Journal of Alzheimer’s Disease 11 (2007) 313–321 313 IOS Press Alzheimer’s Disease and Smoking: Bias in Cohort Studies Sara M. Debanne a,∗ , Roger A. Bielefeld a,b , Vinay K. Cheruvu a , Thomas Fritsch d,e and Douglas Y. Rowland a,c a Department of Epidemiology & Biostatistics, School of Medicine, Case Western Reserve University, Cleveland, OH, USA b Department of Research Computing, Division of Information Technology Services, Case Western Reserve University, Cleveland, OH, USA c D Y Rowland Associates, 3189 Scarborough Road, Cleveland Heights, OH, USA d University Memory and Aging Center, University Hospitals of Cleveland and, Case Western Reserve University, Cleveland, OH, USA e Department of Neurology, School of Medicine, Case Western Reserve University, Cleveland, OH, USA Abstract. The discrepancy between cohort and case-control studies regarding the association between smoking and Alzheimer’s disease (AD) has been attributed to the competing risk of early mortality of smokers. A simulation study was conducted to show that the bias favoring smokers acts also on cohort studies. In the model, individuals grow older and have smoking habits according to published year-age-gender-specific patterns, with morbidity and mortality according to their demographic and smoking profiles. Those individuals dying of smoking-related causes (“phantoms”) remain at risk of AD and of death from other causes. Three scenarios were considered: no association of AD and smoking, increased risk for smokers, and decreased risk for smokers. For each simulation of a cohort study, two incidence density ratios (IDR) were computed: one including the phantoms that developed AD (thus ignoring smoking-related deaths) and another excluding them (thus mimicking real-life studies). For all scenarios, the simulations show that smoking-related death creates a bias, resulting in smokers having an understated risk of AD compared to non-smokers. The speculation that the conflicting results of case-control and cohort studies are solely due to the increased mortality in smokers thus appears unjustified. Other factors must also be considered to explain the discrepancy in results. Keywords: Alzheimer’s disease, smoking, bias, competing risk, Markov Chain, simulation, cohort studies INTRODUCTION There are conflicting results in the literature con- cerning the association of AD and smoking. Most of the studies that have reported a reduction in the risk of AD for smokers have been based on the case-control design [1,2], while results have been fairly consistent in showing the opposite effect when using a cohort ap- ∗ Address for correspondence: Sara M. Debanne, PhD, Depart- ment of Epidemiology and Biostatistics, School of Medicine, Case Western Reserve University, Cleveland, OH 44106-4945, USA. Tel.: +1 216 368 3895; Fax: +1 216 368 3970; E-mail: sara.debanne@ case.edu. proach [3–11]. Yet other studies have found no associ- ation [12–17]. It has been postulated that the reduction of risk seen with case-control studies is a spurious con- sequence of the competing risk of death due to smok- ing [12,15,18]. What happens in the absence of this competing risk cannot be seen in real-world studies, since it is not possible to predict with any degree of certainty whether someone who died at a fairly young age would have developed AD at a later time. The study reported here examined the effect of the competing risk of death from smoking-related caus- es acting on cohort studies by using simulation tech- niques. In this approach, cohort studies were repeat- edly simulated, where individuals dying of smoking- ISSN 1387-2877/07/$17.00  2007 – IOS Press and the authors. All rights reserved