Title |
Pooled individual patient data from five countries were used to derive a clinical prediction rule for coronary artery disease in primary care
|
---|---|
Published in |
Journal of Clinical Epidemiology, October 2016
|
DOI | 10.1016/j.jclinepi.2016.09.011 |
Pubmed ID | |
Authors |
International Working Group on Chest Pain in Primary Care, Marc Aerts, Girma Minalu, Stefan Bösner, Frank Buntinx, Bernard Burnand, Jörg Haasenritter, Lilli Herzig, J. André Knottnerus, Staffan Nilsson, Walter Renier, Carol Sox, Harold Sox, Norbert Donner-Banzhoff |
Abstract |
To construct a clinical prediction rule for coronary artery disease (CAD) presenting with chest pain in primary care. Meta-Analysis using 3099 patients from 5 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 5 studies. 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 AUC was 0.84. We applied this rule to a study setting with a CAD prevalence of 13.2% using a prediction score cut-off 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%). Clinical prediction rules are a key strategy for individualizing care. Large data sets based on electronic health records from diverse sites creates opportunities for improving their internal and external validity. Our patient-level meta-analysis from 5 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 cut-off prediction score for taking action. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Canada | 4 | 57% |
Spain | 1 | 14% |
United States | 1 | 14% |
Unknown | 1 | 14% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Practitioners (doctors, other healthcare professionals) | 2 | 29% |
Science communicators (journalists, bloggers, editors) | 2 | 29% |
Members of the public | 2 | 29% |
Scientists | 1 | 14% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 68 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Master | 11 | 16% |
Researcher | 10 | 15% |
Student > Ph. D. Student | 9 | 13% |
Student > Bachelor | 6 | 9% |
Professor > Associate Professor | 4 | 6% |
Other | 10 | 15% |
Unknown | 18 | 26% |
Readers by discipline | Count | As % |
---|---|---|
Medicine and Dentistry | 22 | 32% |
Nursing and Health Professions | 7 | 10% |
Computer Science | 4 | 6% |
Engineering | 3 | 4% |
Social Sciences | 2 | 3% |
Other | 4 | 6% |
Unknown | 26 | 38% |