Chagas Disease Clinical Case Clustering Dataset

This dataset contains annotated and semantically clustered Spanish clinical cases related to Chagas disease. It is intended to use this resource in biomedical natural language processing (NLP), clustering analysis, and clinical text mining research. The repository containd a csv file (chagas_clustering_dataset.csv), containing the following columns: Column Description filename Identifier of the case report file. labels List of NER entity types extracted from the case (e.g., ENFERMEDAD, SINTOMA, PROCEDIMIENTO). spans List text spans corresponding to the detected NER labels in the case. case_report Full clinical case report text (in Spanish). labels_kmeans Cluster label assigned to the case using KMeans clustering over entity-based semantic embeddings. x_pca, y_pca Principal Component Analysis (PCA) 2D projection coordinates of the case embedding for visualization. x_umap, y_umap UMAP 2D projection coordinates of the case embedding for visualization.