{"title":"利用深度学习进行基于雷达的震颤量化,改进帕金森病和姑息治疗评估","authors":"Desar Mejdani;Johanna Bräunig;Stefan G. GrießHammer;Daniel Krauss;Tobias Steigleder;Lukas Engel;Jelena Jukic;Anna Rozhdestvenskaya;Jürgen Winkler;Bjoern Eskofier;Christoph Ostgathe;Martin Vossiek","doi":"10.1109/TRS.2024.3494473","DOIUrl":null,"url":null,"abstract":"Tremor is one of the most prevalent movement disorders, which is especially observed in patients with Parkinson’s disease (PD) and other conditions common in palliative care (PC). Effective treatment and monitoring of disease progression are crucial in the context of PC for patients suffering from movement disorders. To this aim, accurate and continuous detection and assessment of tremor characteristics, such as the tremor frequency, is required. Current evaluations by clinicians conducted during sporadic consultations are subjective and intermittent. Radar sensors provide continuous, objective evaluations of tremor motion in patient monitoring, offering a contactless, light-independent, and privacy-preserving method that directly measures tremor’s radial motion through the Doppler effect. As previous radar-based research lacks continuous tremor monitoring in realistic scenarios, this study uses a frequency-modulated continuous-wave (FMCW) radar to detect subtle tremor motions and estimates their frequencies amid challenges such as large body motion interference in a clinical setting. Seventeen healthy participants were instructed to mimic tremors in their right hand while performing three diagnostics movements frequently used in tremor assessment, and two activities that were inspired by common daily tasks encountered in PC settings. Tremor detection and frequency estimation was enabled using suitable radar signal preprocessing followed by a neural network comprising convolutional and recurrent layers. Reference frequencies were obtained from an inertial measurement unit (IMU) attached to the participants’ right hands. Cross-validation revealed a mean absolute error (MAE) of 1.47 Hz in radar-based frequency estimation compared with the reference and a 90% accuracy in distinguishing the presence or absence of tremor, highlighting the proposed approach’s high potential for future tremor assessment.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"2 ","pages":"1174-1185"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Radar-Based Tremor Quantification Using Deep Learning for Improved Parkinson’s and Palliative Care Assessment\",\"authors\":\"Desar Mejdani;Johanna Bräunig;Stefan G. GrießHammer;Daniel Krauss;Tobias Steigleder;Lukas Engel;Jelena Jukic;Anna Rozhdestvenskaya;Jürgen Winkler;Bjoern Eskofier;Christoph Ostgathe;Martin Vossiek\",\"doi\":\"10.1109/TRS.2024.3494473\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Tremor is one of the most prevalent movement disorders, which is especially observed in patients with Parkinson’s disease (PD) and other conditions common in palliative care (PC). Effective treatment and monitoring of disease progression are crucial in the context of PC for patients suffering from movement disorders. To this aim, accurate and continuous detection and assessment of tremor characteristics, such as the tremor frequency, is required. Current evaluations by clinicians conducted during sporadic consultations are subjective and intermittent. Radar sensors provide continuous, objective evaluations of tremor motion in patient monitoring, offering a contactless, light-independent, and privacy-preserving method that directly measures tremor’s radial motion through the Doppler effect. As previous radar-based research lacks continuous tremor monitoring in realistic scenarios, this study uses a frequency-modulated continuous-wave (FMCW) radar to detect subtle tremor motions and estimates their frequencies amid challenges such as large body motion interference in a clinical setting. Seventeen healthy participants were instructed to mimic tremors in their right hand while performing three diagnostics movements frequently used in tremor assessment, and two activities that were inspired by common daily tasks encountered in PC settings. Tremor detection and frequency estimation was enabled using suitable radar signal preprocessing followed by a neural network comprising convolutional and recurrent layers. Reference frequencies were obtained from an inertial measurement unit (IMU) attached to the participants’ right hands. Cross-validation revealed a mean absolute error (MAE) of 1.47 Hz in radar-based frequency estimation compared with the reference and a 90% accuracy in distinguishing the presence or absence of tremor, highlighting the proposed approach’s high potential for future tremor assessment.\",\"PeriodicalId\":100645,\"journal\":{\"name\":\"IEEE Transactions on Radar Systems\",\"volume\":\"2 \",\"pages\":\"1174-1185\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-11-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Radar Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10747547/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Radar Systems","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10747547/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
震颤是最常见的运动障碍之一,尤其见于帕金森病(PD)患者和姑息治疗(PC)中常见的其他疾病。有效治疗和监测疾病进展对于运动障碍患者的姑息治疗至关重要。为此,需要对震颤特征(如震颤频率)进行准确、持续的检测和评估。目前临床医生在零星会诊时进行的评估是主观和间歇性的。雷达传感器可在患者监测过程中对震颤运动进行连续、客观的评估,它提供了一种非接触、不受光线影响、保护隐私的方法,可通过多普勒效应直接测量震颤的径向运动。由于以往基于雷达的研究缺乏在现实场景中的连续震颤监测,本研究使用频率调制连续波(FMCW)雷达来检测微妙的震颤运动,并估算其频率,以应对临床环境中的大型体动干扰等挑战。17 名健康的参与者在进行震颤评估中常用的三个诊断动作和两个受 PC 环境中常见日常任务启发的活动时,被要求模仿右手的震颤。震颤检测和频率估算是通过适当的雷达信号预处理,然后利用由卷积层和递归层组成的神经网络实现的。参考频率由连接在参与者右手上的惯性测量单元(IMU)获得。交叉验证显示,与参考频率相比,基于雷达的频率估计平均绝对误差(MAE)为 1.47 Hz,区分是否存在震颤的准确率为 90%,这凸显了所提出的方法在未来震颤评估中的巨大潜力。
Radar-Based Tremor Quantification Using Deep Learning for Improved Parkinson’s and Palliative Care Assessment
Tremor is one of the most prevalent movement disorders, which is especially observed in patients with Parkinson’s disease (PD) and other conditions common in palliative care (PC). Effective treatment and monitoring of disease progression are crucial in the context of PC for patients suffering from movement disorders. To this aim, accurate and continuous detection and assessment of tremor characteristics, such as the tremor frequency, is required. Current evaluations by clinicians conducted during sporadic consultations are subjective and intermittent. Radar sensors provide continuous, objective evaluations of tremor motion in patient monitoring, offering a contactless, light-independent, and privacy-preserving method that directly measures tremor’s radial motion through the Doppler effect. As previous radar-based research lacks continuous tremor monitoring in realistic scenarios, this study uses a frequency-modulated continuous-wave (FMCW) radar to detect subtle tremor motions and estimates their frequencies amid challenges such as large body motion interference in a clinical setting. Seventeen healthy participants were instructed to mimic tremors in their right hand while performing three diagnostics movements frequently used in tremor assessment, and two activities that were inspired by common daily tasks encountered in PC settings. Tremor detection and frequency estimation was enabled using suitable radar signal preprocessing followed by a neural network comprising convolutional and recurrent layers. Reference frequencies were obtained from an inertial measurement unit (IMU) attached to the participants’ right hands. Cross-validation revealed a mean absolute error (MAE) of 1.47 Hz in radar-based frequency estimation compared with the reference and a 90% accuracy in distinguishing the presence or absence of tremor, highlighting the proposed approach’s high potential for future tremor assessment.