Joint use of clinical parameters, biological markers and cage questionnaire for the identification of heavy drinkers in a large population-based sample

Aims: Alcohol consumption in France is one of the highest in the world. Factors associated with excessive alcohol drinking are numerous. However, taken separately, none of the existing clinical or biological markers of excessive alcohol intake enables an adequate identification of heavy drinkers. The aim of this cross-sectional survey was to identify socio-demographic, clinical and biological factors associated with excessive alcohol drinking, to develop a model and to assess its reliability, thus enabling the detection of heavy drinkers. Methods: Subjects were 1619 men and 1559 women, aged 35-64 years, living in three French areas (Lille, Strasbourg and Toulouse) and randomly selected from polling lists. Socio-demographic status, lifestyle, reported alcohol intake and answers to the CAGE questionnaire (alcohol dependence) were obtained by questionnaire. A blood sample was taken for quantification of biological parameters. Men who drank 60 g of ethanol a day (g/day) or above and women who drank 30 g/day or above were classified as heavy drinkers. The reference class (RC) gathered non-drinkers and moderate drinkers together. The sample was divided into two sub-samples: the first was used to estimate the parameters of a logistic regression model (heavy drinkers vs others), and the second to assess the accuracy of this model for the identification of heavy drinkers, using receiver operating characteristic (ROC) curves. A specific analysis was performed for each gender. Results: Fourteen per cent of men and 40.8% of women were non-drinkers. Nine per cent of women and 14.4% of men were heavy drinkers. Wine was the most consumed alcoholic beverage. In the univariate analyses, differences were observed between the two groups of alcohol consumers for most of the socio-demographic, clinical and biological variables considered. In the multivariate analyses, low educational level, smoking, apoprotein B, high density lipoprotein cholesterol, mean corpuscular volume (MCV), gamma-glutamyl-transferase (GGT) and the CAGE score for men, and living area, age, MCV, GGT and the CAGE score for women remained independently and significantly associated with heavy drinking. In the validation sub-sample, these models combining different types of markers enabled a good discrimination between heavy drinkers and the RC, with an area under the ROC curve of 82% for men and of 79% for women. Conclusions: In this study, socio-demographic, clinical and biological factors and the CAGE score were independently related to excessive alcohol drinking and their joint utilization in a screening model enabled a good recognition of heavy drinkers.