Conditional pathways to loneliness in older adults with vision impairment: a decision-tree analysis.
- 1Department of Counseling and Human Development, Warner School of Education and Human Development, University of Rochester, Rochester, New York, United States.
Abstract
Background and objectives
The prevalence of vision impairment continues to increase globally due to population growth and aging. Among older adults with vision impairment, loneliness is common. Prior studies assessing loneliness risk have relied on regression-based approaches, which may not capture complex, heterogeneous conditional pathways. We apply a theoretically guided machine learning approach to examine loneliness risk among older adults with age-related macular degeneration (AMD).Research design and methods
Using baseline data from 210 adults with AMD (Agemean = 80.1 years) enrolled in a randomized controlled trial, we applied a decision tree method using measures of legal blindness, emotional responses to vision loss, social life satisfaction, anxiety, depression, optimism, future planning, and sociodemographic factors to investigate heterogeneous pathways to loneliness.Results
Decision tree models demonstrated stable discrimination (AUCtrain = .88, AUCtest = .78, DeLong 95% confidence interval: 0.68-0.88) and robust classification performance across thresholds. Social life satisfaction emerged as the primary branching condition differentiating loneliness outcomes. Distinct pathways suggested that high social life satisfaction was strongly associated with lower loneliness; optimism served as a compensatory resource when social satisfaction was lower. Additional pathways highlighted the effects of vision loss severity, anxiety, and emotional responses to vision loss on loneliness. Depressive symptoms differentiated loneliness outcomes within a lower-anxiety branch, suggesting depression may overshadow protective factors.Discussion and implications
These findings suggest that loneliness arises through heterogeneous psychological pathways rather than single risk factors. By identifying conditional configurations of psychosocial and health-related factors, interpretable decision-tree models may inform more targeted screening, evaluation, and intervention strategies.
Related
- Loneliness, quality of life, and life satisfaction among older adults: the mediating role of resilience
- Sensory impairment, loneliness, and the emergence of physical-psychological-cognitive multimorbidity: a cross-national cohort study in China, the United States, and England.
- Associations of digital self-efficacy and social network connectedness with loneliness among urban older adults in kerman, iran: a cross-sectional study
- Participant Characteristics Associated With Loneliness Reduction During a Digital Social Robot Intervention Among Older Adults Living Alone in Japan: Secondary Analysis of a Randomized Controlled Trial
- Chronic loneliness and isolation phenotypes and physical and mental health in older adults
BibTeX
@article{chang2026conditional,
title = {{Conditional pathways to loneliness in older adults with vision impairment: a decision-tree analysis.}},
author = {Ya-Han Chang and Silvia Sörensen},
journal = {Innovation in aging},
year = {2026},
month = sep,
doi = {10.1093/geroni/igag102},
url = {https://europepmc.org/article/MED/42847076},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Conditional pathways to loneliness in older adults with vision impairment: a decision-tree analysis.
AU - Ya-Han Chang
AU - Silvia Sörensen
PY - 2026
DA - 2026/09/16
JO - Innovation in aging
DO - 10.1093/geroni/igag102
UR - https://europepmc.org/article/MED/42847076
AB - Background and objectives The prevalence of vision impairment continues to increase globally due to population growth and aging. Among older adults with vision impairment, loneliness is common. Prior studies assessing loneliness risk have relied on regression-based approaches, which may not capture complex, heterogeneous conditional pathways. We apply a theoretically guided machine learning approach to examine loneliness risk among older adults with age-related macular degeneration (AMD).Research design and methods Using baseline data from 210 adults with AMD (Agemean = 80.1 years) enrolled in a randomized controlled trial, we applied a decision tree method using measures of legal blindness, emotional responses to vision loss, social life satisfaction, anxiety, depression, optimism, future planning, and sociodemographic factors to investigate heterogeneous pathways to loneliness.Results Decision tree models demonstrated stable discrimination (AUCtrain = .88, AUCtest = .78, DeLong 95% confidence interval: 0.68-0.88) and robust classification performance across thresholds. Social life satisfaction emerged as the primary branching condition differentiating loneliness outcomes. Distinct pathways suggested that high social life satisfaction was strongly associated with lower loneliness; optimism served as a compensatory resource when social satisfaction was lower. Additional pathways highlighted the effects of vision loss severity, anxiety, and emotional responses to vision loss on loneliness. Depressive symptoms differentiated loneliness outcomes within a lower-anxiety branch, suggesting depression may overshadow protective factors.Discussion and implications These findings suggest that loneliness arises through heterogeneous psychological pathways rather than single risk factors. By identifying conditional configurations of psychosocial and health-related factors, interpretable decision-tree models may inform more targeted screening, evaluation, and intervention strategies.
SN - 2399-5300
ER -