Institute for Research on Socio-Economic Inequality, University of Luxembourg, Esch-sur-Alzette, Luxembourg.
Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
Sci Rep. 2024 Mar 20;14(1):6657. doi: 10.1038/s41598-024-56734-7.
Feasibility constraints limit availability of validated cognitive assessments in observational studies. Algorithm-based identification of 'probable dementia' is thus needed, but no algorithm developed so far has been applied in the European context. The present study sought to explore the usefulness of the Langa-Weir (LW) algorithm to detect 'probable dementia' while accounting for country-level variation in prevalence and potential underreporting of dementia. Data from 56 622 respondents of the Survey of Health, Ageing and Retirement in Europe (SHARE, 2017) aged 60 years and older with non-missing data were analyzed. Performance of LW was compared to a logistic regression, random forest and XGBoost classifier. Population-level 'probable dementia' prevalence was compared to estimates based on data from the Organisation for Economic Co-operation and Development. As such, application of the prevalence-specific LW algorithm, based on recall and limitations in instrumental activities of daily living, reduced underreporting from 61.0 (95% CI, 53.3-68.7%) to 30.4% (95% CI, 19.3-41.4%), outperforming tested machine learning algorithms. Performance in other domains of health and cognitive function was similar for participants classified 'probable dementia' and those self-reporting physician-diagnosis of dementia. Dementia classification algorithms can be adapted to cross-national cohort surveys such as SHARE and help reduce underreporting of dementia with a minimal predictor set.
可行性限制限制了观察性研究中经过验证的认知评估的可用性。因此，需要基于算法的“可能痴呆”识别，但到目前为止，还没有开发出适用于欧洲背景的算法。本研究旨在探讨 Langa-Weir（LW）算法在考虑到国家间痴呆患病率的差异和潜在的漏报率的情况下，检测“可能痴呆”的有用性。对年龄在 60 岁及以上且无缺失数据的 56622 名欧洲健康、老龄化和退休调查（SHARE，2017 年）受访者的数据进行了分析。比较了 LW 的性能与逻辑回归、随机森林和 XGBoost 分类器。与基于经济合作与发展组织数据的估计相比，比较了人群水平的“可能痴呆”患病率。因此，基于回忆和日常生活活动能力受限的特定患病率的 LW 算法的应用，将漏报率从 61.0%（95%CI，53.3-68.7%）降至 30.4%（95%CI，19.3-41.4%），优于测试的机器学习算法。对于被分类为“可能痴呆”的参与者和那些自我报告医生诊断为痴呆的参与者，在健康和认知功能的其他领域的表现相似。痴呆分类算法可以适应 SHARE 等跨国队列调查，并有助于用最小的预测器集减少痴呆的漏报。
