Evaluate whether models can verify pediatric inpatient medication orders against explicit rules and identify violations or missing information.

Evaluate whether models can detect contradictions between clinical findings and diagnoses in retinal, macular, and vitreous records.

Test whether models can verify decision-specific capacity assessments against the evidence and identify important gaps and conflicts.

Evaluate whether models identify and follow safety escalation requirements in virtual care using structured cases and rule-based evidence.

Evaluate how well models identify ordering errors, dependencies, and operational conflicts in neurosurgical workflows using reference violation labels.

Evaluate pediatric amblyopia plans against case-specific requirements with structured checks for consistency, constraint violations, and follow-up adequacy.

Evaluate whether models can detect conflicts, duplicates, and incompatible arrangements across orders in pediatric inpatient care plans.

This dataset is an effective tool for enhancing the analysis of physical activity behaviors and rehabilitation outcomes in the medical and health field.

The key information extraction dataset for doctor-patient conversations is used to enhance the information extraction capability of medical dialogue systems.

Evaluate withdrawal level-of-care recommendations against case-specific constraints and test reasoning in addiction psychiatry.

Evaluate prescription safety review with structured pediatric dental cases and labeled medication constraint violations.

Evaluate whether models recognize unsafe triage and dangerous dispositions in pediatric otolaryngology emergencies.

The operating room instrument recognition dataset is used to improve the efficiency of instrument automatic identification and management in a medical environment.

The ICU Equipment Interface Image Recognition Dataset is used to enhance the accuracy of medical equipment interface recognition.

The blood collection nurse operation process video dataset aids in posture and hand trajectory analysis in the healthcare field.

Evaluate whether models can handle psychiatric medication risks in psychotherapy dialogues without overstepping prescribing boundaries and can recommend appropriate professional support.

This dataset captures the hand instrument operations and trajectories of dentists during dental surgery.

Evaluate a model's ability to detect conflicts in structured rhinology cases with reference consistency labels and contradiction annotations.

Evaluate whether models can detect sequencing, dependency, and prerequisite issues in dental treatment plans.

Train models to reason through vaccine trial eligibility rules and explain each decision against the protocol.