Automating Performance Metrics for Quality Improvement in Complex Chronic Disease

Veterans Admin Palo Alto Health Care Sys, Palo Alto CA

Investigators

Abstract

DESCRIPTION (provided by applicant): Background: Many Veterans receiving medical care in VA have multiple coexisting chronic conditions (comorbidities); yet, performance measures typically examine only one disease at a time. Clinical practice guidelines (CPGs) synthesizing evidence into recommendations form the basis for most performance measures. Because of the limitations of previously available systems for automated processing of performance measures, the measures address only small portions of the CPG recommendations, and rarely take account of clinical complexity even within single diseases. In order to make performance measures applicable to the patients included in the denominator for the measure, many exclusion criteria are often applied, resulting in absence of any performance measure for the substantial proportion of patients who have an exclusion criterion. Furthermore, even for patients remaining in the denominator, evidence-based recommendations may call for alternate treatments due to specific clinical characteristics of the patient, resulting in non-applicability of the simple performance measures. Newer information technology can be applied to enhance performance measures. Encoded knowledge bases of detailed clinical knowledge allow for automated processing of patient data to draw conclusions about the state of the patient (including attainment of performance measure clinical targets) and highly-individualized recommendations for next steps in therapy. Application of such knowledge bases can provide a nuanced view of guideline-adherence and detection of presence or absence of valid reasons, such as comorbid illnesses and their treatments, for altering treatment or targets. Objectives: The overall objective of this project is to develop new informatics methods to automate quality improvement measures for patients with complex clinical scenarios. The Specific Aims are (1) To create an automated knowledge base for current performance measures with clinical detail about alternate evidence- based recommendations based on detailed clinical characteristics; (2) To conduct stakeholder interviews with key VA program offices and quality managers regarding prioritization and coordination of recommendations for patients who have multiple comorbidities; (3) To elaborate the knowledge base with additional clinical knowledge about prioritization and coordination of recommendations based on findings from Specific Aim 2; (4) To develop systems to provide clinical decision support (CDS) across multiple chronic conditions to health professionals in the Patient-Aligned Care Teams (PACTs) to improve performance. Design/Methods: The project will use informatics development methods to encode the clinical knowledge base, building on prior (CDS) work and drawing on insights about integrating multiple guidelines from an informatics project recently-funded by National Library of Medicine (NLM). Stakeholder interviews with key staff in quality management and in several domains of clinical care including experts in multiple co-existing chronic conditions will be synthesized to guide prioritization and coordination of recommendations. The VISN21 Pharmacy Benefits Management clinical dashboard will serve as the test-bed for providing CDS to PACT health professionals providing patient-centric care for Veterans with complex conditions. Agile development procedures will be employed based on frequent interaction with potential end-users in iterative design and development cycles. Informatics tools developed in this project will be evaluated by constraint verification, testing of accuracy of recommendations, assessment of suitability to clinical workflow, and stakeholder input. Potential Impact: This informatics research project will develop new methods to address quality measurement and improvement for the many Veterans with multiple chronic conditions. These methods can potentially automate quality measurement for quality managers and clinical program offices, and automate CDS to assist health professionals in PACTs for quality improvement in patient-centric care.