Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/24154

Title: Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care
Authors: Aerts, Marc
Minalu, Girma
Boesner, Stefan
Buntinx, Frank
Burnand, Bernard
Haasenritter, Joerg
Herzig, Lilli
Knottnerus, J. Andre
Nilsson, Staffan
Renier, Walter
Sox, Carol
Sox, Harold
Donner-Banzhoff, Norbert
Issue Date: 2017
Abstract: Objective: To construct a clinical prediction rule for coronary artery disease (CAD) presenting with chest pain in primary care. Study Design and Setting: Meta-Analysis using 3,099 patients from five studies. To identify candidate predictors, we used random forest trees, multiple imputation of missing values, and logistic regression within individual studies. To generate a prediction rule on the pooled data, we applied a regression model that took account of the differing standard data sets collected by the five studies. Results: The most parsimonious rule included six equally weighted predictors: age >= 55 (males) or >= 65 (females) (+1); attending physician suspected a serious diagnosis (+1); history of CAD (+1); pain brought on by exertion (+1); pain feels like "pressure" (+1); pain reproducible by palpation (-1). CAD was considered absent if the prediction score is <2. The area under the ROC curve was 0.84. We applied this rule to a study setting with a CAD prevalence of 13.2% using a prediction score cutoff of <2 (i.e., 1, 0, or +1). When the score was <2, the probability of CAD was 2.1% (95% CI: 1.1-3.9%); when the score was >= 2, it was 43.0% (95% CI: 35.8-50.4%). Conclusions: Clinical prediction rules are a key strategy for individualizing care. Large data sets based on electronic health records from diverse sites create opportunities for improving their internal and external validity. Our patient-level meta-analysis from five primary care sites should improve external validity. Our strategy for addressing site-to-site systematic variation in missing data should improve internal validity. Using principles derived from decision theory, we also discuss the problem of setting the cutoff prediction score for taking action. (C) 2016 Elsevier Inc. All rights reserved.
Notes: [Aerts, Marc; Minalu, Girma] Hasselt Univ, Interuniv Inst Biostat & Stat Bioinformat I BIOST, I BioStat, Bldg D, B-3590 Diepenbeek, Belgium. [Boesner, Stefan; Haasenritter, Joerg; Donner-Banzhoff, Norbert] Philipps Univ Marburg, Dept Gen Practice & Family Med, Karl von Str 4, D-35037 Marburg, Germany. [Buntinx, Frank; Renier, Walter] Katholieke Univ Leuven, Dept Publ Hlth & Primary Care, Kapucijnenvoer 33,Blok J,PB 7001, B-3000 Leuven, Belgium. [Buntinx, Frank; Knottnerus, J. Andre] Maastricht Univ, Dept Gen Practice, Peter Debyeplein 1,POB 616, NL-6200 MD Maastricht, Netherlands. [Burnand, Bernard] Univ Lausanne Hosp, Inst Social & Prevent Med, Route Corniche 10, CH-1010 Lausanne, Switzerland. [Herzig, Lilli] Univ Lausanne, Inst Family Med, 44 Rue Bugnon, CH-1011 Lausanne, Switzerland. [Sox, Carol; Sox, Harold] Linkoping Univ, Dept Med & Hlth Sci, Div Community Med, SE-58183 Linkoping, Sweden. [Sox, Harold] Patient Ctr Outcomes Res Inst, 1828 L St NW,Suite 900, Washington, DC 20036 USA.
URI: http://hdl.handle.net/1942/24154
DOI: 10.1016/j.jclinepi.2016.09.011
ISI #: 000395497500016
ISSN: 0895-4356
Category: A1
Type: Journal Contribution
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version381.55 kBAdobe PDF
Peer-reviewed author version2.2 MBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.