Predictors of Dementia in the Oldest Old: A Novel Machine Learning Approach.
Predictors of Dementia in the Oldest Old: A Novel Machine Learning Approach.
复制标题
DOI：
10.1097/wad.0000000000000400
复制
发表时间：
2020-10
影响因子：
2.1
通讯作者：
Ganguli M
中科院分区：
文献类型：
--
作者：
Jia Y;Chang CH;Hughes TF;Jacobsen E;Wang S;Berman SB;Kamboh MI;Ganguli M
痴呆症的发病率随着年龄的增长呈指数增长；在生命的第九和第十个十年，人们对其风险因素知之甚少。我们在纵向人群队列中确定了85岁以后发病的痴呆的预测因素。根据年度评估，痴呆事件病例定义为新近接受临床痴呆评分（CDR®）≥1的患者。我们使用机器学习方法，利用HyDaP聚类进行马尔可夫建模，以识别与后续痴呆事件相关的变量。在1439名参与者中，641人在10年的随访中达到85岁，其中45人成为偶发性痴呆病例。使用HyDaP，在85岁以上的人群中，发生痴呆的概率与自我评价健康状况较差、服用更多处方药、主观记忆抱怨、心脏病、心律失常、甲状腺疾病、关节炎、高血压、收缩压和舒张压升高以及听力障碍相关。在85 - 89岁的亚组中，痴呆的风险还与抑郁症状、目前不吸烟和缺乏知己有关。在一项基于人群的队列研究中，一种理论机器学习方法揭示了与85岁以后痴呆概率增加相关的几个因素。如果在其他队列中独立验证，这些发现可以帮助确定痴呆症风险最高的老年人。
Incidence of dementia increases exponentially with age; little is known about its risk factors in the ninth and tenth decades of life. We identified predictors of dementia with onset after age 85y in a longitudinal population-based cohort. Based on 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 HyDaP clustering, to identify variables associated with subsequent incident dementia. Of 1,439 participants, 641 reached age 85y during ten years of follow-up and 45 of these became incident dementia cases. Using HyDaP, among those aged 85+y, 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 85–89y, 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 85y 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.