Association between social networks and discussions regarding advance care planning among Japanese older adults

Background Older adults' discussions with family, or with physicians, or with both, about advance care planning (ACP) are increasingly regarded as important for the management of end-of-life care, and yet the factors that induce older adults to engage in ACP discussions are poorly understood. For example, in older adults, is stronger connectedness with family and friends (stronger "networks") associated with ACP discussions? By facilitating, or by impeding ACP discussions? We sought to evaluate the associations between ACP discussions and social networks in Japanese older adults. Methods In July 2016 we conducted a cross-sectional survey on 355 community-dwelling patients aged. 65 years visiting community hospital clinics in Fukushima, Japan. We used the Lubben Social Network Scale (LSNS-6, the shortest available LSNS scale) to assess social networks and recorded two components of social network structure, marital status (dichotomized as "married" vs. "single / other") and living status ("living with others" vs. "living alone"). One item asked if patients had had ACP discussions. We analyzed the LSNS-6 social network and marital and living status data in relation to the occurrence of ACP discussions using multiple logistic regression models with adjustments for possible confounding factors. Results Respondents' social network was "limited" in 16% of cases; 61% had had ACP discussions. Respondents with a limited social network had a significantly lower tendency to have had ACP discussions than respondents with an "adequate" social network (adjusted odds ratio [AOR]: 0.35; 95% confidence interval [CI]: 0.18-0.66; P < 0.001). Marital status and living status were not significantly associated with ACP discussion. Conclusions Among Japanese older adults, weaker social networks may be associated with a lower tendency to discuss ACP. Our findings may help practitioners to quickly screen populations at risk for inadequate ACP discussion by using the LSNS-6.