This Article Full Text Free Full Text (PDF) Free Data Supplement All Versions of this Article: M2753v1 15/6/787    most recent Submit a response Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Tripp, J. S. Articles by Huff, S. M. Search for Related Content PubMed PubMed Citation Articles by Tripp, J. S. Articles by Huff, S. M.

Evaluating the Accuracy of Existing EMR Data as Predictors of Follow-up Providers

^a Department of Biomedical Informatics, University of Utah, Salt Lake City, UT
^b Department of Family and Preventive Medicine, University of Utah, Salt Lake City, UT
^c Intermountain Healthcare, Salt Lake City, UT

^_* Correspondence: Jacob S. Tripp, Department of Biomedical Informatics, University of Utah School of Medicine, 26 South 2000 East, Suite 5700 HSEB, Salt Lake City, UT 84112-5750 (Email: jacob.tripp{at}hsc.utah.edu).

Received for publication: 02/11/08; accepted for publication: 08/14/08.

In order to evaluate the accuracy of existing EMR data in predicting follow-up providers, a retrospective analysis was performed on six months of data for inpatient and ED encounters occurring at two hospitals, and on related outpatient data. Sensitivity and Positive Predictive Value (PPV) were calculated for each of eight predictors, to determine their effectiveness in predicting follow-up providers. Our findings indicate that access to longitudinal patient care records can improve prediction of which providers a patient is likely to see post-discharge compared to simply using Primary Care Provider data from admissions records. Of the predictors evaluated, a patient's past appointment history was the best predictor of which providers they would see in the future (PPV = 48% following inpatient visits, 35% following emergency department visits). However, even the best performing predictors failed to predict more than half of the follow-up providers and might generate many "false" alerts.