Comparing the effectiveness of a brief intervention to reduce unhealthy alcohol use among adult primary care patients with and without depression: A machine learning approach with augmented inverse probability weighting.

BACKGROUND: The combination of unhealthy alcohol use and depression is associated with adverse outcomes including higher rates of alcohol use disorder and poorer depression course. Therefore, addressing alcohol use among individuals with depression may have a substantial public health impact. We compared the effectiveness of a brief intervention (BI) for unhealthy alcohol use among patients with and without depression. METHOD: This observational study included 312,056 adult primary care patients at Kaiser Permanente Northern California who screened positive for unhealthy drinking between 2014 and 2017. Approximately half (48%) received a BI for alcohol use and 9% had depression. We examined 12-month changes in heavy drinking days in the previous three months, drinking days per week, drinks per drinking day, and drinks per week. Machine learning was used to estimate BI propensity, follow-up participation, and alcohol outcomes for an augmented inverse probability weighting (AIPW) estimator of the average treatment (BI) effect. This approach does not depend on the strong parametric assumptions of traditional logistic regression, making it more robust to model misspecification. RESULTS: BI had a significant effect on each alcohol use outcome in the non-depressed subgroup (-0.41 to -0.05, all ps < .003), but not in the depressed subgroup (-0.33 to -0.01, all ps > .28). However, differences between subgroups were nonsignificant (0.00 to 0.11, all ps > .44). CONCLUSION: On average, BI is an effective approach to reducing unhealthy drinking, but more research is necessary to understand its impact on patients with depression. AIPW with machine learning provides a robust method for comparing intervention effectiveness across subgroups.

Associations between young informal caring and mental health: a prospective observational study using augmented inverse probability weighting.

BACKGROUND: Across the world, many young people are supplying unpaid, informal care. There is growing evidence of the impact of this caring role on the lives of young informal carers, however there has been little quantitative analysis of the mental health impacts. This research aimed to estimate the effect of informal caring at age 14/15 years on mental health at age 18/19 years. METHOD: Data was drawn from Waves 5, 6, 8 (2012-2018) of the Longitudinal Study of Australian Children. Effects of caring on mental health were assessed using augmented inverse probability weighting, with adjustment for potential confounders, and using the Kessler-10 measure of mental health. Caring was assessed with both a binary (any caring vs none), and a three category variable (no caring, less than daily caring, daily caring). Multiple imputation was carried out using chained equations, and analysis was conducted on both complete case (n=2165) and the imputed dataset (n=3341). OUTCOMES: In complete case models, any caring at age 14/15 years was associated with poorer mental health at age 18/19 years compared to those reporting no caring, with an average treatment effect (ATE) of 1.10 (95%CI 0.37, 1.83). The ATE of daily caring compared to no caring at age 14/15 years of age was 1.94 (95%CI 0.48, 3.39), and caring less than daily (compared to no caring) was associated with a treatment effect of 0.83(95%CI 0.06, 1.61). Associations were robust to several sensitivity analyses. INTERPRETATION: These results suggest there is a mental health impact of caring in adolescence on mental health four years later. This highlights the need for support for young informal carers, particularly for those providing more intensive caring. FUNDING: This study was supported by an Australian Research Council Discovery Early Career Award (TK, DE200100607).