{"title":"Risk factors for cardiovascular events of antidementia drugs in Alzheimer's disease patients","authors":"Inmaculada Hernandez PharmD","doi":"10.1016/j.jcgg.2016.01.002","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Antidementia drugs have been associated with an increased risk of cardiovascular events. The objective of this study was to identify the predictors for cardiovascular events among patients with Alzheimer's disease (AD) on antidementia drugs, mining large longitudinal claims data.</p></div><div><h3>Methods</h3><p>Using 2006–2011 claims from a 5% random sample of Medicare beneficiaries, I identified patients with AD who filled a prescription for an antidementia drug between 2007 and 2011. I followed them from the initiation of the antidementia drug until a cardiovascular event or December 31, 2011, censored by death or discontinuation of antidementia drugs. The outcome was the incidence of cardiovascular events, which include acute myocardial infarction, bradycardia, syncope, atrioventricular block, QT prolongation, and ventricular tachycardia. Covariates included predefined patient characteristics and empirical attributes identified from the claims, including <em>International Classification of Diseases, Ninth Revision</em> (ICD-9) diagnosis codes, Healthcare Common Procedure Coding System codes, and therapeutic classes of all prescriptions filled. After using feature selection to choose the top covariates, a logistic regression with multivariate variable selection was constructed.</p></div><div><h3>Results</h3><p>With an accuracy of 83.9% and a sensitivity of 93.3%, the algorithm identified 22 predictors for cardiovascular events, including a history of ischemic heart disease, congestive heart failure, syncope, stroke or transient ischemic attack, diabetes, number of other comorbidities, and procedures including venipuncture and radiologic examinations.</p></div><div><h3>Conclusion</h3><p>The results of this study can help clinicians identify AD patients with a higher risk of cardiovascular events who therefore should be prescribed antidementia drugs cautiously.</p></div>","PeriodicalId":100764,"journal":{"name":"Journal of Clinical Gerontology and Geriatrics","volume":"7 3","pages":"Pages 77-82"},"PeriodicalIF":0.0000,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.jcgg.2016.01.002","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Gerontology and Geriatrics","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S221083351600006X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Background
Antidementia drugs have been associated with an increased risk of cardiovascular events. The objective of this study was to identify the predictors for cardiovascular events among patients with Alzheimer's disease (AD) on antidementia drugs, mining large longitudinal claims data.
Methods
Using 2006–2011 claims from a 5% random sample of Medicare beneficiaries, I identified patients with AD who filled a prescription for an antidementia drug between 2007 and 2011. I followed them from the initiation of the antidementia drug until a cardiovascular event or December 31, 2011, censored by death or discontinuation of antidementia drugs. The outcome was the incidence of cardiovascular events, which include acute myocardial infarction, bradycardia, syncope, atrioventricular block, QT prolongation, and ventricular tachycardia. Covariates included predefined patient characteristics and empirical attributes identified from the claims, including International Classification of Diseases, Ninth Revision (ICD-9) diagnosis codes, Healthcare Common Procedure Coding System codes, and therapeutic classes of all prescriptions filled. After using feature selection to choose the top covariates, a logistic regression with multivariate variable selection was constructed.
Results
With an accuracy of 83.9% and a sensitivity of 93.3%, the algorithm identified 22 predictors for cardiovascular events, including a history of ischemic heart disease, congestive heart failure, syncope, stroke or transient ischemic attack, diabetes, number of other comorbidities, and procedures including venipuncture and radiologic examinations.
Conclusion
The results of this study can help clinicians identify AD patients with a higher risk of cardiovascular events who therefore should be prescribed antidementia drugs cautiously.