Artificial intelligence and machine learning are poised to influence nearly every aspect of the human condition, and cardiology is not an exception to this trend. This paper provides a guide for clinicians on relevant aspects of artificial intelligence and machine learning, reviews selected applications of these methods in cardiology to date, and identifies how cardiovascular medicine could incorporate artificial intelligence in the future. In particular, the paper first reviews predictive modeling concepts relevant to cardiology such as feature selection and frequent pitfalls such as improper dichotomization. Second, it discusses common algorithms used in supervised learning and reviews selected applications in cardiology and related disciplines. Third, it describes the advent of deep learning and related methods collectively called unsupervised learning, provides contextual examples both in general medicine and in cardiovascular medicine, and then explains how these methods could be applied to enable precision cardiology and improve patient outcomes.

Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements such as step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist, where noise remains an unsolved problem. Here we develop DeepBeat, a multitask deep learning method to jointly assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation. The model is trained on approximately one million simulated unlabeled physiological signals and fine-tuned on a curated dataset of over 500 K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that, in comparison with a single-task model, our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of atrial fibrillation detection from a F1 score of 0.54 to 0.96. We also include in our evaluation a prospectively derived replication cohort of ambulatory participants where the algorithm performed with high sensitivity (0.98), specificity (0.99), and F1 score (0.93). We show that two-stage training can help address the unbalanced data problem common to biomedical applications, where large-scale well-annotated datasets are hard to generate due to the expense of manual annotation, data acquisition, and participant privacy.

Determining the etiology of left ventricular hypertrophy (LVH) can be challenging due to the similarity in (1) Aim: Determining the etiology of left ventricular hypertrophy (LVH) can be challenging due to the similarity in clinical presentation and cardiac morphological features of diverse causes of disease. In particular, distinguishing individuals with hypertrophic cardiomyopathy (HCM) from the much larger set of individuals with manifest or occult hypertension (HTN) is of major importance for family screening and the prevention of sudden death. We hypothesized that an artificial intelligence method based joint interpretation of 12 lead electrocardiograms and echocardiogram videos could augment physician interpretation. (2) Methods and Results: We chose not to train on proximate data labels such as physician over-reads of ECGs or echocardiograms but instead took advantage of electronic health record derived clinical blood pressure measurements and diagnostic consensus (often including molecular testing) among physicians in an HCM center of excellence. Using over 18,000 combined instances of electrocardiograms and echocardiograms from 2,728 patients, we developed LVH-Fusion. On held-out test data, LVH-Fusion achieved an F1-score of 0.71 in predicting HCM, and 0.96 in predicting HTN. In head-to-head comparison with human readers LVH-Fusion had higher sensitivity and specificity rates than its human counterparts. Finally, we use explainability techniques to investigate local and global features that positively and negatively impact LVH-Fusion prediction estimates providing confirmation from unsupervised analysis the diagnostic power of lateral T wave inversion on the ECG and proximal septal hypertrophy on the echocardiogram for HCM. (3) Conclusion: These results show that deep learning can provide effective physician augmentation in the face of a common diagnostic dilemma with far reaching implications for the prevention of sudden cardiac death.

Cardiovascular diseases (CVDs) are responsible for more deaths than any other cause, with coronary heart disease and stroke accounting for two-thirds of those deaths. Morbidity and mortality due to CVD are largely preventable, through either primary prevention of disease or secondary prevention of cardiac events. Monitoring cardiac status in healthy and diseased cardiovascular systems has the potential to dramatically reduce cardiac illness and injury. Smart technology in concert with mobile health platforms is creating an environment where timely prevention of and response to cardiac events are becoming a reality.

Determining the etiology of left ventricular hypertrophy (LVH) can be challenging due to the similarity in clinical presentation and cardiac morphological features of diverse causes of disease. In particular, distinguishing individuals with hypertrophic cardiomyopathy (HCM) from the much larger set of individuals with manifest or occult hypertension (HTN) is of major importance for family screening and the prevention of sudden death. We hypothesized that deep learning based joint interpretation of 12 lead electrocardiograms and echocardiogram videos could augment physician interpretation. We chose not to train on proximate data labels such as physician over-reads of ECGs or echocardiograms but instead took advantage of electronic health record derived clinical blood pressure measurements and diagnostic consensus (often including molecular testing) among physicians in an HCM center of excellence. Using over 18,000 combined instances of electrocardiograms and echocardiograms from 2,728 patients, we developed LVH-Fusion. On held-out test data, LVH-Fusion achieved an F1-score of 0.71 in predicting HCM, and 0.96 in predicting HTN. In head-to-head comparison with human readers LVH-Fusion had higher sensitivity and specificity rates than its human counterparts. Finally, we use explainability techniques to investigate local and global features that positively and negatively impact LVH-Fusion prediction estimates providing confirmation from unsupervised analysis the diagnostic power of lateral T wave inversion on the ECG and proximal septal hypertrophy on the echocardiogram for HCM. In conclusion, these results show that deep learning can provide effective physician augmentation in the face of a common diagnostic dilemma with far reaching implications for the prevention of sudden cardiac death.