Novel phenotype issues raised in cross-national epidemiological research on drug dependence

Abstract

Stage-transition models based on the American Diagnostic and Statistical Manual (DSM) generally are applied in epidemiology and genetics research on drug dependence syndromes associated with cannabis, cocaine, and other internationally regulated drugs (IRDs). Difficulties with DSM stage-transition models have surfaced during cross-national research intended to provide a truly global perspective, such as the work of the World Mental Health Surveys Consortium. Alternative simpler dependence-related phenotypes are possible, including population-level count process models for steps early and before coalescence of clinical features into a coherent syndrome (e.g., zero-inflated Poisson [ZIP] regression). Selected findings are reviewed, based on ZIP modeling of alcohol, tobacco, and IRD count processes, with an illustration that may stimulate new research on genetic susceptibility traits. The annual National Surveys on Drug Use and Health (NSDUH) can be readily modified for this purpose, along the lines of a truly anonymous research approach that can help make NSDUH-type cross-national epidemiological surveys more useful in the context of subsequent genomewide association (GWAS) research and post-GWAS investigations with a truly global health perspective.

Figure 1

Violation of the acyclic assumption. Often, there is an insidious onset of the drug dependence syndrome, once use starts. Plus, as the dependence develops, feedback loops appear, such that the choice to quit becomes more difficult. The count of drug experiences drives the dependence process, but in addition, the count is itself influenced by the dependence process. (Copyright, J.C. Anthony, 2009. Permission granted for use of this figure in J.C. Anthony Addiction Reviews article within which it is contained.)

Figure 2

Estimated Item Response Theory Discrimination Parameter Estimates from four sites of the World Mental Health Survey Consortium, based on standardized field survey assessments of the DSM-IV drug dependence syndrome with respect to internationally regulated drugs (primarily cannabis). Data from large multi-stage nationally representative population samples in each of six de-identified sites, 2002-2007.

Figure 3

The estimated risk of developing clinical features associated with tobacco dependence among recent-onset tobacco smokers, by age of onset (11-17 years versus >17 years), within 24 months after first onset of smoking. Data are from the National Household Survey on Drug Abuse and National Surveys on Drug Use and Health, 2000-2002 (Citation 28). The clinical feature abbreviations are explained in the text. [This figure was adapted and re-drawn from a previously published figure for which this article's author is responsible. Anthony et al., 2005].