Abstract
BackgroundWith higher adoption of electronic health records at health-care centers, electronic search algorithms (computable phenotype) for identifying acute decompensated heart failure (ADHF) among hospitalized patients can be an invaluable tool to enhance data abstraction accuracy and efficacy in order to improve clinical research accrual and patient centered outcomes. We aimed to derive and validate a computable phenotype for ADHF in hospitalized patients.MethodsWe screened 256, 443 eligible (age > 18 years and with prior research authorization) individuals who were admitted to Mayo Clinic Hospital in Rochester, MN, from January 1, 2006, through December 31, 2014. Using a randomly selected derivation cohort of 938 patients, several iterations of a free-text electronic search were developed and refined. The computable phenotype was subsequently validated in an independent cohort 100 patients. The sensitivity and specificity of the computable phenotype were compared to the gold standard (expert review of charts) and International Classification of Diseases-9 (ICD-9) codes for Acute Heart Failure.ResultsIn the derivation cohort, the computable phenotype achieved a sensitivity of 97.5%, and specificity of 100%, whereas ICD-9 codes for Acute Heart Failure achieved a sensitivity of 47.5% and specificity of 96.7%. When all Heart Failure codes (ICD-9) were used, sensitivity and specificity were 97.5 and 86.6%, respectively. In the validation cohort, the sensitivity and specificity of the computable phenotype were 100 and 98.5%. The sensitivity and specificity for the ICD-9 codes (Acute Heart Failure) were 42 and 98.5%. Upon use of all Heart Failure codes (ICD-9), sensitivity and specificity were 96.8 and 91.3%.ConclusionsOur results suggest that using computable phenotype to ascertain ADHF from the clinical notes contained within the electronic medical record are feasible and reliable. Our computable phenotype outperformed ICD-9 codes for the detection of ADHF.
Highlights
With higher adoption of electronic health records at health-care centers, electronic search algorithms for identifying acute decompensated heart failure (ADHF) among hospitalized patients can be an invaluable tool to enhance data abstraction accuracy and efficacy in order to improve clinical research accrual and patient centered outcomes
With the goal to achieve sensitivity of more than 95%, the automated search algorithm was continuously refined with additional free text search terms, inclusion and exclusion keywords, and the inclusion of more datasets in Electronic health record (EHR)
Performance of computable phenotype as compared to manual review Initially, the computable phenotype automated electronic ADHF search strategy achieved a sensitivity of 89.4% and specificity of 81% for ADHF in the derivation cohort when analyzed against a manual review in the initial derivation cohort (N2)
Summary
With higher adoption of electronic health records at health-care centers, electronic search algorithms (computable phenotype) for identifying acute decompensated heart failure (ADHF) among hospitalized patients can be an invaluable tool to enhance data abstraction accuracy and efficacy in order to improve clinical research accrual and patient centered outcomes. The utility of electronic health records (EHRs) has been increased in past decade and the size of available health information for clinical and epidemiologic research has rapidly stretched [1, 2] This brings new hurdles for current methodology, such as the inability to manually review sufficient amounts of data in a reasonable time. For better provider decision making for sepsis care, supervised machine learning has been deployed as two-step machine-human interface [12] These studies have all demonstrated that electronic searches can achieve sensitivities and specificities greater than 90% when compared to manual search efforts. There is limited literature on automation for identifying acute decompensated heart failure (ADHF) and the effectiveness of such methodology, when compared to the manual chart review of a prospectively collected electronic database
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
