European heart journal. Digital health最新文献

Aims: Aortic elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We assess qualitatively and quantitatively explainable methods to understand the decisions of a deep learning model for detecting aortic elongation using chest X-ray (CXR) images.

Methods and results: In this study, we evaluated the performance of deep learning models (DenseNet and EfficientNet) for detecting aortic elongation using transfer learning and fine-tuning techniques with CXR images as input. EfficientNet achieved higher accuracy (86.7% $\pm$ 2.1), precision (82.7% $\pm$ 2.7), specificity (89.4% $\pm$ 1.7), F1 score (82.5% $\pm$ 2.9), and area under the receiver operating characteristic (92.7% $\pm$ 0.6) but lower sensitivity (82.3% $\pm$ 3.2) compared with DenseNet. To gain insights into the decision-making process of these models, we employed gradient-weighted class activation mapping and local interpretable model-agnostic explanations explainability methods, which enabled us to identify the expected location of aortic elongation in CXR images. Additionally, we used the pixel-flipping method to quantitatively assess the model interpretations, providing valuable insights into model behaviour.

Conclusion: Our study presents a comprehensive strategy for analysing CXR images by integrating aortic elongation detection models with explainable artificial intelligence techniques. By enhancing the interpretability and understanding of the models' decisions, this approach holds promise for aiding clinicians in timely and accurate diagnosis, potentially improving patient outcomes in clinical practice.

[This corrects the article DOI: 10.1093/ehjdh/ztad010.].

Aims: Current deep learning algorithms for automatic ECG analysis have shown notable accuracy but are typically narrowly focused on singular diagnostic conditions. This exploratory study aims to investigate the capability of a single deep learning model to predict a diverse range of both cardiac and non-cardiac discharge diagnoses based on a single ECG collected in the emergency department.

Methods and results: In this study, we assess the performance of a model trained to predict a broad spectrum of diagnoses. We find that the model can reliably predict 253 ICD codes (81 cardiac and 172 non-cardiac) in the sense of exceeding an AUROC score of 0.8 in a statistically significant manner.

Conclusion: The model demonstrates proficiency in handling a wide array of cardiac and non-cardiac diagnostic scenarios, indicating its potential as a comprehensive screening tool for diverse medical encounters.

Aims: Mobile devices such as smartphones and watches can now record single-lead electrocardiograms (ECGs), making wearables a potential screening tool for cardiac and wellness monitoring outside of healthcare settings. Because friends and family often share their smart phones and devices, confirmation that a sample is from a given patient is important before it is added to the electronic health record.

Methods and results: We sought to determine whether the application of Siamese neural network would permit the diagnostic ECG sample to serve as both a medical test and biometric identifier. When using similarity scores to discriminate whether a pair of ECGs came from the same patient or different patients, inputs of single-lead and 12-lead medians produced an area under the curve of 0.94 and 0.97, respectively.

Conclusion: The similar performance of the single-lead and 12-lead configurations underscores the potential use of mobile devices to monitor cardiac health.

Aims: Recently, deep learning artificial intelligence (AI) models have been trained to detect cardiovascular conditions, including hypertrophic cardiomyopathy (HCM), from the 12-lead electrocardiogram (ECG). In this external validation study, we sought to assess the performance of an AI-ECG algorithm for detecting HCM in diverse international cohorts.

Methods and results: A convolutional neural network-based AI-ECG algorithm was developed previously in a single-centre North American HCM cohort (Mayo Clinic). This algorithm was applied to the raw 12-lead ECG data of patients with HCM and non-HCM controls from three external cohorts (Bern, Switzerland; Oxford, UK; and Seoul, South Korea). The algorithm's ability to distinguish HCM vs. non-HCM status from the ECG alone was examined. A total of 773 patients with HCM and 3867 non-HCM controls were included across three sites in the merged external validation cohort. The HCM study sample comprised 54.6% East Asian, 43.2% White, and 2.2% Black patients. Median AI-ECG probabilities of HCM were 85% for patients with HCM and 0.3% for controls (P < 0.001). Overall, the AI-ECG algorithm had an area under the receiver operating characteristic curve (AUC) of 0.922 [95% confidence interval (CI) 0.910-0.934], with diagnostic accuracy 86.9%, sensitivity 82.8%, and specificity 87.7% for HCM detection. In age- and sex-matched analysis (case-control ratio 1:2), the AUC was 0.921 (95% CI 0.909-0.934) with accuracy 88.5%, sensitivity 82.8%, and specificity 90.4%.

Conclusion: The AI-ECG algorithm determined HCM status from the 12-lead ECG with high accuracy in diverse international cohorts, providing evidence for external validity. The value of this algorithm in improving HCM detection in clinical practice and screening settings requires prospective evaluation.

Aims: Cardiovascular disease (CVD) is a leading cause of mortality, especially in developing countries. This study aimed to develop and validate a CVD risk prediction model, Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), for recurrent cardiovascular events using machine learning technique.

Methods and results: Three cohorts of Chinese patients with established CVD were included if they had used any of the public healthcare services provided by the Hong Kong Hospital Authority (HA) since 2004 and categorized by their geographical locations. The 10-year CVD outcome was a composite of diagnostic or procedure codes with specific International Classification of Diseases, Ninth Revision, Clinical Modification. Multivariate imputation with chained equations and XGBoost were applied for the model development. The comparison with Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention (TRS-2°P) and Secondary Manifestations of ARTerial disease (SMART2) used the validation cohorts with 1000 bootstrap replicates. A total of 48 799, 119 672 and 140 533 patients were included in the derivation and validation cohorts, respectively. A list of 125 risk variables were used to make predictions on CVD risk, of which 8 classes of CVD-related drugs were considered interactive covariates. Model performance in the derivation cohort showed satisfying discrimination and calibration with a C statistic of 0.69. Internal validation showed good discrimination and calibration performance with C statistic over 0.6. The P-CARDIAC also showed better performance than TRS-2°P and SMART2.

Conclusion: Compared with other risk scores, the P-CARDIAC enables to identify unique patterns of Chinese patients with established CVD. We anticipate that the P-CARDIAC can be applied in various settings to prevent recurrent CVD events, thus reducing the related healthcare burden.

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.

Aims: The accuracy of voice-assisted technologies, such as Amazon Alexa, to collect data in patients who are older or have heart failure (HF) is unknown. The aim of this study is to analyse the impact of increasing age and comorbid HF, when compared with younger participants and caregivers, and how these different subgroups classify their experience using a voice-assistant device, for screening purposes.

Methods and results: Subgroup analysis (HF vs. caregivers and younger vs. older participants) of the VOICE-COVID-II trial, a randomized controlled study where participants were assigned with subsequent crossover to receive a SARS-CoV2 screening questionnaire by Amazon Alexa or a healthcare personnel. Overall concordance between the two methods was compared using unweighted kappa scores and percentage of agreement. From the 52 participants included, the median age was 51 (34-65) years and 21 (40%) were HF patients. The HF subgroup showed a significantly lower percentage of agreement compared with caregivers (95% vs. 99%, P = 0.03), and both the HF and older subgroups tended to have lower unweighted kappa scores than their counterparts. In a post-screening survey, both the HF and older subgroups were less acquainted and found the voice-assistant device more difficult to use compared with caregivers and younger individuals.

Conclusion: This subgroup analysis highlights important differences in the performance of a voice-assistant-based technology in an older and comorbid HF population. Younger individuals and caregivers, serving as facilitators, have the potential to bridge the gap and enhance the integration of these technologies into clinical practice.

Study registration: ClinicalTrials.gov Identifier: NCT04508972.

Aims: European and American clinical guidelines for implantable cardioverter defibrillators are insufficiently accurate for ventricular arrhythmia (VA) risk stratification, leading to significant morbidity and mortality. Artificial intelligence offers a novel risk stratification lens through which VA capability can be determined from the electrocardiogram (ECG) in normal cardiac rhythm. The aim of this study was to develop and test a deep neural network for VA risk stratification using routinely collected ambulatory ECGs.

Methods and results: A multicentre case-control study was undertaken to assess VA-ResNet-50, our open source ResNet-50-based deep neural network. VA-ResNet-50 was designed to read pyramid samples of three-lead 24 h ambulatory ECGs to decide whether a heart is capable of VA based on the ECG alone. Consecutive adults with VA from East Midlands, UK, who had ambulatory ECGs as part of their NHS care between 2014 and 2022 were recruited and compared with all comer ambulatory electrograms without VA. Of 270 patients, 159 heterogeneous patients had a composite VA outcome. The mean time difference between the ECG and VA was 1.6 years (⅓ ambulatory ECG before VA). The deep neural network was able to classify ECGs for VA capability with an accuracy of 0.76 (95% confidence interval 0.66-0.87), F1 score of 0.79 (0.67-0.90), area under the receiver operator curve of 0.8 (0.67-0.91), and relative risk of 2.87 (1.41-5.81).

Conclusion: Ambulatory ECGs confer risk signals for VA risk stratification when analysed using VA-ResNet-50. Pyramid sampling from the ambulatory ECGs is hypothesized to capture autonomic activity. We encourage groups to build on this open-source model.

Question: Can artificial intelligence (AI) be used to predict whether a person is at risk of a lethal heart rhythm, based solely on an electrocardiogram (an electrical heart tracing)?

Findings: In a study of 270 adults (of which 159 had lethal arrhythmias), the AI was correct in 4 out of every 5 cases. If the AI said a person was at risk, the risk of lethal event was three times higher than normal adults.

Meaning: In this study, the AI performed better than current medical guidelines. The AI was able to accurately determine the risk of lethal arrhythmia from standard heart tracings for 80% of cases over a year away-a conceptual shift in what an AI model can see and predict. This method shows promise in better allocating implantable shock box pacemakers (implantable cardioverter defibrillators) that save lives.

Aims: ECG abnormalities are often the first signs of arrhythmogenic right ventricular cardiomyopathy (ARVC) and we hypothesized that an artificial intelligence (AI)-enhanced ECG could help identify patients with ARVC and serve as a valuable disease-detection tool.

Methods and results: We created a convolutional neural network to detect ARVC using a 12-lead ECG. All patients with ARVC who met the 2010 task force criteria and had disease-causative genetic variants were included. All case ECGs were randomly assigned in an 8:1:1 ratio into training, validation, and testing groups. The case ECGs were age- and sex-matched with control ECGs at our institution in a 1:100 ratio. Seventy-seven patients (51% male; mean age 47.2 ± 19.9), including 56 patients with PKP2, 7 with DSG2, 6 with DSC2, 6 with DSP, and 2 with JUP were included. The model was trained using 61 case ECGs and 5009 control ECGs; validated with 7 case ECGs and 678 control ECGs and tested in 22 case ECGs and 1256 control ECGs. The sensitivity, specificity, positive and negative predictive values of the model were 77.3, 62.9, 3.32, and 99.4%, respectively. The area under the curve for rhythm ECG and median beat ECG was 0.75 and 0.76, respectively.

Conclusion: Our study found that the model performed well in excluding ARVC and supports the concept that the AI ECG can serve as a biomarker for ARVC if a larger cohort were available for network training. A multicentre study including patients with ARVC from other centres would be the next step in refining, testing, and validating this algorithm.