Provenance-based Trust Model for Assessing Data Quality during Clinical Decision Making

Data quality is a critical requirement for data-driven clinical decision making in modern healthcare. It is a key prerequisite to many clinical analytics applications, yet much of the research to date focuses on assessing data quality of electronic health records for secondary use. This paper proposes a trust model and provenance-based assessment method for considering data quality during clinical decision making at the point of care. The method uses fuzzy logic to infer data quality trust from a data user's trust preferences with respect to data producers, data production methods, verification of data items, and certification of data production methods. Implementation with an existing “SMART on FHIR” app in primary care demonstrates the feasibility of model and method. An extension to FHIR resources for data quality trust allows for platform interoperability across system contexts. We consider dual process theories in designing a user interface that supports data quality trust for clinical decisions in heuristic and systematic cognitive processing modes. Model and method are adaptable to other application domains that rely on data quality for decision making.