trajectory-awareness
clinical-trajectory-awareness-v0.1
What this dataset does
This dataset tests whether a model can distinguish current severity from future direction.
The task is not to identify which patient looks worse now.
The task is to identify whether the patient trajectory is moving toward stability or deterioration.
Core stability idea
A patient who looks severe may be improving.
A patient who looks mild may be deteriorating.
Trajectory awareness requires separating present-state severity from direction of… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-trajectory-awareness-v0.1.clinical-trajectory-awareness-v0.2
What this dataset does
This dataset tests whether a model can distinguish current severity from future direction.
The task is not to identify which patient looks worse now.
The task is to classify whether the patient trajectory is moving toward stability or deterioration.
What changed in v0.2
v0.2 adds counterfactual and adversarial cases.
Some high-severity patients are improving and should be classified as stable or improving.
Some low-severity patients are… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-trajectory-awareness-v0.2.