A prognostic model based on readily available clinical data enriched a pre-emptive pharmacogenetic testing program

• Published in: Journal of clinical epidemiology Vol. 72; pp. 107 - 115
• Main Authors: Schildcrout, Jonathan S., Shi, Yaping, Danciu, Ioana, Bowton, Erica, Field, Julie R., Pulley, Jill M., Basford, Melissa A., Gregg, William, Cowan, James D., Harrell, Frank E., Roden, Dan M., Peterson, Josh F., Denny, Joshua C.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.04.2016; Elsevier Limited
• Subjects: Adult; Age Factors; Aged; Cardiology; Cardiovascular disease; Clinics; Clopidogrel; Computer decision support; Computerized physician order entry; Datasets; Decision Support Systems, Clinical; Diabetes; Drug Utilization - statistics & numerical data; Electronic health records; Electronic Health Records - organization & administration; Epidemiology; Female; Humans; Hydroxymethylglutaryl-CoA Reductase Inhibitors - therapeutic use; Hypertension; Internal Medicine; Longitudinal Studies; Male; Medicine; Middle Aged; Models, Statistical; Nephrology; Pharmacogenetics - organization & administration; Precision medicine; Predictive Value of Tests; Prescriptions; Prognosis; Program Evaluation; Proportional Hazards Models; Reproducibility of Results; Risk Factors; Sex Factors; Statin; Statins; Survival analysis; Ticlopidine - analogs & derivatives; Ticlopidine - therapeutic use; United States; Variables; Warfarin; Warfarin - therapeutic use; Clopidogrel; Warfarin; Computer decision support; Statin; Precision medicine; Electronic health records
• ISSN: 0895-4356; 1878-5921; 1878-5921
• DOI: 10.1016/j.jclinepi.2015.08.028

We describe the development, implementation, and evaluation of a model to pre-emptively select patients for genotyping based on medication exposure risk. Using deidentified electronic health records, we derived a prognostic model for the prescription of statins, warfarin, or clopidogrel. The model was implemented into a clinical decision support (CDS) tool to recommend pre-emptive genotyping for patients exceeding a prescription risk threshold. We evaluated the rule on an independent validation cohort and on an implementation cohort, representing the population in which the CDS tool was deployed. The model exhibited moderate discrimination with area under the receiver operator characteristic curves ranging from 0.68 to 0.75 at 1 and 2 years after index dates. Risk estimates tended to underestimate true risk. The cumulative incidences of medication prescriptions at 1 and 2 years were 0.35 and 0.48, respectively, among 1,673 patients flagged by the model. The cumulative incidences in the same number of randomly sampled subjects were 0.12 and 0.19, and in patients over 50 years with the highest body mass indices, they were 0.22 and 0.34. We demonstrate that prognostic algorithms can guide pre-emptive pharmacogenetic testing toward those likely to benefit from it.