Atrial fibrillation risk prediction from the 12-lead electrocardiogram using digital biomarkers and deep representation learning

A roadmap for modelling radiation-induced cardiac disease

Cardiac risk mitigation is a major priority in improving outcomes for cancer survivors as advances in cancer screening and treatments continue to decrease cancer mortality. More than half of adult cancer patients will be treated with radiotherapy (RT); therefore it is crucial to develop a framework for how to assess and predict radiation-induced cardiac disease (RICD). Historically, RICD was modelled solely using whole heart metrics such as mean heart dose. However, data over the past decade has identified cardiac substructures which outperform whole heart metrics in predicting for significant cardiac events. Additionally, non-RT factors such as pre-existing cardiovascular risk factors and toxicity from other therapies contribute to risk of future cardiac events. In this review, we aim to discuss the current evidence and knowledge gaps in predicting RICD and provide a roadmap for the development of comprehensive models based on three interrelated components, (1) baseline CV risk assessment, (2) cardiac substructure radiation dosimetry linked with cardiac-specific outcomes and (3) novel biomarker development.

An artificial intelligence-enabled Holter algorithm to identify patients with ventricular tachycardia by analysing their electrocardiogram during sinus rhythm

Aims

Ventricular tachycardia (VT) is a dangerous cardiac arrhythmia that can lead to sudden cardiac death. Early detection and management of VT is thus of high clinical importance. We hypothesize that it is possible to identify patients with VT during sinus rhythm by leveraging a continuous 24 h Holter electrocardiogram and artificial intelligence.

Methods and results

We analysed a retrospective Holter data set from the Rambam Health Care Campus, Haifa, Israel, which included 1773 Holter recordings from 1570 non-VT patients and 52 recordings from 49 VT patients. Morphological and heart rate variability features were engineered from the raw electrocardiogram signal and fed, together with demographical features, to a data-driven model for the task of classifying a patient as either VT or non-VT. The model obtained an area under the receiving operative curve of 0.76 ± 0.07. Feature importance suggested that the proportion of premature ventricular beats and beat-to-beat interval variability was discriminative of VT, while demographic features were not.

Conclusion

This original study demonstrates the feasibility of VT identification from sinus rhythm in Holter.

Early warning of atrial fibrillation using deep learning

Atrial fibrillation (AF), the most prevalent cardiac rhythm disorder, significantly increases hospitalization and health risks. Reverting from AF to sinus rhythm (SR) often requires intensive interventions. This study presents a deep-learning model capable of predicting the transition from SR to AF on average 30.8 min before the onset appears, with an accuracy of 83% and an F1 score of 85% on the test data. This performance was obtained from R-to-R interval signals, which can be accessible from wearable technology. Our model, entitled Warning of Atrial Fibrillation (WARN), consists of a deep convolutional neural network trained and validated on 24-h Holter electrocardiogram data from 280 patients, with 70 additional patients used for testing and further evaluation on 33 patients from two external centers. The low computational cost of WARN makes it ideal for integration into wearable technology, allowing for continuous heart monitoring and early AF detection, which can potentially reduce emergency interventions and improve patient outcomes.

Application of artificial intelligence in the diagnosis and treatment of cardiac arrhythmia

The rapid growth in computational power, sensor technology, and wearable devices has provided a solid foundation for all aspects of cardiac arrhythmia care. Artificial intelligence (AI) has been instrumental in bringing about significant changes in the prevention, risk assessment, diagnosis, and treatment of arrhythmia. This review examines the current state of AI in the diagnosis and treatment of atrial fibrillation, supraventricular arrhythmia, ventricular arrhythmia, hereditary channelopathies, and cardiac pacing. Furthermore, ChatGPT, which has gained attention recently, is addressed in this paper along with its potential applications in the field of arrhythmia. Additionally, the accuracy of arrhythmia diagnosis can be improved by identifying electrode misplacement or erroneous swapping of electrode position using AI. Remote monitoring has expanded greatly due to the emergence of contactless monitoring technology as wearable devices continue to develop and flourish. Parallel advances in AI computing power, ChatGPT, availability of large data sets, and more have greatly expanded applications in arrhythmia diagnosis, risk assessment, and treatment. More precise algorithms based on big data, personalized risk assessment, telemedicine and mobile health, smart hardware and wearables, and the exploration of rare or complex types of arrhythmia are the future direction.

Artificial-intelligence-based risk prediction and mechanism discovery for atrial fibrillation using heart beat-to-beat intervals

BACKGROUND

Early diagnosis of atrial fibrillation (AF) is important for preventing stroke and other complications. Predicting AF risk in advance can improve early diagnostic efficiency. Deep learning has been used for disease risk prediction; however, it lacks adherence to evidence-based medicine standards. Identifying the underlying mechanisms behind disease risk prediction is important and required.

METHODS

We developed an explainable deep learning model called HBBI-AI to predict AF risk using only heart beat-to-beat intervals (HBBIs) during sinus rhythm. We proposed a possible AF mechanism based on the model's explainability and verified this conjecture using confirmed AF risk factors while also examining new AF risk factors. Finally, we investigated the changes in clinicians' ability to predict AF risk using only HBBIs before and after learning the model's explainability.

FINDINGS

HBBI-AI consistently performed well across large in-house and external public datasets. HBBIs with large changes or extreme stability were critical predictors for increased AF risk, and the underlying cause was autonomic imbalance. We verified various AF risk factors and discovered that autonomic imbalance was associated with all these factors. Finally, cardiologists effectively understood and learned from these findings to improve their abilities in AF risk prediction.

CONCLUSIONS

HBBI-AI effectively predicted AF risk using only HBBI information through evaluating autonomic imbalance. Autonomic imbalance may play an important role in many risk factors of AF rather than in a limited number of risk factors.

FUNDING

This study was supported in part by the National Key R&D Program and the National Natural Science Foundation of China.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

Prediction of atrial fibrillation from at-home single-lead ECG signals without arrhythmias

Early identification of atrial fibrillation (AF) can reduce the risk of stroke, heart failure, and other serious cardiovascular outcomes. However, paroxysmal AF may not be detected even after a two-week continuous monitoring period. We developed a model to quantify the risk of near-term AF in a two-week period, based on AF-free ECG intervals of up to 24 h from 459,889 patch-based ambulatory single-lead ECG (modified lead II) recordings of up to 14 days. A deep learning model was used to integrate ECG morphology data with demographic and heart rhythm features toward AF prediction. Observing a 1-day AF-free ECG recording, the model with deep learning features produced the most accurate prediction of near-term AF with an area under the curve AUC = 0.80 (95% confidence interval, CI = 0.79-0.81), significantly improving discrimination compared to demographic metrics alone (AUC 0.67; CI = 0.66-0.68). Our model was able to predict incident AF over a two-week time frame with high discrimination, based on AF-free single-lead ECG recordings of various lengths. Application of the model may enable a digital strategy for improving diagnostic capture of AF by risk stratifying individuals with AF-negative ambulatory monitoring for prolonged or recurrent monitoring, potentially leading to more rapid initiation of treatment.

End-to-end risk prediction of atrial fibrillation from the 12-Lead ECG by deep neural networks

BACKGROUND

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias that affects millions of people each year worldwide and it is closely linked to increased risk of cardiovas- cular diseases such as stroke and heart failure. Machine learning methods have shown promising results in evaluating the risk of developing atrial fibrillation from the electrocardiogram. We aim to develop and evaluate one such algorithm on a large CODE dataset collected in Brazil.

METHODS

We used the CODE cohort to develop and test a model for AF risk prediction for individual patients from the raw ECG recordings without the use of additional digital biomarkers. The cohort is a collection of ECG recordings and annotations by the Telehealth Network of Minas Gerais, in Brazil. A convolutional neural network based on a residual network architecture was implemented to produce class probabilities for the classification of AF. The probabilities were used to develop a Cox proportional hazards model and a Kaplan-Meier model to carry out survival analysis. Hence, our model is able to perform risk prediction for the development of AF in patients without the condition.

RESULTS

The deep neural network model identified patients without indication of AF in the presented ECG but who will develop AF in the future with an AUC score of 0.845. From our survival model, we obtain that patients in the high-risk group (i.e. with the probability of a future AF case being >0.7) are 50% more likely to develop AF within 40 weeks, while patients belonging to the minimal-risk group (i.e. with the probability of a future AF case being less than or equal to 0.1) have >85% chance of remaining AF free up until after seven years.

CONCLUSION

We developed and validated a model for AF risk prediction. If applied in clinical practice, the model possesses the potential of providing valuable and useful information in decision- making and patient management processes.

Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm: External Validation of the AI Approach

BACKGROUND

Atrial fibrillation (AF) may occur asymptomatically and can be diagnosed only with electrocardiography (ECG) while the arrhythmia is present.

OBJECTIVES

The aim of this study was to independently validate the approach of using artificial intelligence (AI) to identify underlying paroxysmal AF from a 12-lead ECG in sinus rhythm (SR).

METHODS

An AI algorithm was trained to identify patients with underlying paroxysmal AF, using electrocardiographic data from all in- and outpatients from a single center with at least 1 ECG in SR. For patients without AF, all ECGs in SR were included. For patients with AF, all ECGs in SR starting 31 days before the first AF event were included. The patients were randomly allocated to training, internal validation, and testing datasets in a 7:1:2 ratio. In a secondary analysis, the AF prevalence of the testing group was modified. Additionally, the performance of the algorithm was validated at an external hospital.

RESULTS

The dataset consisted of 494,042 ECGs in SR from 142,310 patients. Testing the model on the first ECG of each patient (AF prevalence 9.0%) resulted in accuracy of 78.1% (95% CI: 77.6%-78.5%), area under the receiver-operating characteristic curve of 0.87 (95% CI: 0.86-0.87), and area under the precision recall curve (AUPRC) of 0.48 (95% CI: 0.46-0.50). In a low-risk group (AF prevalence 3%), the AUPRC decreased to 0.21 (95% CI: 0.18-0.24). In a high-risk group (AF prevalence 30%), the AUPRC increased to 0.76 (95% CI: 0.75-0.78). This performance was robust when validated in an external hospital.

CONCLUSIONS

The approach of using an AI-enabled electrocardiographic algorithm for the identification of patients with underlying paroxysmal AF from ECGs in SR was independently validated.

Comparison of discrimination and calibration performance of ECG-based machine learning models for prediction of new-onset atrial fibrillation

BACKGROUND

Machine learning (ML) methods to build prediction models starting from electrocardiogram (ECG) signals are an emerging research field. The aim of the present study is to investigate the performances of two ML approaches based on ECGs for the prediction of new-onset atrial fibrillation (AF), in terms of discrimination, calibration and sample size dependence.

METHODS

We trained two models to predict new-onset AF: a convolutional neural network (CNN), that takes as input the raw ECG signals, and an eXtreme Gradient Boosting model (XGB), that uses the signal's extracted features. A penalized logistic regression model (LR) was used as a benchmark. Discrimination was evaluated with the area under the ROC curve, while calibration with the integrated calibration index. We investigated the dependence of models' performances on the sample size and on class imbalance corrections introduced with random under-sampling.

RESULTS

CNN's discrimination was the most affected by the sample size, outperforming XGB and LR only around n = 10.000 observations. Calibration showed only a small dependence on the sample size for all the models considered. Balancing the training set with random undersampling did not improve discrimination in any of the models. Instead, the main effect of imbalance corrections was to worsen the models' calibration (for CNN, integrated calibration index from 0.014 [0.01, 0.018] to 0.17 [0.16, 0.19]). The sample size emerged as a fundamental point for developing the CNN model, especially in terms of discrimination (AUC = 0.75 [0.73, 0.77] when n = 10.000, AUC = 0.80 [0.79, 0.81] when n = 150.000). The effect of the sample size on the other two models was weaker. Imbalance corrections led to poorly calibrated models, for all the approaches considered, reducing the clinical utility of the models.

CONCLUSIONS

Our results suggest that the choice of approach in the analysis of ECG should be based on the amount of data available, preferring more standard models for small datasets. Moreover, imbalance correction methods should be avoided when developing clinical prediction models, where calibration is crucial.

Deep-learning-based prognostic modeling for incident heart failure in patients with diabetes using electronic health records: A retrospective cohort study

Patients with type 2 diabetes mellitus (T2DM) have more than twice the risk of developing heart failure (HF) compared to patients without diabetes. The present study is aimed to build an artificial intelligence (AI) prognostic model that takes in account a large and heterogeneous set of clinical factors and investigates the risk of developing HF in diabetic patients. We carried out an electronic health records- (EHR-) based retrospective cohort study that included patients with cardiological clinical evaluation and no previous diagnosis of HF. Information consists of features extracted from clinical and administrative data obtained as part of routine medical care. The primary endpoint was diagnosis of HF (during out-of-hospital clinical examination or hospitalization). We developed two prognostic models using (1) elastic net regularization for Cox proportional hazard model (COX) and (2) a deep neural network survival method (PHNN), in which a neural network was used to represent a non-linear hazard function and explainability strategies are applied to estimate the influence of predictors on the risk function. Over a median follow-up of 65 months, 17.3% of the 10,614 patients developed HF. The PHNN model outperformed COX both in terms of discrimination (c-index 0.768 vs 0.734) and calibration (2-year integrated calibration index 0.008 vs 0.018). The AI approach led to the identification of 20 predictors of different domains (age, body mass index, echocardiographic and electrocardiographic features, laboratory measurements, comorbidities, therapies) whose relationship with the predicted risk correspond to known trends in the clinical practice. Our results suggest that prognostic models for HF in diabetic patients may improve using EHRs in combination with AI techniques for survival analysis, which provide high flexibility and better performance with respect to standard approaches.

Image based deep learning in 12-lead ECG diagnosis

Background

The electrocardiogram is an integral tool in the diagnosis of cardiovascular disease. Most studies on machine learning classification of electrocardiogram (ECG) diagnoses focus on processing raw signal data rather than ECG images. This presents a challenge for models in many areas of clinical practice where ECGs are printed on paper or only digital images are accessible, especially in remote and regional settings. This study aims to evaluate the accuracy of image based deep learning algorithms on 12-lead ECG diagnosis.

Methods

Deep learning models using VGG architecture were trained on various 12-lead ECG datasets and evaluated for accuracy by testing on holdout test data as well as data from datasets not seen in training. Grad-CAM was utilized to depict heatmaps of diagnosis.

Results

The results demonstrated excellent AUROC, AUPRC, sensitivity and specificity on holdout test data from datasets used in training comparable to the best signal and image-based models. Detection of hidden characteristics such as gender were achieved at a high rate while Grad-CAM successfully highlight pertinent features on ECGs traditionally used by human interpreters.

Discussion

This study demonstrates feasibility of image based deep learning algorithms in ECG diagnosis and identifies directions for future research in order to develop clinically applicable image based deep-learning models in ECG diagnosis.

Statistical and Diagnostic Properties of pRRx Parameters in Atrial Fibrillation Detection

Background: We studied the diagnostic properties of the percentage of successive RR intervals differing by at least x ms (pRRx) as functions of the threshold value x in a range of 7 to 195 ms for the differentiation of atrial fibrillation (AF) from sinus rhythm (SR). Methods: RR intervals were measured in 60-s electrocardiogram (ECG) segments with either AF (32,141 segments) or SR (32,769 segments) from the publicly available Physionet Long-Term Atrial Fibrillation Database (LTAFDB). For validation, we have used ECGs from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT–BIH) Atrial Fibrillation Database. The pRRx distributions in AF and SR in relation to x were studied by histograms, along with the mutual association by the nonparametric Spearman correlations for all pairs of pRRx, and separately for AF or SR. The optimal cutoff values for all pRRx were determined using the receiver operator curve characteristic. A nonparametric bootstrap with 5000 samples was used to calculate a 95% confidence interval for several classification metrics. Results: The distributions of pRRx for x in the 7–195 ms range are significantly different in AF than in SR. The sensitivity, specificity, accuracy, and diagnostic odds ratios differ for pRRx, with the highest values for x = 31 ms (pRR31) rather than x = 50 (pRR50), which is most commonly applied in studies on heart rate variability. For the optimal cutoff of pRR31 (68.79%), the sensitivity is 90.42%, specificity 95.37%, and the diagnostic odds ratio is 194.11. Validation with the ECGs from the MIT–BIH Atrial Fibrillation Database confirmed our findings. Conclusions: We demonstrate that the diagnostic properties of pRRx depend on x, and pRR31 outperforms pRR50, at least for ECGs of 60-s duration.

Machine learning to support triage of children at risk for epileptic seizures in the pediatric intensive care unit

OBJECTIVE

Epileptic seizures are relatively common in critically-ill children admitted to the pediatric intensive care unit (PICU) and thus serve as an important target for identification and treatment. Most of these seizures have no discernible clinical manifestation but still have a significant impact on morbidity and mortality. Children that are deemed at risk for seizures within the PICU are monitored using continuous-electroencephalogram (cEEG). cEEG monitoring cost is considerable and as the number of available machines is always limited, clinicians need to resort to triaging patients according to perceived risk in order to allocate resources. This research aims to develop a computer aided tool to improve seizures risk assessment in critically-ill children, using an ubiquitously recorded signal in the PICU, namely the electrocardiogram (ECG).

APPROACH

A novel data-driven model was developed at a patient-level approach, based on features extracted from the first hour of ECG recording and the clinical data of the patient.

MAIN RESULTS

The most predictive features were the age of the patient, the brain injury as coma etiology and the QRS area. For patients without any prior clinical data, using one hour of ECG recording, the classification performance of the random forest classifier reached an area under the receiver operating characteristic curve (AUROC) score of 0.84. When combining ECG features with the patients clinical history, the AUROC reached 0.87.

SIGNIFICANCE

Taking a real clinical scenario, we estimated that our clinical decision support triage tool can improve the positive predictive value by more than 59% over the clinical standard.

Using Minimum Redundancy Maximum Relevance Algorithm to Select Minimal Sets of Heart Rate Variability Parameters for Atrial Fibrillation Detection

Heart rate is quite regular during sinus (normal) rhythm (SR) originating from the sinus node. In contrast, heart rate is usually irregular during atrial fibrillation (AF). Complete atrioventricular block with an escape rhythm, ventricular pacing, or ventricular tachycardia are the most common exceptions when heart rate may be regular in AF. Heart rate variability (HRV) is the variation in the duration of consecutive cardiac cycles (RR intervals). We investigated the utility of HRV parameters for automated detection of AF with machine learning (ML) classifiers. The minimum redundancy maximum relevance (MRMR) algorithm, one of the most effective algorithms for feature selection, helped select the HRV parameters (including five original), best suited for distinguishing AF from SR in a database of over 53,000 60 s separate electrocardiogram (ECG) segments cut from longer (up to 24 h) ECG recordings. HRV parameters entered the ML-based classifiers as features. Seven different, commonly used classifiers were trained with one to six HRV-based features with the highest scores resulting from the MRMR algorithm and tested using the 5-fold cross-validation and blindfold validation. The best ML classifier in the blindfold validation achieved an accuracy of 97.2% and diagnostic odds ratio of 1566. From all studied HRV features, the top three HRV parameters distinguishing AF from SR were: the percentage of successive RR intervals differing by at least 50 ms (pRR50), the ratio of standard deviations of points along and across the identity line of the Poincare plots, respectively (SD2/SD1), and coefficient of variation—standard deviation of RR intervals divided by their mean duration (CV). The proposed methodology and the presented results of the selection of HRV parameters have the potential to develop practical solutions and devices for automatic AF detection with minimal sets of simple HRV parameters. Using straightforward ML classifiers and the extremely small sets of simple HRV features, always with pRR50 included, the differentiation of AF from sinus rhythms in the 60 s ECGs is very effective.

Automated multilabel diagnosis on electrocardiographic images and signals

The application of artificial intelligence (AI) for automated diagnosis of electrocardiograms (ECGs) can improve care in remote settings but is limited by the reliance on infrequently available signal-based data. We report the development of a multilabel automated diagnosis model for electrocardiographic images, more suitable for broader use. A total of 2,228,236 12-lead ECGs signals from 811 municipalities in Brazil are transformed to ECG images in varying lead conformations to train a convolutional neural network (CNN) identifying 6 physician-defined clinical labels spanning rhythm and conduction disorders, and a hidden label for gender. The image-based model performs well on a distinct test set validated by at least two cardiologists (average AUROC 0.99, AUPRC 0.86), an external validation set of 21,785 ECGs from Germany (average AUROC 0.97, AUPRC 0.73), and printed ECGs, with performance superior to signal-based models, and learning clinically relevant cues based on Grad-CAM. The model allows the application of AI to ECGs across broad settings.

Artificial intelligence opportunities in cardio-oncology: Overview with spotlight on electrocardiography

Cardiovascular disease is a leading cause of death among cancer survivors, second only to cancer recurrence or development of new tumors. Cardio-oncology has therefore emerged as a relatively new specialty focused on prevention and management of cardiovascular consequences of cancer therapies. Yet challenges remain regarding precision and accuracy with predicting individuals at highest risk for cardiotoxicity. Barriers such as access to care also limit screening and early diagnosis to improve prognosis. Thus, developing innovative approaches for prediction and early detection of cardiovascular illness in this population is critical. In this review, we provide an overview of the present state of machine learning applications in cardio-oncology. We begin by outlining some factors that should be considered while utilizing machine learning algorithms. We then examine research in which machine learning has been applied to improve prediction of cardiac dysfunction in cancer survivors. We also highlight the use of artificial intelligence (AI) in conjunction with electrocardiogram (ECG) to predict cardiac malfunction and also atrial fibrillation (AF), and we discuss the potential role of wearables. Additionally, the article summarizes future prospects and critical takeaways for the application of machine learning in cardio-oncology. This study is the first in a series on artificial intelligence in cardio-oncology, and complements our manuscript on echocardiography and other forms of imaging relevant to cancer survivors cared for in cardiology clinical practice.