Summary: Using artificial intelligence technology, researchers have identified both risk and protective factors for depression in middle-aged to older adults. Social isolation, according to the study, was the biggest risk factor for depression, followed by mobility difficulties and health problems.
Source: Colorado State University
Depression is one of the leading causes of disability worldwide, with middle-aged and older adults disproportionately affected, a growing global demographic.
To better understand the reasons for how this age group develops a depressive disorder, commonly referred to as depression, Stephen Aichele, assistant professor in the Department of Human Development and Family Studies at Colorado State University, and his team used a machine learning approach to analyze data from a large representative sample of the population of middle-aged and older European adults.
This is one of the few studies to use such an approach to compare many risk and protective factors for depression later in life, and is likely the first to apply it so broadly within this community. population (with 18 European countries represented and 56 risk and protective factors). factors considered).
Depression risk factors
Of 56 variables examined, Aichele and her team found that for both men and women, social isolation was the main risk factor for depression, followed by poor general health and mobility difficulties.
Other recent studies have identified social isolation as a key risk factor for depression in older adults, but Aichele and her team also looked at 30 variables related to specific dimensions of participants’ social networks and family configurations, such as as the frequency of contacts, the number of friends. , and interpersonal transactions related to physical care and financial support.
“It’s less about the frequency of contact or how many friends you have,” Aichele said. “It’s more about physical closeness to the person you feel emotionally closest to, whether it’s your spouse, partner, or another primary social relationship.”
For men, a fourth key risk factor was difficulty with instrumental activities of daily living, such as managing finances, taking medications, and making phone calls. For women, a fourth key risk factor was family burden – women who strongly agreed that ‘family responsibilities prevent me from doing the things I want to do’ were at high risk for depression . However, these sex-specific factors explained only a small proportion of the differences in depression risk.
“The prevalence of depression in older women is about twice as high as in older men,” Aichele said. “And yet the same primary risk factors appear for both (social isolation, poor health, mobility problems). The reason for this discrepancy has not been resolved, at least by this study.
Cognition and Health Analytics
Research in Aichele’s lab focuses on using advanced statistical approaches to understand age- and disease-related changes in cognition and mental health after middle age. Aichele’s first published study to use machine learning showed that the age-related decline in information processing speed of older adults was strongly related to mortality risk – comparable in its predictive effect to knowledge of a person’s smoking history.
More recently, Aichele and colleagues used “bivariate latent change score models”, a type of time series analysis, to show that a decline in memory and problem-solving performance at a given age precedes reliably a two- to three-year increase in depressive symptoms in the elderly.
“If we can detect cognitive decline early enough, there may be a window of time to prevent associated increases in depression risk,” Aichele said. “The question then becomes what factors exacerbate or attenuate the effects of cognitive loss on depression.”
To achieve this goal, Aichele and her team again used a machine learning approach, random forest analysis (RFA), to compare risk and protective factors for depression using data from the Survey on Health, Aging and Retirement in Europe (SHARE).
Study participants ranged in age from 45 to 105 and represented 18 European countries. SHARE data covers a wide range of socio-demographic, health-related, economic and cognitive variables. Importantly, SHARE also includes multiple measures of participants’ relational networks.
“We wanted to target a wide variety of risk and protective factors for depression,” Aichele said. “And we felt it would be particularly important to examine different dimensions of social and relational support given that self-reported social isolation may be more closely related to some factors than others.”
The RFA methodology was chosen for the analyzes because it considers potentially complex interactions between risk factors (eg, between memory problems and the quality of social interactions) in rankings of risk factor importance.
“Conventional statistical approaches are ill-suited to comprehensively test these complex associations,” Aichele said.
About this depression research
Original research: Free access.
“Predictors of depression in middle-aged and older men and women in Europe: a machine learning approach” by Elizabeth P. Handing et al. The Lancet Regional Health – Europe
Predictors of depression in middle-aged and older men and women in Europe: a machine learning approach
The high prevalence of depression in a growing aging population represents a critical public health issue. It is unclear how social, health, cognitive, and functional variables rank as risk/protective factors for depression in older adults and whether there are clear differences between men and women.
We used random forest analysis (RFA), a machine learning method, to compare 56 risk/protective factors for depression in a large representative sample of European older adults (N=67,603; aged 45 at age 105; 56.1% women; 18 countries) from the Survey on Health, Aging and Retirement in Europe (SHARE Wave 6). Depressive symptoms were assessed using the EURO-D questionnaire: scores ≥ 4 indicated depression. Predictors included a wide range of sociodemographic, relationship, health, lifestyle, and cognitive variables.
Self-rated social isolation and poor self-rated health were the strongest risk factors, accounting for 22.0% (in men) and 22.3% (in women) of depression variability. The odds ratios (OR) per +1SD in social isolation were 1.99x, 95% CI [1.90,2.08] at men’s; 1.93x, 95% CI [1.85,2.02] in women. The OR for poor self-rated health was 1.93x, 95% CI [1.81,2.05] at men’s; 1.98x, 95% CI [1.87,2.10] in women. Mobility difficulties (in both sexes), difficulty in instrumental activities of daily living (in men) and higher self-rated family burden (in women) accounted for an additional but small percentage variance in depression risk (2.2% in men, 1.5% in women).
Among 56 predictors, self-perceived social isolation and self-rated poor health were the most salient risk factors for depression in middle-aged and older men and women. Difficulties in instrumental activities of daily living (in men) and increased family burden (in women) seem to influence the risk of depression differently according to gender.
This study was internally funded by Colorado State University with research seed funds provided to Stephen Aichele, Ph.D.