Related Experiment Videos
A framework for evidence-adaptive quality assessment that unifies guideline-based and performance-indicator
Aneel Advani1, Mary Goldstein, Mark A Musen
1Section on Medical Informatics, Stanford School of Medicine, Stanford, CA, USA.
Proceedings. AMIA Symposium
|December 5, 2002
Summary
This study introduces an evidence-adaptive scoring algorithm for automated quality assessment in healthcare. It provides flexible scoring for clinical guidelines and performance indicators, accounting for practice variations and uncertainties.
Area of Science:
- Medical Informatics
- Health Services Research
- Clinical Quality Improvement
Background:
- Automated quality assessment is crucial for guideline-based medical care.
- Existing methods struggle with complex guidelines, practice variations, and uncertain data.
Purpose of the Study:
- To develop a unified model for evidence-adaptive quality assessment scoring.
- To consistently score adherence using complex guidelines and performance indicators.
- To provide robust scoring despite uncertainties in best practices and data.
Main Methods:
- Developed a unified model representation and algorithm for quality assessment.
- Utilized fuzzy measure-theoretic scoring to handle uncertainty and ambiguity.
- Applied the method to retrospective data from a hypertension care guideline project.
Main Results:
- The algorithm successfully scored adherence to quality measures.
- Demonstrated ability to provide best-case and worst-case scores considering variations.
- Validated the approach on real-world hypertension care data.
Conclusions:
- The proposed algorithm offers a flexible and robust solution for automated quality assessment.
- It effectively addresses uncertainties and variations inherent in clinical practice.
- This method can improve the quality of care through consistent and adaptive scoring.