Deep Learning Models for Predicting Left Heart Abnormalities From Single-Lead Electrocardiogram for the Development of Wearable Devices.

BACKGROUND: Left heart abnormalities are risk factors for heart failure. However, echocardiography is not always available. Electrocardiograms (ECGs), which are now available from wearable devices, have the potential to detect these abnormalities. Nevertheless, whether a model can detect left heart abnormalities from single Lead I ECG data remains unclear.Methods and Results: We developed Lead I ECG models to detect low ejection fraction (EF), wall motion abnormality, left ventricular hypertrophy (LVH), left ventricular dilatation, and left atrial dilatation. We used a dataset comprising 229,439 paired sets of ECG and echocardiography data from 8 facilities, and validated the model using external verification with data from 2 facilities. The area under the receiver operating characteristic curves of our model was 0.913 for low EF, 0.832 for wall motion abnormality, 0.797 for LVH, 0.838 for left ventricular dilatation, and 0.802 for left atrial dilatation. In interpretation tests with 12 cardiologists, the accuracy of the model was 78.3% for low EF and 68.3% for LVH. Compared with cardiologists who read the 12-lead ECGs, the model's performance was superior for LVH and similar for low EF. CONCLUSIONS: From a multicenter study dataset, we developed models to predict left heart abnormalities using Lead I on the ECG. The Lead I ECG models show superior or equivalent performance to cardiologists using 12-lead ECGs.

An explainable artificial intelligence-enabled electrocardiogram analysis model for the classification of reduced left ventricular function.

Aims: The black box nature of artificial intelligence (AI) hinders the development of interpretable AI models that are applicable in clinical practice. We aimed to develop an AI model for classifying patients of reduced left ventricular ejection fraction (LVEF) from 12-lead electrocardiograms (ECG) with the decision-interpretability. Methods and results: We acquired paired ECG and echocardiography datasets from the central and co-operative institutions. For the central institution dataset, a random forest model was trained to identify patients with reduced LVEF among 29 907 ECGs. Shapley additive explanations were applied to 7196 ECGs. To extract the model's decision criteria, the calculated Shapley additive explanations values were clustered for 192 non-paced rhythm patients in which reduced LVEF was predicted. Although the extracted criteria were different for each cluster, these criteria generally comprised a combination of six ECG findings: negative T-wave inversion in I/V5-6 leads, low voltage in I/II/V4-6 leads, Q wave in V3-6 leads, ventricular activation time prolongation in I/V5-6 leads, S-wave prolongation in V2-3 leads, and corrected QT interval prolongation. Similarly, for the co-operative institution dataset, the extracted criteria comprised a combination of the same six ECG findings. Furthermore, the accuracy of seven cardiologists' ECG readings improved significantly after watching a video explaining the interpretation of these criteria (before, 62.9% ± 3.9% vs. after, 73.9% ± 2.4%; P = 0.02). Conclusion: We visually interpreted the model's decision criteria to evaluate its validity, thereby developing a model that provided the decision-interpretability required for clinical application.

Deep learning-based age estimation from chest X-rays indicates cardiovascular prognosis.

BACKGROUND: In recent years, there has been considerable research on the use of artificial intelligence to estimate age and disease status from medical images. However, age estimation from chest X-ray (CXR) images has not been well studied and the clinical significance of estimated age has not been fully determined. METHODS: To address this, we trained a deep neural network (DNN) model using more than 100,000 CXRs to estimate the patients' age solely from CXRs. We applied our DNN to CXRs of 1562 consecutive hospitalized heart failure patients, and 3586 patients admitted to the intensive care unit with cardiovascular disease. RESULTS: The DNN's estimated age (X-ray age) showed a strong significant correlation with chronological age on the hold-out test data and independent test data. Elevated X-ray age is associated with worse clinical outcomes (heart failure readmission and all-cause death) for heart failure. Additionally, elevated X-ray age was associated with a worse prognosis in 3586 patients admitted to the intensive care unit with cardiovascular disease. CONCLUSIONS: Our results suggest that X-ray age can serve as a useful indicator of cardiovascular abnormalities, which will help clinicians to predict, prevent and manage cardiovascular diseases.

Chest X-ray is one of the most widely used medical imaging tests worldwide to diagnose and manage heart and lung diseases. In this study, we developed a computer-based tool to predict patients' age from chest X-rays. The tool precisely estimated patients' age from chest X-rays. Furthermore, in patients with heart failure and those admitted to the intensive care unit for cardiovascular disease, elevated X-ray age estimated by our tool was associated with poor clinical outcomes, including readmission for heart failure or death from any cause. With further testing, our tool may help clinicians to predict outcomes in patients with heart disease based on a simple chest X-ray.

Age prediction from coronary angiography using a deep neural network: Age as a potential label to extract prognosis-related imaging features.

Coronary angiography (CAG) is still considered the reference standard for coronary artery assessment, especially in the treatment of acute coronary syndrome (ACS). Although aging causes changes in coronary arteries, the age-related imaging features on CAG and their prognostic relevance have not been fully characterized. We hypothesized that a deep neural network (DNN) model could be trained to estimate vascular age only using CAG and that this age prediction from CAG could show significant associations with clinical outcomes of ACS. A DNN was trained to estimate vascular age using ten separate frames from each of 5,923 CAG videos from 572 patients. It was then tested on 1,437 CAG videos from 144 patients. Subsequently, 298 ACS patients who underwent percutaneous coronary intervention (PCI) were analysed to assess whether predicted age by DNN was associated with clinical outcomes. Age predicted as a continuous variable showed mean absolute error of 4 years with R squared of 0.72 (r = 0.856). Among the ACS patients stratified by predicted age from CAG images before PCI, major adverse cardiovascular events (MACE) were more frequently observed in the older vascular age group than in the younger vascular age group (p = 0.017). Furthermore, after controlling for actual age, gender, peak creatine kinase, and history of heart failure, the older vascular age group independently suffered from more MACE (hazard ratio 2.14, 95% CI 1.07 to 4.29, p = 0.032). The vascular age estimated based on CAG imaging by DNN showed high predictive value. The age predicted from CAG images by DNN could have significant associations with clinical outcomes in patients with ACS.

Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning.

Left ventricular dilatation (LVD) and left ventricular hypertrophy (LVH) are risk factors for heart failure, and their detection improves heart failure screening. This study aimed to investigate the ability of deep learning to detect LVD and LVH from a 12-lead electrocardiogram (ECG). Using ECG and echocardiographic data, we developed deep learning and machine learning models to detect LVD and LVH. We also examined conventional ECG criteria for the diagnosis of LVH. We calculated the area under the receiver operating characteristic (AUROC) curve, sensitivity, specificity, and accuracy of each model and compared the performance of the models. We analyzed data for 18,954 patients (mean age (standard deviation): 64.2 (16.5) years, men: 56.7%). For the detection of LVD, the value (95% confidence interval) of the AUROC was 0.810 (0.801-0.819) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods (P < 0.001). The AUROCs for the logistic regression and random forest methods (machine learning models) were 0.770 (0.761-0.779) and 0.757 (0.747-0.767), respectively. For the detection of LVH, the AUROC was 0.784 (0.777-0.791) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods and conventional ECG criteria (P < 0.001). The AUROCs for the logistic regression and random forest methods were 0.758 (0.751-0.765) and 0.716 (0.708-0.724), respectively. This study suggests that deep learning is a useful method to detect LVD and LVH from 12-lead ECGs.

Deep learning model to detect significant aortic regurgitation using electrocardiography.

BACKGROUND: Aortic regurgitation (AR) is a common heart disease, with a relatively high prevalence of 4.9% in the Framingham Heart Study. Because the prevalence increases with advancing age, an upward shift in the age distribution may increase the burden of AR. To provide an effective screening method for AR, we developed a deep learning-based artificial intelligence algorithm for the diagnosis of significant AR using electrocardiography (ECG). METHODS: Our dataset comprised 29,859 paired data of ECG and echocardiography, including 412 AR cases, from January 2015 to December 2019. This dataset was divided into training, validation, and test datasets. We developed a multi-input neural network model, which comprised a two-dimensional convolutional neural network (2D-CNN) using raw ECG data and a fully connected deep neural network (FC-DNN) using ECG features, and compared its performance with the performances of a 2D-CNN model and other machine learning models. In addition, we used gradient-weighted class activation mapping (Grad-CAM) to identify which parts of ECG waveforms had the most effect on algorithm decision making. RESULTS: The area under the receiver operating characteristic curve of the multi-input model (0.802; 95% CI, 0.762-0.837) was significantly greater than that of the 2D-CNN model alone (0.734; 95% CI, 0.679-0.783; p<0.001) and those of other machine learning models. Grad-CAM demonstrated that the multi-input model tended to focus on the QRS complex in leads I and aVL when detecting AR. CONCLUSIONS: The multi-input deep learning model using 12-lead ECG data could detect significant AR with modest predictive value.

Potential value of saline-induced Pd/Pa ratio in patients with coronary artery stenosis.

Background: Fractional flow reserve (FFR) is the current gold standard for identifying myocardial ischemia in individuals with coronary artery stenosis. However, FFR is not penetrated as much worldwide due to time consumption, costs associated with adenosine, FFR-related discomfort, and complications. Resting physiological indexes may be widely accepted alternatives to FFR, while the discrepancies with FFR were found in up to 20% of lesions. The saline-induced Pd/Pa ratio (SPR) is a new simplified option for evaluating coronary stenosis. However, the clinical implication of SPR remains unclear. Objectives: In the present study, we aimed to compare the accuracies of SPR and resting full-cycle ratio (RFR) and to investigate the incremental value of SPR in clinical practice. Methods: In this multicenter prospective study, 112 coronary lesions (105 patients) were evaluated by SPR, RFR, and FFR. Results: The overall median age was 71 years, and 84.8% were men. SPR was correlated more strongly with FFR than with RFR (r = 0.874 vs. 0.713, respectively; p < 0.001). Using FFR < 0.80 as the reference standard variable, the area under the receiver-operating characteristic (ROC) curve for SPR was superior to that of RFR (0.932 vs. 0.840, respectively; p = 0.009). Conclusion: Saline-induced Pd/Pa ratio predicted FFR more accurately than RFR. SPR could be an alternative method for evaluating coronary artery stenosis and further investigation including elucidation of the mechanism of SPR is needed (225 words).

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.

Automatic detection of vessel structure by deep learning using intravascular ultrasound images of the coronary arteries.

Intravascular ultrasound (IVUS) is a diagnostic modality used during percutaneous coronary intervention. However, specialist skills are required to interpret IVUS images. To address this issue, we developed a new artificial intelligence (AI) program that categorizes vessel components, including calcification and stents, seen in IVUS images of complex lesions. When developing our AI using U-Net, IVUS images were taken from patients with angina pectoris and were manually segmented into the following categories: lumen area, medial plus plaque area, calcification, and stent. To evaluate our AI's performance, we calculated the classification accuracy of vessel components in IVUS images of vessels with clinically significantly narrowed lumina (< 4 mm2) and those with severe calcification. Additionally, we assessed the correlation between lumen areas in manually-labeled ground truth images and those in AI-predicted images, the mean intersection over union (IoU) of a test set, and the recall score for detecting stent struts in each IVUS image in which a stent was present in the test set. Among 3738 labeled images, 323 were randomly selected for use as a test set. The remaining 3415 images were used for training. The classification accuracies for vessels with significantly narrowed lumina and those with severe calcification were 0.97 and 0.98, respectively. Additionally, there was a significant correlation in the lumen area between the ground truth images and the predicted images (ρ = 0.97, R2 = 0.97, p < 0.001). However, the mean IoU of the test set was 0.66 and the recall score for detecting stent struts was 0.64. Our AI program accurately classified vessels requiring treatment and vessel components, except for stents in IVUS images of complex lesions. AI may be a powerful tool for assisting in the interpretation of IVUS imaging and could promote the popularization of IVUS-guided percutaneous coronary intervention in a clinical setting.

Deep Learning Algorithm to Detect Cardiac Sarcoidosis From Echocardiographic Movies.

BACKGROUND: Because the early diagnosis of subclinical cardiac sarcoidosis (CS) remains difficult, we developed a deep learning algorithm to distinguish CS patients from healthy subjects using echocardiographic movies.Methods and Results:Among the patients who underwent echocardiography from January 2015 to December 2019, we chose 151 echocardiographic movies from 50 CS patients and 151 from 149 healthy subjects. We trained two 3D convolutional neural networks (3D-CNN) to identify CS patients using a dataset of 212 echocardiographic movies with and without a transfer learning method (Pretrained algorithm and Non-pretrained algorithm). On an independent set of 41 echocardiographic movies, the area under the receiver-operating characteristic curve (AUC) of the Pretrained algorithm was greater than that of Non-pretrained algorithm (0.842, 95% confidence interval (CI): 0.722-0.962 vs. 0.724, 95% CI: 0.566-0.882, P=0.253). The AUC from the interpretation of the same set of 41 echocardiographic movies by 5 cardiologists was not significantly different from that of the Pretrained algorithm (0.855, 95% CI: 0.735-0.975 vs. 0.842, 95% CI: 0.722-0.962, P=0.885). A sensitivity map demonstrated that the Pretrained algorithm focused on the area of the mitral valve. CONCLUSIONS: A 3D-CNN with a transfer learning method may be a promising tool for detecting CS using an echocardiographic movie.

Empagliflozin attenuates neointimal hyperplasia after drug-eluting-stent implantation in patients with type 2 diabetes.

The effects of empagliflozin, a sodium-glucose co-transporter 2 inhibitor, on neointimal response after drug-eluting-stent (DES) implantation remains unknown. Insufficiently controlled diabetes patients with coronary artery disease planned for DES stenting were consecutively enrolled. The patients were assigned to receive empagliflozin in addition to standard therapy or intensive therapy using other glucose-lowering drugs (oGLD). The primary endpoint was thickness of neointimal hyperplasia (NIH) 12 months after stenting assessed by optical coherence tomography (OCT). A total of 28 patients were analyzed (n = 15 in the empagliflozin group, n = 13 in the oGLD group). The levels of glucose profile were not significantly different between both groups at follow-up [HbA1c; 7.2 ± 0.8 vs 7.3 ± 0.9%, p = 0.46]. In OCT analysis, neointima was significantly less in the empagliflozin group than the oGLD group [mean NIH thickness: 137 ± 32 vs 168 ± 39 µm, p = 0.02]. Changes of systolic and diastolic blood pressure (BP), changes of body mass index, and changes of hematocrit after additional treatment were significantly associated with NIH attenuation, whereas no correlation was observed in changes in blood glucose parameters. Multivariate logistic regression analysis revealed that changes in systolic BP was the strongest predictor for NIH attenuation, followed by changes in diastolic BP. In patients with type 2 diabetes, standard plus empagliflozin attenuated neointimal progression as compared with intensive standard therapy after DES implantation. Our data possibly support a beneficial effect of empagliflozin in type 2 diabetes required for coronary revascularization therapy.