Applied Medical Informatics, University Medical Center Eppendorf, Germany.
Pharmacy, University Medical Center Eppendorf, Germany.
Stud Health Technol Inform. 2023 Sep 12;307:22-30. doi: 10.3233/SHTI230689.
The diagnosis and treatment of Parkinson's disease depend on the assessment of motor symptoms. Wearables and machine learning algorithms have emerged to collect large amounts of data and potentially support clinicians in clinical and ambulant settings.
However, a systematical and reusable data architecture for storage, processing, and analysis of inertial sensor data is not available. Consequently, datasets vary significantly between studies and prevent comparability.
To simplify research on the neurodegenerative disorder, we propose an efficient and real-time-optimized architecture compatible with HL7 FHIR backed by a relational database schema.
We can verify the adequate performance of the system on an experimental benchmark and in a clinical experiment. However, existing standards need to be further optimized to be fully sufficient for data with high temporal resolution.
帕金森病的诊断和治疗取决于运动症状的评估。可穿戴设备和机器学习算法已经出现，可以收集大量数据，并有可能在临床和门诊环境中为临床医生提供支持。
然而，对于惯性传感器数据的存储、处理和分析，并没有一个系统的、可重复使用的数据架构。因此，不同研究之间的数据集差异很大，从而阻碍了可比性。
为了简化神经退行性疾病的研究，我们提出了一个高效的、实时优化的架构，与 HL7 FHIR 兼容，并由关系数据库模式支持。
我们可以在实验基准和临床实验中验证系统的性能是否足够。然而，现有的标准需要进一步优化，以便对具有高时间分辨率的数据完全适用。
Zotero 插件