Evidence-based framework for evaluating healthcare AI systems across 5 clinical dimensions
Each dimension represents a critical aspect of clinical practice, providing comprehensive coverage for AI evaluation
Clinical competencies based on CanMEDS and ACGME frameworks covering data gathering, reasoning, intervention, and communication.
Healthcare provider roles from attending physicians to allied health professionals with distinct characteristics and responsibilities.
Evidence-based disease prioritization using WHO DALY data, organized by ICD-11 classification with global burden metrics.
Disease progression states from healthy to terminal outcomes, with 26 possible transitions based on clinical pathophysiology.
Healthcare delivery locations from pre-hospital to workplace settings, each with limited or rich resource availability.
Explore individual dimensions, view hierarchical structures, and analyze relationships
Loading dimension data...
Select a dimension to view detailed information and hierarchical structure.
Statistical analysis and metrics will appear here.
Evidence base and citation information will be displayed here.
The Clinical Skill-Mix framework provides a comprehensive, evidence-based approach to evaluating healthcare AI systems across five critical dimensions of clinical practice.
All dimensions grounded in established clinical frameworks and real-world data
Multi-level organization supporting different depths of analysis
Standardized format enables cross-dimensional analysis and comparison