Scoring System Based on Electrocardiogram Features to Predict the Type of Heart Failure in Patients With Chronic Heart Failure

Artificial Intelligence-Based Electrocardiographic Biomarker for Outcome Prediction in Patients With Acute Heart Failure: Prospective Cohort Study

BACKGROUND

Although several biomarkers exist for patients with heart failure (HF), their use in routine clinical practice is often constrained by high costs and limited availability.

OBJECTIVE

We examined the utility of an artificial intelligence (AI) algorithm that analyzes printed electrocardiograms (ECGs) for outcome prediction in patients with acute HF.

METHODS

We retrospectively analyzed prospectively collected data of patients with acute HF at two tertiary centers in Korea. Baseline ECGs were analyzed using a deep-learning system called Quantitative ECG (QCG), which was trained to detect several urgent clinical conditions, including shock, cardiac arrest, and reduced left ventricular ejection fraction (LVEF).

RESULTS

Among the 1254 patients enrolled, in-hospital cardiac death occurred in 53 (4.2%) patients, and the QCG score for critical events (QCG-Critical) was significantly higher in these patients than in survivors (mean 0.57, SD 0.23 vs mean 0.29, SD 0.20; P<.001). The QCG-Critical score was an independent predictor of in-hospital cardiac death after adjustment for age, sex, comorbidities, HF etiology/type, atrial fibrillation, and QRS widening (adjusted odds ratio [OR] 1.68, 95% CI 1.47-1.92 per 0.1 increase; P<.001), and remained a significant predictor after additional adjustments for echocardiographic LVEF and N-terminal prohormone of brain natriuretic peptide level (adjusted OR 1.59, 95% CI 1.36-1.87 per 0.1 increase; P<.001). During long-term follow-up, patients with higher QCG-Critical scores (>0.5) had higher mortality rates than those with low QCG-Critical scores (<0.25) (adjusted hazard ratio 2.69, 95% CI 2.14-3.38; P<.001).

CONCLUSIONS

Predicting outcomes in patients with acute HF using the QCG-Critical score is feasible, indicating that this AI-based ECG score may be a novel biomarker for these patients.

TRIAL REGISTRATION

ClinicalTrials.gov NCT01389843; https://clinicaltrials.gov/study/NCT01389843.

Heart failure classification using deep learning to extract spatiotemporal features from ECG

BACKGROUND

Heart failure is a syndrome with complex clinical manifestations. Due to increasing population aging, heart failure has become a major medical problem worldwide. In this study, we used the MIMIC-III public database to extract the temporal and spatial characteristics of electrocardiogram (ECG) signals from patients with heart failure.

METHODS

We developed a NYHA functional classification model for heart failure based on a deep learning method. We introduced an integrating attention mechanism based on the CNN-LSTM-SE model, segmenting the ECG signal into 2 to 20 s long segments. Ablation experiments showed that the 12 s ECG signal segments could be used with the proposed deep learning model for superior classification of heart failure.

RESULTS

The accuracy, positive predictive value, sensitivity, and specificity of the NYHA functional classification method were 99.09, 98.9855, 99.033, and 99.649%, respectively.

CONCLUSIONS

The comprehensive performance of this model exceeds similar methods and can be used to assist in clinical medical diagnoses.

Integrative review of electrocardiographic characteristics in patients with reduced, mildly reduced, and preserved heart failure

INTRODUCTION

Electrocardiographic (ECG) changes in heart failure with reduced, mildly reduced, and preserved ejection fractions can be critical in clinical assessment while waiting to perform echocardiograms or when it is unavailable. This integrative review aimed to identify ECG characteristics among hospitalized patients demonstrating three types of heart failure during acute decompensation.

METHODS

We searched an electronic database of PubMed, Web of Science, EMBASE, Scopus, Google Scholar, and ClinicalTrials.gov using medical subject headings (MeSH) terms and keywords. Sixteen studies were synthesized and reported.

RESULTS

Heart failure with reduced ejection fraction (HFrEF) was more common in men, comorbid with coronary artery diseases and diabetes mellitus, higher BNP/Pro-BNP, wide QRS, and left bundle branch block on ECG. On average, clients with heart failure with preserved ejection fraction (HFpEF) were older and more likely to have a history of atrial fibrillation, valvular heart diseases, hypertension, chronic obstructive pulmonary, and atrial fibrillation (AF) on ECG. Patients with mildly reduced (HFmrEF) were more similar to HFpEF in older patients, comorbid with hypertension, AF and valvular diseases, and AF on ECG.

CONCLUSIONS

ECG characteristics might be related to left ventricular ejection fraction. Demographics, BNP/Pro-BNP, and ECG changes might help differentiate different heart failure types. Therefore, ECG might be a prognostic tool while caring for heart failure patients when highly skilled resources are unavailable. These identified ECG characteristics help generate research hypotheses and warrant validation in future research.

A generalizable electrocardiogram-based artificial intelligence model for 10-year heart failure risk prediction

Background

Heart failure (HF) is a progressive condition with high global incidence. HF has two main subtypes: HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF). There is an inherent need for simple yet effective electrocardiogram (ECG)-based artificial intelligence (AI; ECG-AI) models that can predict HF risk early to allow for risk modification.

Objective

The main objectives were to validate HF risk prediction models using Multi-Ethnic Study of Atherosclerosis (MESA) data and assess performance on HFpEF and HFrEF classification.

Methods

There were six models in comparision derived using ARIC data. 1) The ECG-AI model predicting HF risk was developed using raw 12-lead ECGs with a convolutional neural network. The clinical models from 2) ARIC (ARIC-HF) and 3) Framingham Heart Study (FHS-HF) used 9 and 8 variables, respectively. 4) Cox proportional hazards (CPH) model developed using the clinical risk factors in ARIC-HF or FHS-HF. 5) CPH model using the outcome of ECG-AI and the clinical risk factors used in CPH model (ECG-AI-Cox) and 6) A Light Gradient Boosting Machine model using 288 ECG Characteristics (ECG-Chars). All the models were validated on MESA. The performances of these models were evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test.

Results

ECG-AI, ECG-Chars, and ECG-AI-Cox resulted in validation AUCs of 0.77, 0.73, and 0.84, respectively. ARIC-HF and FHS-HF yielded AUCs of 0.76 and 0.74, respectively, and CPH resulted in AUC = 0.78. ECG-AI-Cox outperformed all other models. ECG-AI-Cox provided an AUC of 0.85 for HFrEF and 0.83 for HFpEF.

Conclusion

ECG-AI using ECGs provides better-validated predictions when compared to HF risk calculators, and the ECG feature model and also works well with HFpEF and HFrEF classification.

An automatic approach for heart failure typing based on heart sounds and convolutional recurrent neural networks

Heart failure (HF) is a complex clinical syndrome that poses a major hazard to human health. Patients with different types of HF have great differences in pathogenesis and treatment options. Therefore, HF typing is of great significance for timely treatment of patients. In this paper, we proposed an automatic approach for HF typing based on heart sounds (HS) and convolutional recurrent neural networks, which provides a new non-invasive and convenient way for HF typing. Firstly, the collected HS signals were preprocessed with adaptive wavelet denoising. Then, the logistic regression based hidden semi-Markov model was utilized to segment HS frames. For the distinction between normal subjects and the HF patients with preserved ejection fraction or reduced ejection fraction, a model based on convolutional neural network and recurrent neural network was built. The model can automatically learn the spatial and temporal characteristics of HS signals. The results show that the proposed model achieved a superior performance with an accuracy of 97.64%. This study suggests the proposed method could be a useful tool for HF recognition and as a supplement for HF typing.

Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study

Background

Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied to a single-lead ECG, recorded during ECG-enabled stethoscope examination, to validate a potential point-of-care screening tool for LVEF of 40% or lower.

Methods

We conducted an observational, prospective, multicentre study of a convolutional neural network (known as AI-ECG) that was previously validated for the detection of reduced LVEF using 12-lead ECG as input. We used AI-ECG retrained to interpret single-lead ECG input alone. Patients (aged ≥18 years) attending for transthoracic echocardiogram in London (UK) were recruited. All participants had 15 s of supine, single-lead ECG recorded at the four standard anatomical positions for cardiac auscultation, plus one handheld position, using an ECG-enabled stethoscope. Transthoracic echocardiogram-derived percentage LVEF was used as ground truth. The primary outcome was performance of AI-ECG at classifying reduced LVEF (LVEF ≤40%), measured using metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with two-sided 95% CIs. The primary outcome was reported for each position individually and with an optimal combination of AI-ECG outputs (interval range 0–1) from two positions using a rule-based approach and several classification models. This study is registered with ClinicalTrials.gov, NCT04601415.

Findings

Between Feb 6 and May 27, 2021, we recruited 1050 patients (mean age 62 years [SD 17·4], 535 [51%] male, 432 [41%] non-White). 945 (90%) had an ejection fraction of at least 40%, and 105 (10%) had an ejection fraction of 40% or lower. Across all positions, ECGs were most frequently of adequate quality for AI-ECG interpretation at the pulmonary position (979 [93·3%] of 1050). Quality was lowest for the aortic position (846 [80·6%]). AI-ECG performed best at the pulmonary valve position (p=0·02), with an AUROC of 0·85 (95% CI 0·81–0·89), sensitivity of 84·8% (76·2–91·3), and specificity of 69·5% (66·4–72·6). Diagnostic odds ratios did not differ by age, sex, or non-White ethnicity. Taking the optimal combination of two positions (pulmonary and handheld positions), the rule-based approach resulted in an AUROC of 0·85 (0·81–0·89), sensitivity of 82·7% (72·7–90·2), and specificity of 79·9% (77·0–82·6). Using AI-ECG outputs from these two positions, a weighted logistic regression with l2 regularisation resulted in an AUROC of 0·91 (0·88–0·95), sensitivity of 91·9% (78·1–98·3), and specificity of 80·2% (75·5–84·3).

Interpretation

A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG-enabled stethoscope can detect LVEF of 40% or lower. These findings highlight the potential for inexpensive, non-invasive, workflow-adapted, point-of-care screening, for earlier diagnosis and prognostically beneficial treatment.

Funding

NHS Accelerated Access Collaborative, NHSX, and the National Institute for Health Research.

Effect of ivabradine in heart failure: a meta-analysis of heart failure patients with reduced versus preserved ejection fraction

In clinical trials of heart failure reduced ejection fraction (HFrEF), ivabradine seemed to be an effective heart rate lowering agent associated with lower risk of cardiovascular death. In contrast, ivabradine failed to improve cardiovascular outcomes in heart failure preserved ejection fraction (HFpEF) despite the significant effect on heart rate. This meta-analysis is the first to compare the effects of ivabradine on heart rate and mortality parameters in HFpEF versus HFrEF. We screened three databases: PubMed, Embase, and Cochrane Library. The outcomes of these studies were mortality, reduction in heart rate, and left ventricular function improvement. We compared the efficacy of ivabradine treatment in HFpEF versus HFrEF. Heart rate analysis of pooled data showed decrease in both HFrEF (-17.646 beats/min) and HFpEF (-11.434 beats/min), and a tendency to have stronger bradycardic effect in HFrEF (p = 0.094) in randomized clinical trials. Left ventricular ejection fraction analysis revealed significant improvement in HFrEF (5.936, 95% CI: [4.199-7.672], p < 0.001) when compared with placebo (p < 0.001). We found that ivabradine significantly improves left ventricular performance in HFrEF, at the same time it exerts a tendency to have improved bradycardic effect in HFrEF. These disparate effects of ivabradine and the higher prevalence of non-cardiac comorbidities in HFpEF may explain the observed beneficial effects in HFrEF and the unchanged outcomes in HFpEF patients after ivabradine treatment.

Using Deep-Learning Algorithms to Simultaneously Identify Right and Left Ventricular Dysfunction From the Electrocardiogram

OBJECTIVES

This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.

BACKGROUND

Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right- ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.

METHODS

A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.

RESULTS

We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% < LVEF ≤50%, and LVEF >50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation.

CONCLUSIONS

DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

Artificial intelligence assessment for early detection of heart failure with preserved ejection fraction based on electrocardiographic features

Aims

Although heart failure with preserved ejection fraction (HFpEF) is a rapidly emerging global health problem, an adequate tool to screen it reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance.

Methods and results

This retrospective cohort study included two hospitals. 34 103 patients who underwent echocardiography and ECG within 1 week and indicated normal left ventricular systolic function were included in this study. A DLM based on an ensemble neural network was developed using 32 671 ECGs of 20 169 patients. The internal validation included 1979 ECGs of 1979 patients. Furthermore, we conducted an external validation with 11 955 ECGs of 11 955 patients from another hospital. The endpoint was to detect HFpEF. During the internal and external validation, the area under the receiver operating characteristic curves of a DLM using 12-lead ECG for detecting HFpEF were 0.866 (95% confidence interval 0.850-0.883) and 0.869 (0.860-0.877), respectively. In the 1412 individuals without HFpEF at initial echocardiography, patients whose DLM was defined as having a higher risk had a significantly higher chance of developing HFpEF than those in the low-risk group (33.6% vs. 8.4%, P < 0.001). Sensitivity map showed that the DLM focused on the QRS complex and T-wave.

Conclusion

The DLM demonstrated high performance for HFpEF detection using not only a 12-lead ECG but also 6- single-lead ECG. These results suggest that HFpEF can be screened using conventional ECG devices and diverse life-type ECG machines employing the DLM, thereby preventing disease progression.

Relationship between changes of electrocardiogram indexes in chronic heart failure with arrhythmia and serum PIIINP and BNP

Relationship between changes of electrocardiogram (ECG) indexes in chronic heart failure (CHF) with arrhythmia and serum type III procollagen amino-terminal peptide (PIIINP) and brain natriuretic peptide (BNP) were evaluated. From December 2017 to December 2018, 101 patients with heart failure (HF) were collected. Among them, 48 patients with HF and slow arrhythmia were in group A, and 53 cases of HF with non-slow arrhythmia were sin group B, including 33 males and 20 females. BNP was detected by chemiluminescence and PIIINP was detected by immunoassay. The changes of ECG indexes in the two groups, the correlation between serum PIIINP and BNP and NYHA classification of cardiac function, and the correlation between ECG indexes and PIIINP and BNP were detected. ROC curve analysis of BNP and PIIINP in the diagnosis of slow HF was carried out. Serum PIIINP and BNP in group A were significantly higher than those in group B (P<0.05). The levels of PIIINP and BNP in serum of NYHA patients with different cardiac functions, and those in serum of patients with class III were significantly higher than those of group II (P<0.05), while significantly lower than those of group IV (P<0.05). The heart rate and Q-T interval in group A were significantly higher than those in group B (P<0.05). The P-R interval and QES wave group in group A were significantly lower than those in group B (P<0.05). BNP had a positive correlation with Hr and G-T, and was negatively correlated with P-R and QRS; PIIINP was positively correlated with Hr and G-T, and had a negative correlation with P-R, QRS and BNP; PIIINP had positive correlation with NYHA; ECG indexes were correlated with BNP and PIIINP, and had diagnostic value for CHF. Using ECG indexes to predict BNP and PIIINP levels was conducive to the diagnosis of CHF.

Electrocardiographic characteristics in patients with heart failure and normal ejection fraction: A systematic review and meta-analysis

BACKGROUND

Little is known about ECG abnormalities in patients with heart failure and normal ejection fraction (HeFNEF) and how they relate to different etiologies or outcomes.

METHODS AND RESULTS

We searched the literature for peer-reviewed studies describing ECG abnormalities in HeFNEF other than heart rhythm alone. Thirty five studies were identified and 32,006 participants. ECG abnormalities reported in patients with HeFNEF include atrial fibrillation (prevalence 12%-46%), long PR interval (11%-20%), left ventricular hypertrophy (LVH, 10%-30%), pathological Q waves (11%-18%), RBBB (6%-16%), LBBB (0%-8%), and long JTc (3%-4%). Atrial fibrillation is more common in patients with HeFNEF compared to those with heart failure and reduced ejection fraction (HeFREF). In contrast, long PR interval, LVH, Q waves, LBBB, and long JTc are more common in patients with HeFREF. A pooled effect estimate analysis showed that QRS duration ≥120 ms, although uncommon (13%-19%), is associated with worse outcomes in patients with HeFNEF.

CONCLUSIONS

There is high variability in the prevalence of ECG abnormalities in patients with HeFNEF. Atrial fibrillation is more common in patients with HeFNEF compared to those with HeFREF. QRS duration ≥120 ms is associated with worse outcomes in patients with HeFNEF. Further studies are needed to address whether ECG abnormalities correlate with different phenotypes in HeFNEF.

Development and Validation of Deep-Learning Algorithm for Electrocardiography-Based Heart Failure Identification

BACKGROUND AND OBJECTIVES

Screening and early diagnosis for heart failure (HF) are critical. However, conventional screening diagnostic methods have limitations, and electrocardiography (ECG)-based HF identification may be helpful. This study aimed to develop and validate a deep-learning algorithm for ECG-based HF identification (DEHF).

METHODS

The study involved 2 hospitals and 55,163 ECGs of 22,765 patients who performed echocardiography within 4 weeks were study subjects. ECGs were divided into derivation and validation data. Demographic and ECG features were used as predictive variables. The primary endpoint was detection of HF with reduced ejection fraction (HFrEF; ejection fraction [EF]≤40%), and the secondary endpoint was HF with mid-range to reduced EF (≤50%). We developed the DEHF using derivation data and the algorithm representing the risk of HF between 0 and 1. We confirmed accuracy and compared logistic regression (LR) and random forest (RF) analyses using validation data.

RESULTS

The area under the receiver operating characteristic curves (AUROCs) of DEHF for identification of HFrEF were 0.843 (95% confidence interval, 0.840-0.845) and 0.889 (0.887-0.891) for internal and external validation, respectively, and these results significantly outperformed those of LR (0.800 [0.797-0.803], 0.847 [0.844-0.850]) and RF (0.807 [0.804-0.810], 0.853 [0.850-0.855]) analyses. The AUROCs of deep learning for identification of the secondary endpoint was 0.821 (0.819-0.823) and 0.850 (0.848-0.852) for internal and external validation, respectively, and these results significantly outperformed those of LR and RF.

CONCLUSIONS

The deep-learning algorithm accurately identified HF using ECG features and outperformed other machine-learning methods.