Key result
Deep neural network-based sex misclassification on normal ECGs was associated with a 1.4 times higher risk of all-cause mortality compared to correctly classified peers.
Why the study?
Deep neural networks accurately predict sex from electrocardiograms, and it was hypothesized that ECG-based sex misclassification predicts mortality.
Does ECG-based sex misclassification by deep neural networks predict all-cause mortality in individuals with otherwise normal ECGs?
Cohort (n=144,760)
Yes
Does ECG-based sex misclassification by deep neural networks predict all-cause mortality in individuals with otherwise normal ECGs?
Effect estimate: HR 1.38 for males; HR 1.37 for females (95% CI 1.28-1.49 for males; 1.19-1.57 for females)
Absolute Event Rate: 17.2% vs 12.3%
AI-based misclassification of biological sex on a standard normal ECG serves as a novel biomarker for increased all-cause mortality, revealing unappreciated prognostic features such as short QRS duration.
Aims: Incorporation of sex in study design can lead to discoveries in medical research. Deep neural networks (DNNs) accurately predict sex based on the electrocardiogram (ECG) and we hypothesized that misclassification of sex is an important predictor for mortality. Therefore, we first developed and validated a DNN that classified sex based on the ECG and investigated the outcome. Second, we studied ECG drivers of DNN-classified sex and mortality. Methods and results: A DNN was trained to classify sex based on 131 673 normal ECGs. The algorithm was validated on internal (68 500 ECGs) and external data sets (3303 and 4457 ECGs). The survival of sex (mis)classified groups was investigated using time-to-event analysis and sex-stratified mediation analysis of ECG features. The DNN successfully distinguished female from male ECGs {internal validation: area under the curve (AUC) 0.96 [95% confidence interval (CI): 0.96, 0.97]; external validations: AUC 0.89 (95% CI: 0.88, 0.90), 0.94 (95% CI: 0.93, 0.94)}. Sex-misclassified individuals (11%) had a 1.4 times higher mortality risk compared with correctly classified peers. The ventricular rate was the strongest mediating ECG variable (41%, 95% CI: 31%, 56%) in males, while the maximum amplitude of the ST segment was strongest in females (18%, 95% CI: 11%, 39%). Short QRS duration was associated with higher mortality risk. Conclusion: Deep neural networks accurately classify sex based on ECGs. While the proportion of ECG-based sex misclassifications is low, it is an interesting biomarker. Investigation of the causal pathway between misclassification and mortality uncovered new ECG features that might be associated with mortality. Increased emphasis on sex as a biological variable in artificial intelligence is warranted.
No takes yet. Share an insight, caveat, or question.
Siegersma et al. (2022) conducted a cohort in Normal ECG (n=144,760). Sex misclassification by deep neural network based on ECG vs. Correct biological sex classification by the deep neural network was evaluated on All-cause mortality (HR 1.38 for males; HR 1.37 for females, 95% CI 1.28-1.49 for males; 1.19-1.57 for females). Deep neural network-based sex misclassification on normal ECGs was associated with a 1.4 times higher risk of all-cause mortality compared to correctly classified peers.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: