Education, Research, and Quality Improvement: Education, Research, and Quality Improvement II |

Derivation and Validation of an Automated Electronic Search Algorithm to Identify Pre-operative History of Renal Replacement Therapy FREE TO VIEW

Rashid Ali, MD; Devang Sanghavi, MD; Melissa Pasee; Gregory Wilson; Vivek Iyer, MD; Rahul Kashyap, MD
Author and Funding Information

Mayo Clinic, Rochester, MN

Copyright 2016, American College of Chest Physicians. All Rights Reserved.

Chest. 2016;150(4_S):626A. doi:10.1016/j.chest.2016.08.718
Text Size: A A A
Published online

SESSION TITLE: Education, Research, and Quality Improvement II

SESSION TYPE: Original Investigation Poster

PRESENTED ON: Wednesday, October 26, 2016 at 01:30 PM - 02:30 PM

PURPOSE: To derive and validate an electronic search algorithm to identify history of dialysis for a patient prior to a reference date. Our project reference date was the date of liver transplant surgery

METHODS: Using EMR sources, a retrospective analysis of patients admitted to a tertiary care center was done. A total of 1582 patients underwent liver transplant surgery from March 17, 1999 through January 15, 2016. All ages of patients were included. Using a derivation cohort of 100 patients, several iterations of a free-text electronic search were developed and refined for dialysis, but using procedure codes for the search was found to be more reliable than free-text. Subsequently, the automated search algorithm was validated on an independent cohort of 100 patients. The sensitivity and specificities were compared with the results of comprehensive manual medical records review (reference standard) for dialysis.

RESULTS: Using the procedure codes for dialysis for the initial derivation group yielded a sensitivity of 70% and specificity of 97%. In the final derivation subset, the automated search algorithm achieved a sensitivity of 100%, and a specificity of 97% for dialysis. When applied to the validation cohort, the automated digital algorithm achieved a median sensitivity of 100% and a median specificity of 97% for dialysis.

CONCLUSIONS: Derivation and validation of an electronic search algorithm is a feasible tool to facilitate and expedite extraction of data from EMR, and has an excellent reliability compared to manual review. Similar electronic tools can be developed and used for different purposes like research and quality improvement projects.

CLINICAL IMPLICATIONS: Electronic search algorithms can be a useful tool to accelerate searching and extraction of patients’ data and facilitate clinical research by reducing the hassle of manual review of Electronic medical records (EMR). Chronic kidney disease (CKD) is a common complication after liver transplant and affects graft and patient survival. Pre-transplant renal function is a key factor of post-transplant CKD. History of renal replacement therapy or dialysis can reflect the renal function status.

DISCLOSURE: The following authors have nothing to disclose: Rashid Ali, Devang Sanghavi, Melissa Pasee, Gregory Wilson, Vivek Iyer, Rahul Kashyap

No Product/Research Disclosure Information




Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Find Similar Articles
CHEST Journal Articles
PubMed Articles
  • CHEST Journal
    Print ISSN: 0012-3692
    Online ISSN: 1931-3543