The Division of Clinical Data Analytics and Decision Support (CDADS) provides timely, targeted, meaningful data analytics and clinical decision support systems (CDSS) for the purposes of research, clinical care and quality improvement at the University of Arizona College of Medicine – Phoenix and associated institutions. CDSS use innovative, algorithm-based software incorporated into electronic medical records (EMRs) to manage the massive amounts of medical data and incorporate scientific evidence. These systems provide pertinent and timely information at the point of care to guide the clinical decision-making process. As an evolving technology with the potential for wide applicability to individualize and improve patient care, CDSS require thoughtful design, effective implementation and critical evaluation for success.

The quantity and quality of clinical data are rapidly expanding throughout databanks, including electronic health records, disease registries, patient surveys and information exchanges. Real-time integration of robust, reliable and meaningful clinical data dramatically improves the rate at which translational and interprofessional research and quality improvement can progress. CDADS collects and organizes relevant data from many clinical databases in order to implement decision support tools for purposes of care delivery, research and quality improvement.

Many EMRs used in the U.S. fail to provide guidance relevant to the specific patient receiving care, present data poorly and cause alert fatigue to health care providers. A key goal of CDADS is to ensure that CDSS tools are integrated into clinical workflow, provide actionable information, save clinician time and improve patient care. Engagement of all clinicians — including physicians, nurses, pharmacists and other professionals involved in the delivery of health care — ensures that the tools created fit these guidelines.

The Division of Clinical Data Analytics and Decision Support provides:

  • Critical, independent analysis of medical evidence to guide clinical practice.
  • Conduit for research and quality improvement projects, including outcomes evaluation.
  • Access to the Clinical Research Data Warehouse.
  • Meaningful clinical data analytics for translational research.
  • Design of CDSS with stakeholder engagement.
  • Monitoring of CDSS performance, studying how clinicians respond to CDSS advisories and recommendations.
  • Collection and analysis of feedback from clinicians for iterative improvements in CDSS logic and presentation.
  • Leadership in medical education and training in precision medicine, clinical data and decision support systems.