Deep neural networks learn by using human-selected electrocardiogram features and novel features

We sought to investigate whether artificial intelligence (AI) and specifically deep neural networks (NNs) for electrocardiogram (ECG) signal analysis can be explained using human-selected features. We also sought to quantify such explainability and test if the AI model learns features that are similar to a human expert.

We used a set of 100 000 ECGs that were annotated by human explainable features. We applied both linear and non-linear models to predict published ECG AI models output for the detection of patients’ age and sex. We further used canonical correlation analysis to quantify the amount of shared information between the NN features and human-selected features. We reconstructed single human-selected ECG features from the unexplained NN features using a simple linear model. We noticed a strong correlation between the simple models and the AI output ($R^2$ of 0.49–0.57 for the linear models and $R^2$ of 0.69–0.70 for the non-linear models). We found that the correlation of the human explainable features with either 13 of the strongest age AI features or 15 of the strongest sex AI features was above 0.85 (for comparison, the first 14 principal components explain 90% of the human feature variance). We linearly reconstructed single human-selected ECG features from the AI features with $R^2$ up to 0.86.

This work shows that NNs for ECG signals extract features in a similar manner to human experts and that they also generate additional novel features that help achieve superior performance.