Neural networks applied to 12-lead electrocardiograms predict body mass index, visceral adiposity and concurrent cardiometabolic ill-health

Artificial intelligence-enhanced electrocardiography derived body mass index as a predictor of future cardiometabolic disease

The electrocardiogram (ECG) can capture obesity-related cardiac changes. Artificial intelligence-enhanced ECG (AI-ECG) can identify subclinical disease. We trained an AI-ECG model to predict body mass index (BMI) from the ECG alone. Developed from 512,950 12-lead ECGs from the Beth Israel Deaconess Medical Center (BIDMC), a secondary care cohort, and validated on UK Biobank (UKB) (n = 42,386), the model achieved a Pearson correlation coefficient (r) of 0.65 and 0.62, and an R2 of 0.43 and 0.39 in the BIDMC cohort and UK Biobank, respectively for AI-ECG BMI vs. measured BMI. We found delta-BMI, the difference between measured BMI and AI-ECG-predicted BMI (AI-ECG-BMI), to be a biomarker of cardiometabolic health. The top tertile of delta-BMI showed increased risk of future cardiometabolic disease (BIDMC: HR 1.15, p < 0.001; UKB: HR 1.58, p < 0.001) and diabetes mellitus (BIDMC: HR 1.25, p < 0.001; UKB: HR 2.28, p < 0.001) after adjusting for covariates including measured BMI. Significant enhancements in model fit, reclassification and improvements in discriminatory power were observed with the inclusion of delta-BMI in both cohorts. Phenotypic profiling highlighted associations between delta-BMI and cardiometabolic diseases, anthropometric measures of truncal obesity, and pericardial fat mass. Metabolic and proteomic profiling associates delta-BMI positively with valine, lipids in small HDL, syntaxin-3, and carnosine dipeptidase 1, and inversely with glutamine, glycine, colipase, and adiponectin. A genome-wide association study revealed associations with regulators of cardiovascular/metabolic traits, including SCN10A, SCN5A, EXOG and RXRG. In summary, our AI-ECG-BMI model accurately predicts BMI and introduces delta-BMI as a non-invasive biomarker for cardiometabolic risk stratification.

Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Previous studies have successfully predicted overweight status by applying deep learning to 12-lead electrocardiogram (ECG); however, models for predicting underweight status remain unexplored. Here, we assessed the feasibility of deep learning in predicting extremely low body weight using 12-lead ECGs, thereby investigating the prediction rationale for highlighting the parts of ECGs that are associated with extremely low body weight. Using records of inpatients predominantly with anorexia nervosa, we trained a convolutional neural network (CNN) that inputs a 12-lead ECG and outputs a binary prediction of whether body mass index is ≤ 12.6 kg/m2. This threshold was identified in a previous study as the optimal cutoff point for predicting the onset of refeeding syndrome. The CNN model achieved an area under the receiver operating characteristic curve of 0.807 (95% confidence interval, 0.745-0.869) on the test dataset. The gradient-weighted class activation map showed that the model focused on QRS waves. A negative correlation with the prediction scores was observed for QRS voltage. These results suggest that deep learning is feasible for predicting extremely low body weight using 12-lead ECGs, and several ECG features, such as lower QRS voltage, may be associated with extremely low body weight in patients with anorexia nervosa.

Genetic Susceptibility to Atrial Fibrillation Identified via Deep Learning of 12-Lead Electrocardiograms

BACKGROUND

Artificial intelligence (AI) models applied to 12-lead ECG waveforms can predict atrial fibrillation (AF), a heritable and morbid arrhythmia. However, the factors forming the basis of risk predictions from AI models are usually not well understood. We hypothesized that there might be a genetic basis for an AI algorithm for predicting the 5-year risk of new-onset AF using 12-lead ECGs (ECG-AI)-based risk estimates.

METHODS

We applied a validated ECG-AI model for predicting incident AF to ECGs from 39 986 UK Biobank participants without AF. We then performed a genome-wide association study (GWAS) of the predicted AF risk and compared it with an AF GWAS and a GWAS of risk estimates from a clinical variable model.

RESULTS

In the ECG-AI GWAS, we identified 3 signals (P<5×10-8) at established AF susceptibility loci marked by the sarcomeric gene TTN and sodium channel genes SCN5A and SCN10A. We also identified 2 novel loci near the genes VGLL2 and EXT1. In contrast, the clinical variable model prediction GWAS indicated a different genetic profile. In genetic correlation analysis, the prediction from the ECG-AI model was estimated to have a higher correlation with AF than that from the clinical variable model.

CONCLUSIONS

Predicted AF risk from an ECG-AI model is influenced by genetic variation implicating sarcomeric, ion channel and body height pathways. ECG-AI models may identify individuals at risk for disease via specific biological pathways.

Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022;3:405-414. [PMID: 36712163 PMCID: PMC9708023 DOI: 10.1093/ehjdh/ztac042]

Aims

Accurately determining atrial arrhythmia mechanisms from a 12-lead electrocardiogram (ECG) can be challenging. Given the high success rate of cavotricuspid isthmus (CTI) ablation, identification of CTI-dependent typical atrial flutter (AFL) is important for treatment decisions and procedure planning. We sought to train a convolutional neural network (CNN) to classify CTI-dependent AFL vs. non-CTI dependent atrial tachycardia (AT), using data from the invasive electrophysiology (EP) study as the gold standard.

Methods and results

We trained a CNN on data from 231 patients undergoing EP studies for atrial tachyarrhythmia. A total of 13 500 five-second 12-lead ECG segments were used for training. Each case was labelled CTI-dependent AFL or non-CTI-dependent AT based on the findings of the EP study. The model performance was evaluated against a test set of 57 patients. A survey of electrophysiologists in Europe was undertaken on the same 57 ECGs. The model had an accuracy of 86% (95% CI 0.77-0.95) compared to median expert electrophysiologist accuracy of 79% (range 70-84%). In the two thirds of test set cases (38/57) where both the model and electrophysiologist consensus were in agreement, the prediction accuracy was 100%. Saliency mapping demonstrated atrial activation was the most important segment of the ECG for determining model output.

Conclusion

We describe the first CNN trained to differentiate CTI-dependent AFL from other AT using the ECG. Our model matched and complemented expert electrophysiologist performance. Automated artificial intelligence-enhanced ECG analysis could help guide treatment decisions and plan ablation procedures for patients with organized atrial arrhythmias.