Machine Learning for Electrocardiographic Features to Identify Left Atrial Enlargement in Young Adults: CHIEF Heart Study

Comparing Artificial Intelligence-Enabled Electrocardiogram Models in Identifying Left Atrium Enlargement and Long-term Cardiovascular Risk

BACKGROUND

The role of P-wave in identifying left atrial enlargement (LAE) with the use of artificial intelligence (AI)-enabled electrocardiography (ECG) models is unclear. It is also unknown if AI-enabled single-lead ECG could be used as a diagnostic tool for LAE surveillance. We aimed to build AI-enabled P-wave and single-lead ECG models to identify LAE using sinus rhythm (SR) and non-SR ECGs, and compare the prognostic ability of severe LAE, defined as left atrial diameter ≥ 50 mm, assessed by AI-enabled ECG models vs echocardiography.

METHODS

This retrospective study used data from 382,594 consecutive adults with paired 12-lead ECG and echocardiography performed within 2 weeks of each other at Chang Gung Memorial Hospital. UNet++ was used for P-wave segmentation. ResNet-18 was used to develop deep convolutional neural network-enabled ECG models for discriminating LAE. External validation was performed with the use of data from 11,753 patients from another hospital.

RESULTS

The AI-enabled 12-lead ECG model outperformed other ECG models for classifying LAE, but the single-lead ECG models also showed excellent performance at a left atrial diameter cutoff of 50 mm. AI-enabled ECG models had excellent and fair discrimination on LAE using the SR and the non-SR data set, respectively. Severe LAE identified by AI-enabled ECG models was more predictive of future cardiovascular disease than echocardiography; however, the cumulative incidence of new-onset atrial fibrillation and heart failure was higher in patients with echocardiography-severe LAE than with AI-enabled ECG-severe LAE.

CONCLUSIONS

P-Wave plays a crucial role in discriminating LAE in AI-enabled ECG models. AI-enabled ECG models outperform echocardiography in predicting new-onset cardiovascular diseases associated with severe LAE.

Estimated power output for a distance run and maximal oxygen uptake in young adults

Background: Both cardiopulmonary exercise testing (CPET) and run field tests are recommended by the American Heart Association for assessing the maximal oxygen uptake (VO₂ max) of youth. Power output was highly correlated with VO₂ max in CPET. However, it is unclear regarding the correlations of time and estimated power output (EPO) for a run field test with VO₂ max obtained from CPET in young adults. Methods: This study included 45 participants, aged 20-40 years, from a sample of 1,120 military personnel who completed a 3,000-m run field test in Taiwan in 2020. The participants subsequently received CPET using the Bruce protocol to assess VO₂ max in the same year. According to the physics rule, EPO (watts) for the run field test was defined as the product of half body mass (kg) and [distance (3000-m)/time (s) for a run field test]. Pearson product-moment correlation analyses were performed. Results: The Pearson correlation coefficient (r) of time against EPO for the run field test was estimated to be 0.708 (p <0.001). The correlation coefficient between the time for the run field test and VO₂ max (L/min) in CPET was estimated to be 0.462 (p = 0.001). In contrast, the correlation coefficient between time for the run field test and VO₂ max scaled to body mass in CPET was estimated to be 0.729 (p <0.001). The correlation coefficient of EPO for the run field test against VO₂ max in CPET was estimated to be 0.813 (p <0.001). Conclusion: In young adults, although the time for a run field test was a reliable estimate of VO₂ max scaled to body mass, EPO proportional to the mean square velocity was found as a superior estimate of VO₂ max.

Algorithms for automated diagnosis of cardiovascular diseases based on ECG data: A comprehensive systematic review

The prevalence of cardiovascular diseases is increasing around the world. However, the technology is evolving and can be monitored with low-cost sensors anywhere at any time. This subject is being researched, and different methods can automatically identify these diseases, helping patients and healthcare professionals with the treatments. This paper presents a systematic review of disease identification, classification, and recognition with ECG sensors. The review was focused on studies published between 2017 and 2022 in different scientific databases, including PubMed Central, Springer, Elsevier, Multidisciplinary Digital Publishing Institute (MDPI), IEEE Xplore, and Frontiers. It results in the quantitative and qualitative analysis of 103 scientific papers. The study demonstrated that different datasets are available online with data related to various diseases. Several ML/DP-based models were identified in the research, where Convolutional Neural Network and Support Vector Machine were the most applied algorithms. This review can allow us to identify the techniques that can be used in a system that promotes the patient's autonomy.

Muscular Strength and Carotid Intima-Media Thickness in Physically Fit Young Adults: The CHIEF Atherosclerosis Study

Background: Greater muscular strength (MusS) has been found to have an inverse association with subclinical atherosclerosis in children, as well as with mortality from cardiovascular diseases (CVDs) in middle-aged and elderly individuals. However, the association of the degree of MusS with atherosclerosis may differ by sex and has not been clarified in young adults. Methods and Results: A total of 1021 Taiwanese military personnel, aged 18−40 years, participated in annual health examinations in 2018−2020. MusS was separately assessed by 2-min push-up and 2-min sit-up numbers. Subclinical atherosclerosis was measured by the left carotid bulb intima−media thickness (cIMT) using high-resolution ultrasonography. Multiple linear regression with adjustments for age, sex, alcohol intake, cigarette smoking, anthropometric indices, blood pressure, and lipid profiles was utilized to determine the correlation between MusS and cIMT. Both 2-min push-up and 2-min sit-up numbers were inversely correlated with cIMT (standardized β: −0.089 and −0.072, respectively; both p-values < 0.05). In men, both 2-min push-up and 2-min sit-up numbers were inversely correlated with cIMT (standardized β: −0.076 and −0.086, respectively; both p-values < 0.05), while in women, 2-min push-up numbers but not 2-min sit-up numbers were inversely correlated with cIMT (standardized β: −0.204 and −0.01; p = 0.03 and 0.99, respectively). Conclusions: Among young adults, there was an inverse association between MusS and cIMT, emphasizing the beneficial impact of MusS on the regression of atherosclerosis. The study also revealed a sex difference and suggested that training of the upper arm muscles may be an effective preventive measure for young women to reduce the risk of early cardiovascular diseases.

Electrocardiographic and cardiometabolic risk markers of left ventricular diastolic dysfunction in physically active adults: CHIEF heart study

Aim

This study was aimed to investigate the association of cardiometabolic and ECG markers with left ventricular diastolic dysfunction (LVDD) in physically active Asian young adults, which has not been clarified in prior studies.

Methods and results

A total of 2,019 men aged 18–43 years were included from the military in Taiwan. All the subjects underwent anthropometric, hemodynamic, and blood metabolic marker measurements. Physical fitness was investigated by time for a 3,000-m run. LVDD was defined by presence of either one of the three echocardiographic criteria: (1) mitral inflow E/A ratio < 0.8 with a peak E velocity of > 50 cm/s, (2) tissue Doppler lateral mitral annulus e′ <10 cm/s, and (3) E/e′ ratio > 14. Multiple logistic regressions with adjustments for age, physical fitness, and pulse rate were conducted to determine the association of cardiometabolic and ECG markers with LVDD. The prevalence of LVDD was estimated to be 4.16% (N = 84). Of the cardiometabolic markers, central obesity, defined as waist circumference ≥ 90 cm, was the only independent marker of LVDD [odds ratio (OR) and 95% confidence interval: 2.97 (1.63–5.41)]. There were no association for hypertension, prediabetes, and dyslipidemia. Of the ECG markers, left atrial enlargement and incomplete right bundle branch block/intraventricular conduction delay were the independent ECG markers of LVDD [OR: 2.98 (1.28–6.94) and 1.94 (1.09–3.47), respectively]. There was borderline association for Cornell-based left ventricular hypertrophy and inferior T wave inversion [OR: 1.94 (0.97–3.63) and 2.44 (0.98–6.08), respectively].

Conclusion

In the physically active Asian young male adults, central obesity and some ECG markers for left heart abnormalities were useful to identify LVDD.

Cardiorespiratory Fitness and Carotid Intima-Media Thickness in Physically Active Young Adults: CHIEF Atherosclerosis Study

Background: The relationship of cardiorespiratory fitness (CRF) with subclinical atherosclerosis affected by the body adiposity has been observed in children, whereas this relationship remains unclear in young adults. Methods and Results: A total of 1520 military recruits, aged 18−40 years, were included in Taiwan in 2018−2020. All subjects underwent detailed physical and blood laboratory examinations. CRF was evaluated by time for a 3000 m run, and subclinical atherosclerosis was evaluated by intima−media thickness of the bulb of the left common carotid artery (cIMT) utilizing high-resolution ultrasonography. Multivariable linear regression analysis with adjustments for age, sex, cigarette smoking, alcohol intake, systolic and diastolic blood pressure, high- and low-density lipoprotein cholesterols, fasting glucose, waist circumference, serum uric acid and serum triglycerides were utilized to determine the correlation between CRF and cIMT. CRF was independently correlated with cIMT (standardized β: 0.11, p < 0.001). Of the cardiometabolic risk markers, serum triglycerides were the only independent risk marker of cIMT (standardized β: 0.063, p = 0.03). In addition, the association of CRF with cIMT did not differ between those with a body mass index (BMI) ≥ 25 kg/m2 and those with BMI < 25 kg/m2 (standardized β: 0.103 and 0.117; p = 0.01 and 0.005, respectively). Conclusions: In physically active young men and women, there was an inverse association of cIMT with CRF, which was observed in both overweight/mild obesity and normal-weight individuals, highlighting the importance of endurance capacity on reducing risk of early atherosclerosis and implying that the moderation effect of body adiposity might not be present in this population.