Related Experiment Video
Updated: Feb 5, 2026

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Towards accurate and interpretable competency-based assessment: enhancing clinical competency assessment through
Sapir Gershov1,2, Fadi Mahameed3,4, Aeyal Raz3,5
1Technion Autonomous Systems Program, Technion - Israel Institute of Technology, Haifa, Israel.
Artificial Intelligence (AI) offers objective competency assessments in medical education. A new AI framework using video, audio, and monitor data accurately evaluates anesthesia residents, improving training fairness and reliability.
Area of Science:
- Medical Education Technology
- Artificial Intelligence in Healthcare
- Simulation-Based Training
Background:
- Current medical competency assessments are subjective and resource-intensive.
- There is a need for objective, reliable, and transparent evaluation methods in medical training.
- Artificial Intelligence (AI) presents a potential solution to these challenges.
Purpose of the Study:
- To introduce a multimodal AI framework for objective competency assessment in medical education.
- To quantify deviations from ideal performance benchmarks using an anomaly detection model.
- To provide interpretable feedback for simulation-based training.
Main Methods:
- Developed a multimodal AI framework integrating video, audio, and patient monitor data.
- Trained an anomaly detection model (MEMTO) on data from 90 anesthesia residents.
- Utilized SHAP analysis to identify key performance drivers.
Main Results:
- AI-derived competency scores strongly correlated with expert ratings (Spearman's ρ = 0.78, ICC = 0.75).
- The model demonstrated high ranking precision (Relative L2-distance = 0.12).
- SHAP analysis highlighted communication and eye contact as significant factors in performance variability.
Conclusions:
- The AI framework provides objective and interpretable competency assessments.
- This approach enhances fairness, reliability, and transparency in simulation-based medical education.
- The study offers evidence for integrating AI into scalable and equitable medical training evaluations.
Related Concept Videos
Angina III: Clinical Manifestations and Assessment
Assessment of the Mouth
Mouth Inspection
The inspection begins with visually examining the mouth for symmetry, color, and size.
Assessment of Respiration
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
Nursing Assessment
The nurse collects all aspects of the patient's health in the initial assessment, establishing priorities for ongoing focused assessments...
Self-Evaluation: Self-Enhancement and Self-Verification
Assessment of the Rectum and Anus
Rectal Inspection
Begin by inspecting the perianal and anal areas for color, texture, rashes,...

