A review of covariate selection for non-experimental comparative effectiveness research.

Abstract:

:This paper addresses strategies for selecting variables for adjustment in non-experimental comparative effectiveness research and uses causal graphs to illustrate the causal network that relates treatment to outcome. Variables in the causal network take on multiple structural forms. Adjustment for a common cause pathway between treatment and outcome can remove confounding, whereas adjustment for other structural types may increase bias. For this reason, variable selection would ideally be based on an understanding of the causal network; however, the true causal network is rarely known. Therefore, we describe more practical variable selection approaches based on background knowledge when the causal structure is only partially known. These approaches include adjustment for all observed pretreatment variables thought to have some connection to the outcome, all known risk factors for the outcome, and all direct causes of the treatment or the outcome. Empirical approaches, such as forward and backward selection and automatic high-dimensional proxy adjustment, are also discussed. As there is a continuum between knowing and not knowing the causal, structural relations of variables, we recommend addressing variable selection in a practical way that involves a combination of background knowledge and empirical selection and that uses high-dimensional approaches. This empirical approach can be used to select from a set of a priori variables based on the researcher's knowledge to be included in the final analysis or to identify additional variables for consideration. This more limited use of empirically derived variables may reduce confounding while simultaneously reducing the risk of including variables that may increase bias.

authors

Sauer BC,Brookhart MA,Roy J,VanderWeele T

doi

10.1002/pds.3506

subject

Has Abstract

pub_date

2013-11-01 00:00:00

pages

1139-45

issue

11

eissn

1053-8569

issn

1099-1557

journal_volume

22

pub_type

杂志文章,评审
  • Development of an adverse events reporting form for Korean folk medicine.

    abstract:PURPOSE:We developed an adverse events (AEs) reporting form for Korean folk medicine. METHODS:The first version of the form was developed and tested in the clinical setting for spontaneous reporting of AEs. Additional revisions to the reporting form were made based on collected data and expert input. RESULTS:We devel...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4077

    authors: Park JH,Choi SM,Moon S,Kim S,Kim B,Kim MK,Lee S

    更新日期:2017-05-01 00:00:00

  • Development of algorithms for identifying fatal cardiovascular disease in Medicare claims.

    abstract:BACKGROUND:Cause of death is often not available in administrative claims data. OBJECTIVE:To develop claims-based algorithms to identify deaths due to fatal cardiovascular disease (CVD; ie, fatal coronary heart disease [CHD] or stroke), CHD, and stroke. METHODS:Reasons for Geographic and Racial Differences in Stroke ...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4421

    authors: Xie F,Colantonio LD,Curtis JR,Kilgore ML,Levitan EB,Monda KL,Safford MM,Taylor B,Woodward M,Muntner P

    更新日期:2018-07-01 00:00:00

  • Optimization of a quantitative signal detection algorithm for spontaneous reports of adverse events post immunization.

    abstract:PURPOSE:To optimize the efficiency of signal detection by maximizing the proportion of true positive (TP) signals among signals detected by a disproportionality algorithm. METHODS:We compared 176 different combinations of stratification factors, sex (S), age (A), region (R) and year of report (Y), and cut-off values o...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.3392

    authors: Van Holle L,Bauchau V

    更新日期:2013-05-01 00:00:00

  • Using claims data to predict dependency in activities of daily living as a proxy for frailty.

    abstract:PURPOSE:Estimating drug effectiveness and safety among older adults in population-based studies using administrative health care claims can be hampered by unmeasured confounding as a result of frailty. A claims-based algorithm that identifies patients likely to be dependent, a proxy for frailty, may improve confounding...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.3719

    authors: Faurot KR,Jonsson Funk M,Pate V,Brookhart MA,Patrick A,Hanson LC,Castillo WC,Stürmer T

    更新日期:2015-01-01 00:00:00

  • Who are we missing? Underrepresentation of data sources used for pharmacoepidemiology research in the United States.

    abstract:PURPOSE:Research using healthcare databases often includes patients frequently excluded from clinical trials; yet it is not known whether commonly used data represents the overall population or specific sub-populations of interest. We aimed to examine population representativeness from data sources in recent research s...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.5087

    authors: Kaviani P,Landi SN,McKethan A,Brookhart MA,McGrath LJ

    更新日期:2020-11-01 00:00:00

  • Maternal use of antibiotics and the risk of orofacial clefts: a nationwide cohort study.

    abstract:PURPOSE:To study the association between antibiotic use in early pregnancy and the risk of isolated orofacial clefts. METHODS:We conducted a cohort study of 806,011 live births in Denmark from 1996 through September 2008. Individual-level information on prescribed antibiotics during pregnancy, orofacial cleft diagnosi...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.2179

    authors: Mølgaard-Nielsen D,Hviid A

    更新日期:2012-03-01 00:00:00

  • Adherence to osteoporosis pharmacotherapy is underestimated using days supply values in electronic pharmacy claims data.

    abstract:PURPOSE:Days supply (prescription duration) values are commonly used to estimate drug exposure and quantify adherence to therapy, yet accuracy is not routinely assessed, and potential inaccurate reporting has been previously identified. We examined the impact of cleaning days supply values on the measurement of adheren...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.3718

    authors: Burden AM,Paterson JM,Gruneir A,Cadarette SM

    更新日期:2015-01-01 00:00:00

  • Patient focused drug surveillance of elderly patients in nursing homes.

    abstract:PURPOSE:To examine whether patient focused drug surveillance was associated with a higher quality of drug treatment at nursing homes. METHODS:An intervention study in four nursing homes in Sweden and four other nursing homes served as controls. At the intervention nursing homes physicians focused on patients' health s...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1891

    authors: Olsson IN,Curman B,Engfeldt P

    更新日期:2010-02-01 00:00:00

  • Trends in the long-term use of benzodiazepine anxiolytics and hypnotics: A national register study for 2006 to 2014.

    abstract:PURPOSE:Long-term benzodiazepine (BZD) treatment continues to be a debated topic. Because individual BZDs have different clinical profiles, we assessed the nationwide trends of long-term BZD use at active substance level during years 2006 to 2014. METHODS:This study covered all reimbursed BZD purchases (n = 408 572-52...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4551

    authors: Kurko T,Saastamoinen LK,Tuulio-Henriksson A,Taiminen T,Tiihonen J,Airaksinen M,Hietala J

    更新日期:2018-06-01 00:00:00

  • Descriptive epidemiology of acute liver enzyme abnormalities in the general population of central Massachusetts.

    abstract:OBJECTIVES:This study quantifies the incidence of liver enzyme abnormalities in the general population of central Massachusetts. METHODS:Computerized data files from a health maintenance organization were used to ascertain potential subjects during the study period of 1 July 1992-30 June 1993. Medical records and labo...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/(SICI)1099-1557(199907)8:4<275::AID-PDS427

    authors: Duh MS,Walker AM,Kronlund KH Jr

    更新日期:1999-07-01 00:00:00

  • Subtle issues in model specification and estimation of marginal structural models.

    abstract::We review the concept of time-dependent confounding by using the example in paper "Comparative effectiveness of individual angiotensin receptor blockers on risk of mortality in patients with chronic heart failure" by Desai et al. and illustrate how to adjust for it by using inverse probability of treatment weighting t...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 评论,杂志文章

    doi:10.1002/pds.2306

    authors: Yang W,Joffe MM

    更新日期:2012-03-01 00:00:00

  • Predicting prolonged dose titration in patients starting warfarin.

    abstract:PURPOSE:Patients initiating warfarin therapy generally experience a dose-titration period of weeks to months, during which time they are at higher risk of both thromboembolic and bleeding events. Accurate prediction of prolonged dose titration could help clinicians determine which patients might be better treated by al...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4069

    authors: Finkelman BS,French B,Bershaw L,Brensinger CM,Streiff MB,Epstein AE,Kimmel SE

    更新日期:2016-11-01 00:00:00

  • Adverse events among nursing home residents with Alzheimer's disease and psychosis.

    abstract:PURPOSE:The objective of this study was to quantify rates of adverse events in a high-risk multi-morbid population of institutionalized patients with Alzheimer's disease (AD). METHODS:We conducted a retrospective cohort study among nursing home residents diagnosed with AD and psychosis during January 1998 to October 1...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1274

    authors: Oliveria SA,Liperoti R,L'italien G,Pugner K,Safferman A,Carson W,Lapane K

    更新日期:2006-11-01 00:00:00

  • Antidepressant medication use and breast cancer risk.

    abstract:PURPOSE:Most epidemiologic studies have detected no association between prior use of antidepressant medications and breast cancer risk. Despite the uniform conclusion, there is a continuous rise in the proportion of women using antidepressants, lending support to further monitoring of disease effects. METHODS:We condu...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1719

    authors: Wernli KJ,Hampton JM,Trentham-Dietz A,Newcomb PA

    更新日期:2009-04-01 00:00:00

  • Design considerations, architecture, and use of the Mini-Sentinel distributed data system.

    abstract:PURPOSE:We describe the design, implementation, and use of a large, multiorganizational distributed database developed to support the Mini-Sentinel Pilot Program of the US Food and Drug Administration (FDA). As envisioned by the US FDA, this implementation will inform and facilitate the development of an active surveil...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.2336

    authors: Curtis LH,Weiner MG,Boudreau DM,Cooper WO,Daniel GW,Nair VP,Raebel MA,Beaulieu NU,Rosofsky R,Woodworth TS,Brown JS

    更新日期:2012-01-01 00:00:00

  • Increased risk of digoxin toxicity following hospitalization.

    abstract:PURPOSE:Adverse drug events (ADEs) are an important cause of preventable hospitalizations among elderly individuals taking high-risk medications. The objective of the study was to identify health care system factors that affect the risk of digoxin toxicity for older adults on digoxin. METHODS:We conducted a prospectiv...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1680

    authors: Haynes K,Hennessy S,Localio AR,Cohen A,Leonard CE,Kimmel SE,Feldman HI,Strom BL,Metlay JP

    更新日期:2009-01-01 00:00:00

  • Exposure to reactive intermediate-inducing drugs during pregnancy and the incident use of psychotropic medications among children.

    abstract:PURPOSE:Our study aimed to investigate the association between prenatal exposure to reactive intermediate (RI)-inducing drugs and the initiation of psychotropic medications among children. METHODS:We designed a cohort study using a pharmacy prescription database. Pregnant women were considered exposed when they receiv...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4161

    authors: Tran YH,Groen H,Bergman JE,Hak E,Wilffert B

    更新日期:2017-03-01 00:00:00

  • The state of dietary supplement adverse event reporting in the United States.

    abstract:PURPOSE:The Dietary Supplements Information Expert Committee (DSI-EC; the Committee) of the United States Pharmacopeial Convention (USP) reviews safety profiles of dietary supplements before development of USP-National Formulary (USP-NF) quality monographs. Because the veracity of dietary supplement adverse event repor...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章,评审

    doi:10.1002/pds.1627

    authors: Gardiner P,Sarma DN,Low Dog T,Barrett ML,Chavez ML,Ko R,Mahady GB,Marles RJ,Pellicore LS,Giancaspro GI

    更新日期:2008-10-01 00:00:00

  • Myocardial infarction and oral contraceptives, a retrospective case control study in England and Scotland ('MICA' Study).

    abstract::Recent studies have shown that modern (third generation), oral contraceptives (OC) are associated with an increased incidence of venous thromboembolic disease compared to older (second generation), OC. It is not known, however, whether this association is also true for arterial thrombosis, in particular myocardial inf...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/(SICI)1099-1557(199707)6:4<283::AID-PDS270

    authors: Dunn NR,Thorogood M,de Caestecker L,Mann RD

    更新日期:1997-07-01 00:00:00

  • US adverse drug reaction surveillance 1989-1994.

    abstract::Adverse drug reaction surveillance conducted by the US Federal Food and Drug Administration (FDA) is important for detecting new safety information about pharmaceuticals. FDA has sought to stimulate reporting of reactions by practitioners and manufacturers. Over the five years from 1989 to 1993, reporting more than do...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/(SICI)1099-1557(199611)5:6<393::AID-PDS235

    authors: Faich GA

    更新日期:1996-11-01 00:00:00

  • An algorithm to derive a numerical daily dose from unstructured text dosage instructions.

    abstract:PURPOSE:The General Practice Research Database (GPRD) is a database of longitudinal patient records from general practices in the United Kingdom. It is an important data source for pharmacoepidemiology studies, but until now it has been tedious to calculate the daily dose and duration of exposure to drugs prescribed. T...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1151

    authors: Shah AD,Martinez C

    更新日期:2006-03-01 00:00:00

  • Use of psychotropic drugs and analgesics among users of antiobesity drugs--a population based study.

    abstract:AIM:The aim of the present study was to investigate to what extent patients using prescription antiobesity drugs (orlistat, sibutramine and rimonabant) concomitantly or concurrently used psychotropic drugs and analgesics and the association between this drug use and the patients' gender and age. An additional aim was t...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.1896

    authors: Amundsen MO,Engdahl B,Berg C,Nordeng H

    更新日期:2010-03-01 00:00:00

  • Variations and determinants of antibiotic consumption in Hungarian adult intensive care units.

    abstract:PURPOSE:The aim of this work was to study the use of systemic antibacterials and its possible determinants in Hungarian intensive care units (ICUs). METHODS:Hospital pharmacy. departments provided package level dispensing data for their corresponding ICU (2006). Data were converted into defined daily doses (DDDs) and ...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.2192

    authors: Benko R,Matuz M,Peto Z,Bogár L,Viola R,Doró P,Soós G,Hajdú E

    更新日期:2012-01-01 00:00:00

  • Reweighted Mahalanobis distance matching for cluster-randomized trials with missing data.

    abstract:PURPOSE:This paper introduces an improved tool for designing matched-pairs randomized trials. The tool allows the incorporation of clinical and other knowledge regarding the relative importance of variables used in matching and allows for multiple types of missing data. The method is illustrated in the context of a clu...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.3260

    authors: Greevy RA Jr,Grijalva CG,Roumie CL,Beck C,Hung AM,Murff HJ,Liu X,Griffin MR

    更新日期:2012-05-01 00:00:00

  • Addressing unmeasured confounding in comparative observational research.

    abstract:PURPOSE:Observational pharmacoepidemiological studies can provide valuable information on the effectiveness or safety of interventions in the real world, but one major challenge is the existence of unmeasured confounder(s). While many analytical methods have been developed for dealing with this challenge, they appear u...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章,评审

    doi:10.1002/pds.4394

    authors: Zhang X,Faries DE,Li H,Stamey JD,Imbens GW

    更新日期:2018-04-01 00:00:00

  • Trends in antipsychotic prescriptions for Japanese outpatients during 2006-2012: a descriptive epidemiological study.

    abstract:PURPOSE:This study aimed to assess the trends in antipsychotic prescriptions for outpatients in Japan, where a community-based approach to mental healthcare is emphasized. METHODS:This descriptive epidemiological study used claims data from 1038 community pharmacies across Japan. Outpatients who were ≥18 years old and...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4187

    authors: Kochi K,Sato I,Nishiyama C,Tanaka-Mizuno S,Doi Y,Arai M,Fujii Y,Matsunaga T,Ogawa Y,Furukawa TA,Kawakami K

    更新日期:2017-06-01 00:00:00

  • Comparison of the ability of double-robust estimators to correct bias in propensity score matching analysis. A Monte Carlo simulation study.

    abstract:OBJECTIVE:As covariates are not always adequately balanced after propensity score matching and double- adjustment can be used to remove residual confounding, we compared the performance of several double-robust estimators in different scenarios. METHODS:We conducted a series of Monte Carlo simulations on virtual obser...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.4325

    authors: Nguyen TL,Collins GS,Spence J,Devereaux PJ,Daurès JP,Landais P,Le Manach Y

    更新日期:2017-12-01 00:00:00

  • A large simple clinical trial prototype for assessment of OTC drug effects using patient-reported data.

    abstract:PURPOSE:Innovative methods are needed to assess risks related to treatment for common medical conditions, where therapy is usually patient-directed or over-the-counter (OTC), and where tolerability, i.e. patient experienced events, may affect patterns of use. A large-scale, blinded, randomised trial was conducted to co...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 临床试验,杂志文章,多中心研究,随机对照试验

    doi:10.1002/pds.1083

    authors: Van Ganse E,Jones JK,Moore N,Parc JM,Wall R,Schneid H

    更新日期:2005-04-01 00:00:00

  • Use of real-world evidence from healthcare utilization data to evaluate drug safety during pregnancy.

    abstract:PURPOSE:Because preapproval clinical trials typically exclude pregnant women, the evidence on drug safety during pregnancy required to inform drug labeling must come from postapproval controlled observational studies. Common designs have included pregnancy registries and case-control studies. Recently, pregnancy cohort...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章,评审

    doi:10.1002/pds.4789

    authors: Huybrechts KF,Bateman BT,Hernández-Díaz S

    更新日期:2019-07-01 00:00:00

  • Evaluation of the representativeness of a Dutch non-malformed control group for the general pregnant population: are these controls useful for EUROCAT?

    abstract:PURPOSE:A case-control study is the most powerful design to test the risk of specific congenital malformations associated with a specific drug. However, malformation registries often lack non-malformed controls. For the Dutch EUROCAT, we collected a non-malformed control group: the 'Healthy Pregnant'. The aim of this s...

    journal_title:Pharmacoepidemiology and drug safety

    pub_type: 杂志文章

    doi:10.1002/pds.2254

    authors: Jentink J,Zetstra-van der Woude AP,Bos J,de Jong-van den Berg LT

    更新日期:2011-11-01 00:00:00