Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification

Clinical machine learning research and AI driven clinical decision support models rely on clinically accurate labels. Manually extracting these labels with the help of clinical specialists is often time-consuming and expensive. This study tests the feasibility of automatic span- and document-level diagnosis extraction from unstructured Dutch echocardiogram reports. We included 115,692 unstructured echocardiogram reports from the UMCU a large university hospital in the Netherlands. A randomly selected subset was manually annotated for the occurrence and severity of eleven commonly described cardiac characteristics. We developed and tested several automatic labelling techniques at both span and document levels, using weighted and macro F1-score, precision, and recall for performance evaluation. We compared the performance of span labelling against document labelling methods, which included both direct document classifiers and indirect document classifiers that rely on span classification results. The SpanCategorizer and MedRoBERTa$.$nl models outperformed all other span and document classifiers, respectively. The weighted F1-score varied between characteristics, ranging from 0.60 to 0.93 in SpanCategorizer and 0.96 to 0.98 in MedRoBERTa$.$nl. Direct document classification was superior to indirect document classification using span classifiers. SetFit achieved competitive document classification performance using only 10% of the training data. Utilizing a reduced label set yielded near-perfect document classification results. We recommend using our published SpanCategorizer and MedRoBERTa$.$nl models for span- and document-level diagnosis extraction from Dutch echocardiography reports. For settings with limited training data, SetFit may be a promising alternative for document classification.

Interpretable ECG classification via a query-based latent space traversal (qLST)

Electrocardiography (ECG) is an effective and non-invasive diagnostic tool that measures the electrical activity of the heart. Interpretation of ECG signals to detect various abnormalities is a challenging task that requires expertise. Recently, the use of deep neural networks for ECG classification to aid medical practitioners has become popular, but their black box nature hampers clinical implementation. Several saliency-based interpretability techniques have been proposed, but they only indicate the location of important features and not the actual features. We present a novel interpretability technique called qLST, a query-based latent space traversal technique that is able to provide explanations for any ECG classification model. With qLST, we train a neural network that learns to traverse in the latent space of a variational autoencoder trained on a large university hospital dataset with over 800,000 ECGs annotated for 28 diseases. We demonstrate through experiments that we can explain different black box classifiers by generating ECGs through these traversals.