Predicting Parkinson's Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data
Predicting Parkinson's Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data
复制标题
DOI：
10.1109/icdm50108.2020.00133
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Weijian Li;Wei Zhu;E. Dorsey;Jiebo Luo
中科院分区：
文献类型：
--
作者：
Weijian Li;Wei Zhu;E. Dorsey;Jiebo Luo
帕金森氏症是一种神经系统疾病，常见于老年人。传统的疾病诊断方法依赖于对一组活动测试的质量进行面对面的主观临床评估。如今，智能手机应用程序收集的高分辨率纵向活动数据使进行远程和方便的健康评估成为可能。然而，实验室外的测试往往受到质量控制不佳以及收集的观察结果不规律的影响，导致测试结果嘈杂。为了解决这些问题，我们提出了一种新的基于时间序列的方法，通过智能手机在野外收集的原始活动测试数据来预测帕金森病。该方法首先在统一的时间点将离散的活动测试同步为多模态特征。接下来，它通过两个关注模块从模态和时间观测的噪声数据中提取和丰富局部和全局表示。利用提出的机制，我们的模型能够处理有噪声的观测，同时提取精细的时间特征，以提高预测性能。在大型公共数据集上的定量和定性结果证明了所提出方法的有效性。
Parkinson's Disease is a neurological disorder and prevalent in elderly people. Traditional ways to diagnose the disease rely on in-person subjective clinical evaluations on the quality of a set of activity tests. The high-resolution longitudinal activity data collected by smartphone applications nowadays make it possible to conduct remote and convenient health assessment. However, out-of-lab tests often suffer from poor quality controls as well as irregularly collected observations, leading to noisy test results. To address these issues, we propose a novel time-series based approach to predicting Parkinson's Disease with raw activity test data collected by smartphones in the wild. The proposed method first synchronizes discrete activity tests into multimodal features at unified time points. Next, it distills and enriches local and global representations from noisy data across modalities and temporal observations by two attention modules. With the proposed mechanisms, our model is capable of handling noisy observations and at the same time extracting refined temporal features for improved prediction performance. Quantitative and qualitative results on a large public dataset demonstrate the effectiveness of the proposed approach.