A systematic review and meta-analysis of prospective associations between alcohol consumption and incident frailty

Background: light-to-moderate alcohol consumption is protective against all-cause mortality and cardiovascular diseases. There is limited evidence in the literature on how alcohol consumption is related to frailty. Methods: five databases (Embase, Scopus, MEDLINE, CINAHL, PsycINFO) were systematically searched in July 2016 for prospective studies published between 2000 and 2016 examining baseline alcohol consumption and subsequent frailty risk among middle-aged or older community-dwelling population. Odds ratios (ORs) for incident frailty were pooled using a random-effects model. Heterogeneity, methodological quality and publication bias were assessed. Results: of 926 studies identified by the systematic search, four studies were included (total n = 44,051, >= 55 years, 66.2% alcohol users). OR of incident frailty for the highest (at least 24 g of alcohol/day for men, 12g of alcohol/day for women) or the most frequent (>= 5 days of drinking/week) alcohol consumption compared with no drinking were used for a metaanalysis. Pooled OR among three studies measuring alcohol consumption quantitatively showed that the highest alcohol consumption was associated with lower frailty risk (3 studies: pooled OR = 0.44, 95% CI = 0.19-1.00, P = 0.05). Adding the other study measuring frequency of alcohol consumption made little change (4 studies: pooled OR = 0.61, 95% CI = 0.44-0.77, P < 0.001). Two of the included studies suggested a possible U-shaped association with lowest risks for moderate drinkers. Heterogeneity was moderate in both analyses (I-2 = 52-67%). There was no evidence of publication bias. Conclusions: this systematic review and meta-analysis study provides the first pooled evidence suggesting that heavier alcohol consumption is associated with lower incident frailty compared with no alcohol consumption among community-dwelling middle-aged and older people. However, this association may be due to unadjusted effect measures, residual confounding, 'sick quitter' effect or survival bias.