datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
10K_MELD_Plus_v1.0
Synthetic MELD-Plus (10K Patients)
Watch a demo
This dataset contains 10,000 synthetic patients inspired by the published MELD-Plus study (a collboration between Massachusetts General Hospital and IBM Research). Each row corresponds to a single admission, with demographics, labs, comorbidities, medications, derived scores (MELD, MELD-Na, MELD-Plus), and the binary outcome Death_Within_90_Days.
All data are artificially generated and contain no identifiable patient records.… See the full description on the dataset page: https://huggingface.co/datasets/DBbun/10K_MELD_Plus_v1.0.1M_MELD_Plus_v1.0
Synthetic MELD-Plus (1M Patients)
This dataset contains 1,000,000 synthetic patients inspired by the published MELD-Plus study (a collboration between Massachusetts General Hospital and IBM Research). Each row corresponds to a single admission, with demographics, labs, comorbidities, medications, derived scores (MELD, MELD-Na, MELD-Plus), and the binary outcome Death_Within_90_Days.
All data are artificially generated and contain no identifiable patient records.… See the full description on the dataset page: https://huggingface.co/datasets/DBbun/1M_MELD_Plus_v1.0.100K_MELD_Plus_v1.0
Synthetic MELD-Plus (100K Patients)
Watch a demo
This dataset contains 100,000 synthetic patients inspired by the published MELD-Plus study (a collboration between Massachusetts General Hospital and IBM Research). Each row corresponds to a single admission, with demographics, labs, comorbidities, medications, derived scores (MELD, MELD-Na, MELD-Plus), and the binary outcome Death_Within_90_Days.
All data are artificially generated and contain no identifiable patient records.… See the full description on the dataset page: https://huggingface.co/datasets/DBbun/100K_MELD_Plus_v1.0.