Computerized Extraction of Information on the Quality of Diabetes Care from Free Text in Electronic Patient Records of General Practitioners
- Jaco Voorham,
- Petra Denig Groningen Initiative to Analyse Type 2 Diabetes Treatment (GIANTT) group
- Affiliations of the authors: Department of Clinical Pharmacology (JV, PD), University Medical Center Groningen, University of Groningen, The Netherlands. Trial Coordination Center, Department of Clinical Epidemiology (JV), University Medical Center, Groningen, University of Groningen, The Netherlands
- Correspondence and reprint requests to: J. Voorham UMCG, Sector F, Department of Clinical Pharmacology, POB 196, 9700 AD Groningen, The Netherlands; email: <j.voorham{at}epi.umcg.nl>
- Received 18 April 2006
- Accepted 26 January 2007
Abstract
Objective This study evaluated a computerized method for extracting numeric clinical measurements related to diabetes care from free text in electronic patient records (EPR) of general practitioners.
Design and Measurements Accuracy of this number-oriented approach was compared to manual chart abstraction. Audits measured performance in clinical practice for two commonly used electronic record systems.
Results Numeric measurements embedded within free text of the EPRs constituted 80% of relevant measurements. For 11 of 13 clinical measurements, the study extraction method was 94%–100% sensitive with a positive predictive value (PPV) of 85%–100%. Post-processing increased sensitivity several points and improved PPV to 100%. Application in clinical practice involved processing times averaging 7.8 minutes per 100 patients to extract all relevant data.
Conclusion The study method converted numeric clinical information to structured data with high accuracy, and enabled research and quality of care assessments for practices lacking structured data entry.
Footnotes
-
The GIANTT project is funded by grants from the University Medical Center Groningen, The Netherlands.
-
The support of the physicians at the practices where data were collected is greatly appreciated. We thank Ineke van de Ven for double coding the gold standard dataset. We thank Promedico ICT B.V., The Netherlands, and iSoft, The Netherlands, for providing their EPR Information Systems for our test environment. Flora Haaijer-Ruskamp and Hans Hillege provided helpful comments on the draft of this paper, as did the anonymous reviewers of this journal.
-
The Groningen Initiative to Analyse Type 2 Diabetes Treatment (GIANTT) group are D. de Zeeuw, F.M. Haaijer-Ruskamp, P. Denig (Department of Clinical Pharmacology, University Medical Center Groningen), R.O.B. Gans (Department of Internal Medicine, University Medical Center Groningen), B.H.R. Wolffenbuttel (Department of Endocrinology, University Medical Center Groningen), F.W. Beltman (Department of General Practice, University Medical Center Groningen), K. Hoogenberg (Department of Internal Medicine, Martini Hospital Groningen), P. Bijster (Regional Diabetes Facility, General Practice Laboratory LabNoord, Groningen), J. Bolt (District Association of General Practitioners, Groningen), L.T.W. de Jong-van den Berg (Department of Social Pharmacy and Pharmacoepidemiology, University of Groningen), J.G.W. Kosterink (Hospital Pharmacy, University Medical Center Groningen), J.L. Hillege (Trial Coordination Center, Department of Clinical Epidemiology, University Medical Center Groningen).
