文献类型： 会议论文

第一作者： ELIAS CHAIBUB NETO

作者： ELIAS CHAIBUB NETO ¹ ; BRIAN M. BOT ¹ ; THANNEER PERUMAL ¹ ; LARSSON OMBERG ¹ ; JUSTIN GUINNEY ¹ ; MIKE KELLEN ¹ ; ARNO KLEIN ¹ ; STEPHEN H. FRIEND ¹ ; ANDREW D. TRISTER ¹ ;

作者机构： 1.Sage Bionetworks, 1100 Fairview Avenue North, Seattle, Washington 98109, USA

关键词： personalized medicine;hypothesis tests;sensor data;remote monitoring;Parkinson

会议名称： Pacific Symposium on Biocomputing

主办单位：

页码： 273-284

摘要： We propose hypothesis tests for detecting dopaminergic medication response in Parkinson disease patients, using longitudinal sensor data collected by smartphones. The processed data is composed of multiple features extracted from active tapping tasks performed by the participant on a daily basis, before and after medication, over several months. Each extracted feature corresponds to a. time series of measurements annotated according to whether the measurement was taken before or after the patient has taken his/her medication. Even though the data is longitudinal in nature, we show that simple hypothesis tests for detecting medication response, which ignore the serial correlation structure of the data, are still statistically valid, showing type I error rates at the nominal level. We propose two distinct personalized testing approaches. In the first, we combine multiple feature-specific tests into a single union-intersection test. In the second, we construct personalized classifiers of the before/after medication labels using all the extracted features of a given participant, and test the null hypothesis that the area under the receiver operating characteristic curve of the classifier is equal to 1/2. We compare the statistical power of the personalized classifier tests and personalized union-intersection tests in a simulation study, and illustrate the performance of the proposed tests using data from mPower Parkinsons disease study, recently launched as part of Apples ResearchKit mobile platform. Our results suggest that the personalized tests, which ignore the longitudinal aspect of the data, can perform well in real data analyses, suggesting they might be used as a sound baseline approach, to which more sophisticated methods can be compared to.

分类号： Q811