bicycle modalities when calculated from aortic blood flow. Peak heart rate decreases from both treadmill to upright bicycle and from upright bicycle to the supine test (0°). Conclusion: There are no differences in peak cardiac output between the upright bicycle test and supine bicycle tests. Heart rate and corrected peak V . O 2 are lower in the supine test (0°) than the upright bicycle test. In the treadmill test, it is a higher absolute and relative peak V . O 2 . Despite the latter differences, we are convinced that both upright and supine bicycle tests are apt in the clinical setting when needed.

RESUMEN

OBJECTIVE: Hypobaric hypoxia decreases exercise capacity and causes hypoxic pulmonary vasoconstriction and pulmonary hypertension. The phosphodiesterase-5 inhibitor sildenafil is a pulmonary vasodilator that may improve exercise capacity at altitude. We aimed to determine whether sildenafil improves exercise capacity, measured as maximal oxygen consumption (peak V̇o2), at moderate altitude in adults 60 years or older. METHODS: The design was a randomized, double-blind, placebo-controlled, crossover study. After baseline cardiopulmonary exercise testing at 1400 m, 12 healthy participants (4 women) aged 60 years or older, who reside permanently at approximately 1400 m and are regularly active in self-propelled mountain recreation above 2000 m, performed maximal cardiopulmonary cycle exercise tests in a hypobaric chamber at a simulated altitude of 2750 m after ingesting sildenafil and after ingesting a placebo. RESULTS: After placebo, mean peak V̇o2 was significantly lower at 2750 m than 1400 m: 37.0 mL · kg(-1) · min(-1) (95% CI, 32.7 to 41.3) vs 39.1 mL · kg(-1) · min(-1) (95% CI, 33.5 to 44.7; P = .020). After placebo, there was no difference in heart rate (HR) or maximal workload at either altitude (z = 0.182; P = .668, respectively). There was no difference between sildenafil and placebo at 2750 m in peak V̇o2 (P = .668), O2 pulse (P = .476), cardiac index (P = .143), stroke volume index (z = 0.108), HR (z = 0.919), or maximal workload (P = .773). Transthoracic echocardiography immediately after peak exercise at 2750 m showed tricuspid annular plane systolic velocity was significantly higher after sildenafil than after placebo (P = .019), but showed no difference in tricuspid annular plane systolic excursion (P = .720). CONCLUSIONS: Sildenafil (50 mg) did not improve exercise capacity in adults 60 years or older at moderate altitude in our study. This might be explained by a "dosing effect" or insufficiently high altitude.

Asunto(s)

Tolerancia al Ejercicio/efectos de los fármacos , Citrato de Sildenafil/farmacología , Anciano , Altitud , Electrocardiografía , Ejercicio Físico/fisiología , Prueba de Esfuerzo , Femenino , Frecuencia Cardíaca/efectos de los fármacos , Humanos , Masculino , Persona de Mediana Edad , Resultado del Tratamiento , Vasodilatadores/farmacología