Screening for Asymptomatic Left Ventricular Dysfunction Using B-Type Natriuretic Peptide

Artificial intelligence in cardiovascular medicine: An updated review of the literature

Screening and early detection of cardiovascular disease (CVD) are crucial for managing progress and preventing related morbidity. In recent years, several studies have reported the important role of Artificial intelligence (AI) technology and its integration into various medical sectors. AI applications are able to deal with the massive amounts of data (medical records, ultrasounds, medications, and experimental results) generated in medicine and identify novel details that would otherwise be forgotten in the mass of healthcare data sets. Nowadays, AI algorithms are currently used to improve diagnosis of some CVDs including heart failure, atrial fibrillation, hypertrophic cardiomyopathy and pulmonary hypertension. This review summarized some AI concepts, critical execution requirements, obstacles, and new applications for CVDs.

Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images

BACKGROUND

Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning-based approach that can use ECG images for the screening of LV systolic dysfunction.

METHODS

Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images.

RESULTS

Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3-33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V2 and V3), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3-4.7]; median follow-up, 3.2 years).

CONCLUSIONS

We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.

Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices

Artificial intelligence (AI) can detect left ventricular systolic dysfunction (LVSD) from electrocardiograms (ECGs). Wearable devices could allow for broad AI-based screening but frequently obtain noisy ECGs. We report a novel strategy that automates the detection of hidden cardiovascular diseases, such as LVSD, adapted for noisy single-lead ECGs obtained on wearable and portable devices. We use 385,601 ECGs for development of a standard and noise-adapted model. For the noise-adapted model, ECGs are augmented during training with random gaussian noise within four distinct frequency ranges, each emulating real-world noise sources. Both models perform comparably on standard ECGs with an AUROC of 0.90. The noise-adapted model performs significantly better on the same test set augmented with four distinct real-world noise recordings at multiple signal-to-noise ratios (SNRs), including noise isolated from a portable device ECG. The standard and noise-adapted models have an AUROC of 0.72 and 0.87, respectively, when evaluated on ECGs augmented with portable ECG device noise at an SNR of 0.5. This approach represents a novel strategy for the development of wearable-adapted tools from clinical ECG repositories.

Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823-0.946) and 0.881 (0.815-0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

Real-world performance, long-term efficacy, and absence of bias in the artificial intelligence enhanced electrocardiogram to detect left ventricular systolic dysfunction

Aims

Some artificial intelligence models applied in medical practice require ongoing retraining, introduce unintended racial bias, or have variable performance among different subgroups of patients. We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm’s long-term efficacy and potential bias in the absence of retraining.

Methods and results

Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. Time series analysis of the model validated its temporal stability. Areas under the curve were similar for all racial and ethnic groups (0.90–0.92) with minimal performance difference between sexes. Patients with a ‘normal sinus rhythm’ electrocardiogram (n = 37 047) exhibited an AUC of 0.91. All other electrocardiogram features had areas under the curve between 0.79 and 0.91, with the lowest performance occurring in the left bundle branch block group (0.79).

Conclusion

The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.

Application of artificial intelligence to the electrocardiogram

Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.

The Effectiveness of a Deep Learning Model to Detect Left Ventricular Systolic Dysfunction from Electrocardiograms

Deep learning models can be applied to electrocardiograms (ECGs) to detect left ventricular (LV) dysfunction. We hypothesized that applying a deep learning model may improve the diagnostic accuracy of cardiologists in predicting LV dysfunction from ECGs. We acquired 37,103 paired ECG and echocardiography data records of patients who underwent echocardiography between January 2015 and December 2019. We trained a convolutional neural network to identify the data records of patients with LV dysfunction (ejection fraction < 40%) using a dataset of 23,801 ECGs. When tested on an independent set of 7,196 ECGs, we found the area under the receiver operating characteristic curve was 0.945 (95% confidence interval: 0.936-0.954). When 7 cardiologists interpreted 50 randomly selected ECGs from the test dataset of 7,196 ECGs, their accuracy for predicting LV dysfunction was 78.0% ± 6.0%. By referring to the model's output, the cardiologist accuracy improved to 88.0% ± 3.7%, which indicates that model support significantly improved the cardiologist diagnostic accuracy (P = 0.02). A sensitivity map demonstrated that the model focused on the QRS complex when detecting LV dysfunction on ECGs. We developed a deep learning model that can detect LV dysfunction on ECGs with high accuracy. Furthermore, we demonstrated that support from a deep learning model can help cardiologists to identify LV dysfunction on ECGs.

Deep learning analysis of resting electrocardiograms for the detection of myocardial dysfunction, hypertrophy, and ischaemia: a systematic review

The aim of this review was to assess the evidence for deep learning (DL) analysis of resting electrocardiograms (ECGs) to predict structural cardiac pathologies such as left ventricular (LV) systolic dysfunction, myocardial hypertrophy, and ischaemic heart disease. A systematic literature search was conducted to identify published original articles on end-to-end DL analysis of resting ECG signals for the detection of structural cardiac pathologies. Studies were excluded if the ECG was acquired by ambulatory, stress, intracardiac, or implantable devices, and if the pathology of interest was arrhythmic in nature. After duplicate reviewers screened search results, 12 articles met the inclusion criteria and were included. Three articles used DL to detect LV systolic dysfunction, achieving an area under the curve (AUC) of 0.89-0.93 and an accuracy of 98%. One study used DL to detect LV hypertrophy, achieving an AUC of 0.87 and an accuracy of 87%. Six articles used DL to detect acute myocardial infarction, achieving an AUC of 0.88-1.00 and an accuracy of 83-99.9%. Two articles used DL to detect stable ischaemic heart disease, achieving an accuracy of 95-99.9%. Deep learning models, particularly those that used convolutional neural networks, outperformed rules-based models and other machine learning models. Deep learning is a promising technique to analyse resting ECG signals for the detection of structural cardiac pathologies, which has clinical applicability for more effective screening of asymptomatic populations and expedited diagnostic work-up of symptomatic patients at risk for cardiovascular disease.

The application of deep learning in electrocardiogram: Where we came from and where we should go?

Electrocardiogram (ECG) is a commonly-used, non-invasive examination recording cardiac voltage versus time traces over a period. Deep learning technology, a robust artificial intelligence algorithm, can imitate the data processing patterns of the human brain, and it has experienced remarkable success in disease screening, diagnosis, and prediction. Compared with traditional machine learning, deep learning algorithms possess more powerful learning capabilities and can automatically extract features without extensive data pre-processing or hand-crafted feature extraction, which makes it a suitable tool to analyze complex structures of high-dimensional data. With the advances in computing power and digitized data availability, deep learning provides us an opportunity to improve ECG data interpretation with higher efficacy and accuracy and, more importantly, expand the original functions of ECG. The application of deep learning has led us to stand at the edge of ECG innovation and will potentially change the current clinical monitoring and management strategies. In this review, we introduce deep learning technology and summarize its advantages compared with traditional machine learning algorithms. Moreover, we provide an overview on the current application of deep learning in ECGs, with a focus on arrhythmia (especially atrial fibrillation during normal sinus rhythm), cardiac dysfunction, electrolyte imbalance, and sleep apnea. Last but not least, we discuss the current challenges and prospect directions for the following studies.

Machine learning phenotyping of scarred myocardium from cine in hypertrophic cardiomyopathy

AIMS

Cardiovascular magnetic resonance (CMR) with late-gadolinium enhancement (LGE) is increasingly being used in hypertrophic cardiomyopathy (HCM) for diagnosis, risk stratification, and monitoring. However, recent data demonstrating brain gadolinium deposits have raised safety concerns. We developed and validated a machine-learning (ML) method that incorporates features extracted from cine to identify HCM patients without fibrosis in whom gadolinium can be avoided.

METHODS AND RESULTS

An XGBoost ML model was developed using regional wall thickness and thickening, and radiomic features of myocardial signal intensity, texture, size, and shape from cine. A CMR dataset containing 1099 HCM patients collected using 1.5T CMR scanners from different vendors and centres was used for model development (n=882) and validation (n=217). Among the 2613 radiomic features, we identified 7 features that provided best discrimination between +LGE and -LGE using 10-fold stratified cross-validation in the development cohort. Subsequently, an XGBoost model was developed using these radiomic features, regional wall thickness and thickening. In the independent validation cohort, the ML model yielded an area under the curve of 0.83 (95% CI: 0.77-0.89), sensitivity of 91%, specificity of 62%, F1-score of 77%, true negatives rate (TNR) of 34%, and negative predictive value (NPV) of 89%. Optimization for sensitivity provided sensitivity of 96%, F2-score of 83%, TNR of 19% and NPV of 91%; false negatives halved from 4% to 2%.

CONCLUSION

An ML model incorporating novel radiomic markers of myocardium from cine can rule-out myocardial fibrosis in one-third of HCM patients referred for CMR reducing unnecessary gadolinium administration.

Assessing and Mitigating Bias in Medical Artificial Intelligence: The Effects of Race and Ethnicity on a Deep Learning Model for ECG Analysis

BACKGROUND

Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG.

METHODS

We performed a retrospective cohort analysis that included 97 829 patients with paired ECGs and echocardiograms. We tested the model performance by race/ethnicity for convolutional neural network designed to identify patients with a left ventricular ejection fraction ≤35% from the 12-lead ECG.

RESULTS

The convolutional neural network that was previously derived in a homogeneous population (derivation cohort, n=44 959; 96.2% non-Hispanic white) demonstrated consistent performance to detect low left ventricular ejection fraction across a range of racial/ethnic subgroups in a separate testing cohort (n=52 870): non-Hispanic white (n=44 524; area under the curve [AUC], 0.931), Asian (n=557; AUC, 0.961), black/African American (n=651; AUC, 0.937), Hispanic/Latino (n=331; AUC, 0.937), and American Indian/Native Alaskan (n=223; AUC, 0.938). In secondary analyses, a separate neural network was able to discern racial subgroup category (black/African American [AUC, 0.84], and white, non-Hispanic [AUC, 0.76] in a 5-class classifier), and a network trained only in non-Hispanic whites from the original derivation cohort performed similarly well across a range of racial/ethnic subgroups in the testing cohort with an AUC of at least 0.930 in all racial/ethnic subgroups.

CONCLUSIONS

Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine.

N-Terminal Pro-B-type Natriuretic Peptide Levels in the Korean General Population

Background and Objectives

B-type natriuretic peptide (BNP) or N-terminal pro-BNP (NT-proBNP) levels may serve as a useful marker of cardiovascular risk for screening of the general population. We evaluated reference levels and distribution of NT-proBNP in the Korean general population based on a large cohort study.

Subjects and Methods

We included 1,518 adult subjects (ages 40-69) of a community-based cohort from the Korea Rural Genomic Cohort (KRGC) Study. Thorough biochemical and clinical data were recorded for all subjects. Levels of NT-proBNP from all participants were determined. In order to determine normal reference levels, subjects with factors known to influence NT-proBNP levels were excluded.

Results

The characteristics of the cohort are described below; subjects were 41.2% male, and the mean age was 54.8±8.4 years. The distribution of risk factors for cardiovascular disease in the cohort included hypertension (25%), left ventricular hypertrophy by electrocardiography (ECG-LVH) (15%), hypercholestolemia (4.5%), smoking (32%), diabetes (10.9%), history of coronary heart disease (4.9%), history of heart failure (0.9%), symptoms of heart failure (6.1%), elevated serum creatinine (≥1.5, 3.7%), and severe obesity (body mass index >30 kg/m², 4.6%). The levels of NT-proBNP of all subjects are shown below; the mean was 60.1±42.1, and the median was 36.5 pg/mL. In addition, the levels of NT-proBNP of normal subjects (which did not have any risk factors, n=224) are shown below; the mean was 40.8, and the median was 32.1 pg/mL. In normal subjects, the NT-proBNP level was slightly higher in females (25.7±24.8 vs. 46.9±35.4, p<0.001). NT-proBNP level increased with age in both the normal population and the total population. There were no significant differences in NT-proBNP levels in subjects who smoked, or had diabetes mellitus, hypertension or ECG-LVH. However, in subjects with a history of congestive heart failure (CHF) (58.5±103.29 vs. 213.8±258.8, p<0.005), elevated serum creatinine levels (≥1.5 mg/dL, 146.2±98.2 vs. 54.3±38.1, p<0.001), or who were older (≥60, 48.4 vs. 84.2±139.5 pg/mL, p<0.05), the BNP level was higher. In addition, patients with more than 3 risk factors for CHF had higher BNP levels (risk 0: 40.8±34.0, 1-2: 57.4±93.2, ≥3: 85.0±152.9 pg/mL). NT-proBNP levels were also related with age, sex, urine albumin, serum Cr, and high sensitivity C-reactive protein (p<0.05).

Conclusion

We determined the reference value and distribution of NT-proBNP in the Korean adult general population. We also found that adjustments for the independent effects of age, sex and renal function appear necessary when determining cardiac risk based on proBNP levels.