期刊
FRONTIERS IN NEUROLOGY
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fneur.2021.678484
关键词
Huntington's disease; disease progression; prognostic variables; machine learning; random forest
资金
- CHDI Foundation
This study investigated potential prognostic variables in patients with Huntington's disease (HD) using the Enroll-HD cohort and trained a random forest regression model to predict clinical outcomes. Novel predictors such as being accompanied at clinical visit and cognitive impairment, in addition to established predictors like CAG repeat length, were found to improve the model's ability to predict clinical outcomes. These novel prognostic variables may be considered for statistical control in HD clinical studies.
Huntington's disease (HD) is characterised by a triad of cognitive, behavioural, and motor symptoms which lead to functional decline and loss of independence. With potential disease-modifying therapies in development, there is interest in accurately measuring HD progression and characterising prognostic variables to improve efficiency of clinical trials. Using the large, prospective Enroll-HD cohort, we investigated the relative contribution and ranking of potential prognostic variables in patients with manifest HD. A random forest regression model was trained to predict change of clinical outcomes based on the variables, which were ranked based on their contribution to the prediction. The highest-ranked variables included novel predictors of progression-being accompanied at clinical visit, cognitive impairment, age at diagnosis and tetrabenazine or antipsychotics use-in addition to established predictors, cytosine adenine guanine (CAG) repeat length and CAG-age product. The novel prognostic variables improved the ability of the model to predict clinical outcomes and may be candidates for statistical control in HD clinical studies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据