datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
hospitalizations_model_test
Datasets used to test hospitalization prediction models
Datasets used in testing the trained models presented in the paper "Predicting Hospitalization with LLMs from Health Insurance Data". We provide data in English and Portuguese.
All data here is anonymized and represents the patient's event history, ordered from left to right in a sentence format, with data on the left being oldest and data on the right being newest. Label values 0 indicate that the patient was not… See the full description on the dataset page: https://huggingface.co/datasets/efbaro/hospitalizations_model_test.model_test_slangmodel_test_stopwordsmodel_test_typosmodel_test_new