摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报告的主题。根据New sRx记者在意大利卡坦扎罗的新闻报道，研究表明：“区分震颤占主导地位的帕金森病Di Sease(tPD)和伴有静止震颤的原发性震颤(rET)可能具有挑战性，通常需要多巴胺成像。本研究旨在通过基于静止震颤(RT)电生理特征和结构MRI数据的机器学习(ML)方法来区分这两种疾病。”我们纳入72名患者，包括40名tPD患者和32名rET患者，以及45名对照受试者(HC)。应用表面肌电图(sEMG)计算RT电生理特征(频率、振幅和相位)。几个MRI形态测量变量(皮质厚度、表面积、皮质/皮质下体积、粗糙度、采用MRI和/或电生理数据对tPD和rET患者进行了基于树型分类算法的ML模型和/或电生理数据的ML模型进行了区分，结构MRI和sEMG数据在区分两组患者方面均显示出可接受的性能，基于电生理数据的模型比仅基于MRI数据的模型稍好(平均AUC:0.92和0.87，表现最好的模型使用了sEMG FEA(振幅和相位)和MRI数据(皮质体积、表面积和ME曲率)的组合，达到AUC:0.97±0.03，表现最好的模型使用单独的MRI(=0.0001)或EMG数据(=0.0231)。在最好的模型中，最重要的特征是RT相位。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting from Catanzaro, Italy, by New sRx journalists, research stated, "Distinguishing tremor-dominant Parkinson's di sease (tPD) from essential tremor with rest tremor (rET) can be challenging and often requires dopamine imaging. This study aimed to differentiate between these two diseases through a machine learning (ML) approach based on rest tremor (RT) electrophysiological features and structural MRI data." The news correspondents obtained a quote from the research from University Magna Graecia, "We enrolled 72 patients including 40 tPD patients and 32 rET patients , and 45 control subjects (HC). RT electrophysiological features (frequency, amp litude, and phase) were calculated using surface electromyography (sEMG). Severa l MRI morphometric variables (cortical thickness, surface area, cortical/subcort ical volumes, roughness, and mean curvature) were extracted using Freesurfer. ML models based on a treebased classification algorithm termed XGBoost using MRI and/or electrophysiological data were tested in distinguishing tPD from rET pati ents. Both structural MRI and sEMG data showed acceptable performance in disting uishing the two patient groups. Models based on electrophysiological data perfor med slightly better than those based on MRI data only (mean AUC: 0.92 and 0.87, respectively; = 0.0071). The top-performing model used a combination of sEMG fea tures (amplitude and phase) and MRI data (cortical volumes, surface area, and me an curvature), reaching AUC: 0.97 ? 0.03 and outperforming models using separate ly either MRI ( = 0.0001) or EMG data ( = 0.0231). In the best model, the most i mportant feature was the RT phase."
NETL
NSTL