Departments of Biostatistics.
Departments of Medicine.
Alzheimer Dis Assoc Disord. 2020 Oct-Dec;34(4):325-332. doi: 10.1097/WAD.0000000000000400.
Incidence of dementia increases exponentially with age; little is known about its risk factors in the ninth and 10th decades of life. We identified predictors of dementia with onset after age 85 years in a longitudinal population-based cohort.
On the basis of annual assessments, incident cases of dementia were defined as those newly receiving Clinical Dementia Rating (CDR) ≥1. We used a machine learning method, Markov modeling with hybrid density-based and partition-based clustering, to identify variables associated with subsequent incident dementia.
Of 1439 participants, 641 reached age 85 years during 10 years of follow-up and 45 of these became incident dementia cases. Using hybrid density-based and partition-based, among those aged 85+ years, probability of incident dementia was associated with worse self-rated health, more prescription drugs, subjective memory complaints, heart disease, cardiac arrhythmia, thyroid disease, arthritis, reported hypertension, higher systolic and diastolic blood pressure, and hearing impairment. In the subgroup aged 85 to 89 years, risk of dementia was also associated with depression symptoms, not currently smoking, and lacking confidantes.
An atheoretical machine learning method revealed several factors associated with increased probability of dementia after age 85 years in a population-based cohort. If independently validated in other cohorts, these findings could help identify the oldest-old at the highest risk of dementia.
痴呆症的发病率随年龄呈指数增长；在第九和第十个十年中，人们对其危险因素知之甚少。我们在一项纵向基于人群的队列研究中确定了 85 岁以后发病的痴呆症的预测因素。
基于年度评估，将痴呆症的新发病例定义为新接受临床痴呆评定量表（CDR）≥1 的病例。我们使用一种机器学习方法，即基于混合密度和基于分区的聚类的马尔可夫建模，来识别与随后发生的痴呆症相关的变量。
在 1439 名参与者中，有 641 名在 10 年的随访期间达到 85 岁，其中 45 名成为新发痴呆症病例。在 85 岁以上的人群中，使用基于混合密度和基于分区的聚类方法，痴呆症的发病概率与较差的自我评估健康状况、更多的处方药、主观记忆投诉、心脏病、心律失常、甲状腺疾病、关节炎、报告的高血压、更高的收缩压和舒张压以及听力障碍有关。在 85 岁至 89 岁的亚组中，痴呆症的风险还与抑郁症状、不吸烟和缺乏知己有关。
一种无理论机器学习方法揭示了基于人群的队列中 85 岁以上人群痴呆症发病概率增加的几个因素。如果在其他队列中得到独立验证，这些发现可以帮助确定痴呆症风险最高的最年长人群。
