Tan Wei Ying, Hargreaves Carol Anne, Dawe Gavin S, Hsu Wynne, Lee Mong Li, Vipin Ashwati, Kandiah Nagaendran, Hilal Saima
Saw Swee Hock School of Public Health (WYT, SH), National University of Singapore and National University Health System, Singapore.
Office of the President (CAH), National University of Singapore, Singapore.
Am J Geriatr Psychiatry. 2025 Mar;33(3):229-244. doi: 10.1016/j.jagp.2024.07.016. Epub 2024 Aug 10.
The current evidence regarding how different predictor domains contributes to predicting incident dementia remains unclear. This study aims to assess the incremental value of five predictor domains when added to a simple dementia risk prediction model (DRPM) for predicting incident dementia in older adults.
Population-based, prospective cohort study.
UK Biobank study.
Individuals aged 60 or older without dementia.
Fifty-five dementia-related predictors were gathered and categorized into clinical and medical history, questionnaire, cognition, polygenetic risk, and neuroimaging domains. Incident dementia (all-cause) and the subtypes, Alzheimer's disease (AD) and vascular dementia (VaD), were determined through hospital and death registries. Ensemble machine learning (ML) DRPMs were employed for prediction. The incremental values of risk predictors were assessed using the percent change in Area Under the Curve (∆AUC%) and the net reclassification index (NRI).
The simple DRPM which included age, body mass index, sex, education, diabetes, hyperlipidaemia, hypertension, depression, smoking, and alcohol consumption yielded an AUC of 0.711 (± 0.008 SD). The five predictor domains exhibited varying levels of incremental value over the basic model when predicting all-cause dementia and the two subtypes. Neuroimaging markers provided the highest incremental value in predicting all-cause dementia (∆AUC% +9.6%) and AD (∆AUC% +16.5%) while clinical and medical history data performed the best at predicting VaD (∆AUC% +12.2%). Combining clinical and medical history, and questionnaire data synergistically enhanced ML DRPM performance.
Combining predictors from different domains generally results in better predictive performance. Selecting predictors involves trade-offs, and while neuroimaging markers can significantly enhance predictive accuracy, they may pose challenges in terms of cost or accessibility.
目前关于不同预测因子领域如何有助于预测新发痴呆症的证据仍不明确。本研究旨在评估将五个预测因子领域添加到一个简单的痴呆症风险预测模型（DRPM）中，对预测老年人新发痴呆症的增量价值。
基于人群的前瞻性队列研究。
英国生物银行研究。
60岁及以上无痴呆症的个体。
收集了55个与痴呆症相关的预测因子，并将其分为临床和病史、问卷、认知、多基因风险和神经影像领域。通过医院和死亡登记确定新发痴呆症（全因性）及其亚型，阿尔茨海默病（AD）和血管性痴呆（VaD）。采用集成机器学习（ML）DRPM进行预测。使用曲线下面积的百分比变化（∆AUC%）和净重新分类指数（NRI）评估风险预测因子的增量价值。
包含年龄、体重指数、性别、教育程度、糖尿病、高脂血症、高血压、抑郁症、吸烟和饮酒的简单DRPM的AUC为0.711（±0.008标准差）。在预测全因性痴呆症和两种亚型时，这五个预测因子领域相对于基本模型表现出不同程度的增量价值。神经影像标志物在预测全因性痴呆症（∆AUC% +9.6%）和AD（∆AUC% +16.5%）方面提供了最高的增量价值，而临床和病史数据在预测VaD方面表现最佳（∆AUC% +12.2%）。将临床和病史以及问卷数据相结合可协同提高ML DRPM的性能。
结合不同领域的预测因子通常会带来更好的预测性能。选择预测因子需要权衡，虽然神经影像标志物可以显著提高预测准确性，但在成本或可及性方面可能存在挑战。
