Search

• Older adults with ADL or IADL dependencies had a higher risk of unmet healthcare needs. • Dependency in any component of ADL or IADL was associated with the risk of unmet healthcare needs after adjusting comorbidities. • Not only mobility dependencies but also dependencies in the non-mobility components of ADL or IADL led to a high risk of unmet healthcare needs. • To reduce unmet healthcare needs, integration of health and social care supporting ADL or IADL dependency could be considered. Purpose: To determine the impact of overall and component-wise activities for daily living (ADL) as well as instrumental activities of daily living (IADL) dependencies on unmet healthcare needs in older adults. Materials and Methods: Cross-sectional analyses were performed based on a National Survey of Older Koreans. A total of 10,082 participants aged ≥ 65 years were included. All data were collected through standardized, personal interviews with participants and their representatives. Logistic regression was used to analyse the risk of unmet healthcare needs, with or without adjustment. Results: Amongst all participants, 734 (7.2%) had ADL dependency. Participants with ADL dependency had lower income, education level, and perceived health status (p <0.001). The adjusted odds ratio (aOR) for the risk of unmet healthcare needs was 1.52 (95%, confidence interval [CI] 1.19–1.95) for ADL and 1.54 (95%, CI 1.28–1.86) for IADL. When men have ADL dependency, aOR of unmet healthcare needs was higher than that of women (aOR 1.89, 95% CI 1.15 - 3.11; aOR 1.65, 95% CI 1.15 - 2.36, respectively) and IADL showed the same trend. Any dependency on ADL or IADL was associated with higher risk of unmet healthcare needs, whether adjusted or not (p <0.001). Conclusions: Older adults with ADL or IADL dependency had higher risks of unmet healthcare needs than their independent counterparts. In addition to mobility problems, other components were related to unmet healthcare needs. Therefore, to reduce unmet healthcare needs, integration of health and social care that supports ADL or IADL dependency should be considered. [ABSTRACT FROM AUTHOR]

• The machine learning methods help researchers select the predictors of health status in the older population efficiently. • The machine learning methods automatically capture the complicated relationships between the non-linear predictors and the health outcomes. • The artificial neural networks have the best prediction accuracy in relation to older people's self-reported health. Health and social care services are crucial to old people. The provision of services to the elderly with care needs requires more accurate predictions of the health status of the elderly to rationalize the allocation of the limited social care resources. The traditional analytical methods have proved incapable of predicting the demands of today's society, compared to which machine learning methods can more accurately capture the nonlinear relationships between the variables. To ascertain visually the performance of these machine learning methods regarding the prediction of the elderly's care needs, we designed and verified the experiment. [ABSTRACT FROM AUTHOR]