Cardiac catheterization represents a significant medical diagnostic or treatment exposure risk for the development of acute kidney injury (AKI). That risk varies widely depending on the patient's pre-procedural medical conditions as well as exposures during or immediately before or after the procedure. Post procedural AKI occurs in 1% to 31% of the patients, depending on the cohort studied, and is associated with a 30% one- year mortality rate. For outcomes further downstream, AKI increases the risk of progressing to chronic kidney disease, which can lead to dialysis, increased cardiovascular adverse outcomes, reductions in quality of life, and significant personal and health care costs. Cardiac catheterization is a high risk, closely observed, and intervenable clinical care window, and preventing an occurrence of AKI would have significant impact on veteran's health and VA costs of care, which has been estimated to be approximately $7,500 per patient. However, automated outcomes surveillance is not widely performed, and the VA does not currently have the informatics tools to conduct this surveillance for the 40,000 veterans a year undergoing the procedure. The overall objective of this project is to develop the infrastructure and tools to perform national VA near real-time automated adverse event surveillance after cardiac catheterization, and to demonstrate the utility of the tools within the use case of post-procedural AKI. More specifically, we will 1) develop and validate near real-time natural language processing (NLP) tools using interactive learning techniques in order to extract information that is relevant to AKI but is collected in structured data, 2) develop and validate a robust family of logistic regression prediction models for AKI following cardiac catheterization for use in the identification of high risk patients and populations, and 3) conduct automated national retrospective and prospective analyses of institutional care variation among veterans receiving cardiac catheterization using novel surveillance methods. This proposal will analyze retrospective and prospective cohort data from the VA Cardiovascular Assessment, Reporting, and Tracking for Catheterization Laboratories (CART-CL) voluntary clinical registry and electronic health record system (CPRS) from 2009 to 2015. All adult patients who received a cardiac catheterization in the VA during this time period will be included. All variables will be extracted from the structured data elements of CART-CL and CPRS, with near real time NLP used to extract risk factors from unstructured data. Risk factors will be identified by comprehensive literature review, expert consensus, and discovery during evaluation of retrospective signals, and selected through the use of the Lasso regression variable selection technique. Logistic regression models will be developed for each of the Acute Kidney Injury Network AKI stages, internally validated with bootstrapping, and externally validated with the Northern New England Cardiovascular Disease Study Group percutaneous coronary intervention registry. Institutional surveillance analyses will be conducted using maximized sequential probability ratio testing and Bayesian hierarchical logistic regression. The strongest institutional outliers will have manual case review of patient cases that experienced the outcome in order to ascertain key clinical care variations. A governance board consisting of CART and VA interventional cardiology leaders will be established to supervise detected signals for identification and feedback to individual institutions. This proposal will improve veterans'care n a number of areas. This work has the potential to discover new risk factors associated with AKI, to provide robust risk stratification tools for the identification of high risk patients prior to te procedure, and allow the detection of institutional outliers and clinical care process variation tht is associated with increased AKI risk that may be amenable to quality improvement interventions. Finally, the informatics infrastructure and NLP development has the potential to be applied in a wide variety of exposures and outcomes beyond AKI for cardiac catheterization surveillance.
Many Veterans have several co-existing chronic medical conditions and many have multiple concurrent medications they are taking. These exposures increase risk for acute kidney injury (AKI) after cardiac catheterization, and approximately 40,000 Veterans a year undergo this procedure, with AKI event rates ranging from 1% to 30% depending on the definition of the outcome. Studies have suggested that there is a wide variation of patient care related to the management of the risk for this outcome outside of the VA, and no structured or automated surveillance of this outcome exists in the VA. This project addresses this need that is coupled with an opportunity presented from the robust clinical electronic health record and recent rise of the CART-CL catheterization data collection program. This project will create informatics tools that can perform the necessary institutional performance surveillance on a daily basis and provide feedback to the national program and individual institutions to promote changes in clinical practice that will reduce the occurrence of adverse outcome.
|Parr, Sharidan K; Matheny, Michael E; Abdel-Kader, Khaled et al. (2018) Acute kidney injury is a risk factor for subsequent proteinuria. Kidney Int 93:460-469|
|Brown, Jeremiah R; MacKenzie, Todd A; Maddox, Thomas M et al. (2015) Acute Kidney Injury Risk Prediction in Patients Undergoing Coronary Angiography in a National Veterans Health Administration Cohort With External Validation. J Am Heart Assoc 4:|
|Cronin, Robert M; VanHouten, Jacob P; Siew, Edward D et al. (2015) National Veterans Health Administration inpatient risk stratification models for hospital-acquired acute kidney injury. J Am Med Inform Assoc 22:1054-71|
|Tsai, Thomas T; Patel, Uptal D; Chang, Tara I et al. (2014) Validated contemporary risk model of acute kidney injury in patients undergoing percutaneous coronary interventions: insights from the National Cardiovascular Data Registry Cath-PCI Registry. J Am Heart Assoc 3:e001380|
|Resnic, Frederic S; Wang, Tracy Y; Arora, Nipun et al. (2012) Quantifying the learning curve in the use of a novel vascular closure device: an analysis of the NCDR (National Cardiovascular Data Registry) CathPCI registry. JACC Cardiovasc Interv 5:82-9|