Subjective stress and alcohol use among young adult and adult drinkers: Systematic review of studies using Intensive Longitudinal Designs

Abstract

Background: Understanding how stress dynamically associates with alcohol use could provide a finer-grain resolution of drinking behavior, facilitating development of more effective and personalized interventions. The primary aim of this systematic review was to examine research using Intensive Longitudinal Designs (ILDs) to determine if greater naturalistic reports of subjective stress (e.g., those assessed moment-to-moment, day-to-day) in alcohol-drinkers associated with a) greater frequency of subsequent drinking, b) greater quantity of subsequent drinking, and c) whether between-/within-person variables moderate or mediate any relationships between stress and alcohol use. Methods: Using PRISMA guidelines, we searched EMBASE, PubMed, PsycINFO, and Web of Science databases in December 2020, ultimately identifying 18 eligible articles, representing 14 distinct studies, from a potential pool of 2,065 studies. Results: Results suggested subjective stress equivocally predicted subsequent alcohol use; in contrast, alcohol use consistently demonstrated an inverse relationship with subsequent subjective stress. These findings remained across ILD sampling strategy and most study characteristics, except for sample type (treatment-seeking vs. community/collegiate). Conclusions: Results appear to emphasize the stress-dampening effects of alcohol on subsequent stress levels and reactivity. Classic tension-reduction models may instead be most applicable to heavier-drinking samples and appear nuanced in lighter-drinking populations, and may depend on specific moderators/mediators (e.g., race/ethnicity, sex, relative coping-strategy use). Notably, a preponderance of studies utilized once-daily, concurrent assessments of subjective stress and alcohol use. Future studies may find greater consistency by implementing ILDs that integrate multiple within-day signal-based assessments, theoretically-relevant event-contingent prompts (e.g., stressor-occurrence, consumption initiation/cessation), and ecological context (e.g., weekday, alcohol availability).

Fig. 1

PRISMA Flow Diagram. Note: Format from Page et al. (2021).

Fig. 2

Sample Proportions for Sample Types, Sampling Rates, and Analytic Approach. Note: *"Distinct Studies" and "Distinct Study Samples" refers to studies whose data were drawn from unique populations. Several studies, noted by letter super-scripts in Tables 2-4, appeared to conduct multiple analyses on the same sample.

Fig. 3

Study Counts and Result Types According to Analytic Direction, and Sampling Strategy. Note: - = Negative association, + = positive association, NS = Non-significant association. ^aDenotes Helzer et al. (2006) who found negative association between stress and same-day consumption, but a non-significant negative trend for next-day consumption. ^bDenotes Luk et al. (2018) who found greater same- and next-day stress respectively predicted increased abstinence likelihood but was non-significantly associated with drinking quantity.