MC COMPARE Multiple Chronic COnditions: MultiPle dAta SouRcEs Project Summary The evidence to guide risk-benefit decisions for patients living with multiple chronic conditions (MCCs) is limited. For example, patients with chronic kidney disease can benefit from tight blood pressure control but are also at risk of adverse events – hypotension, falls, acute kidney injury (AKI) – making treatment difficult. Trials exploring how best to treat patients with MCC including high blood pressure are being performed: A collaborative approach to managing hypertension (HTN): COACH Collaboration-Oriented Approach to Controlling High blood pressure (Dorr and Koopman) and Electronic Tools to Increase Recognition and Improve Primary Care Management for Hypertension in Chronic Kidney Disease (CKD; Samal and Dykes). In this proposal, we will aggregate EHR data from multiple institutions into the eCarePlan, an application intended to bring multiple data sources together for care planning using Fast Healthcare Interoperable Resources (FHIR). These enhanced data sets will help us to quantify the ways that aggregating fragmented data can improve clinical trial results and personalized decision making for older adults. We will then use this dataset to better understand the risk of adverse events in these studies, like falls and AKI, as well as poor clinical outcomes, like strokes and worsening cognitive function. We will proceed in accordance with established steps of data harmonization. First, we will adapt and implement the eCarePlan tool to automatically extract data needed for the two partner studies on HTN and CKD. We will focus on unrecognized chronic conditions, partner study variables, partner study outcomes, health behaviors, social determinants of health, and adverse event outcomes. We will use optical character recognition (OCR) and natural language processing (NLP) to extract and harmonize data from electronic free text notes and scanned documents.Second, we will harmonize data and refine the integration process using Findability/Accessibility/Interoperability/Reusability (FAIR) and data readiness frameworks and engage patients and providers to understand how these integrated studies can be matched to patient prognosis and needs. Third, we will replicate measurement of study criteria and outcomes for both studies. We will provide the resulting interoperable infrastructure openly for all.