Chagas Disease Classification Dataset

This dataset consists of clinical case reports written in Spanish manually annotated with relevant labels in relation to the Chagas disease. Annotations were performed using the Prodigy annotation tool by domain clinical experts, resulting in a high-quality classification dataset suitable for supervised machine learning, clinical text mining, and biomedical NLP tasks. The dataset is presented in a csv format (chagas_classification_dataset.csv), containing 425 case reports with the clinical text and corresponding binary labels for each Chagas label, indicating whether the text diagnosis applies to the case. The classification labels are listed below: no chagas chagas discordante chagas agudo chagas crónico cardíaco chagas crónico digestivo chagas crónico mixto chagas crónico indeterminado reactivación de chagas crónico en paciente inmunodeprimido