生物医学工程

低资源环境下全自动儿童人体测量三维成像系统的准确性:南苏丹马拉卡尔的有效性评估

2022 - 10 - 21 - t09:00:04内

背景:在人道主义环境中采用3D成像系统需要与人工测量相当的精度，尽管与严峻环境相关的额外限制。目的:本研究旨在评估由Body Surface Translations公司开发的autoanthroo 3D成像系统(第三代)产生的儿童身高和中上臂围(MUAC)测量的准确性。方法:在2021年9月至2021年10月期间在南苏丹Malakal平民保护站点进行的两阶段聚集调查中嵌入了设备准确性的研究。选定家庭中所有6至59个月的儿童都符合条件。对于每个儿童，由2名人体测量学家按照2006年世界卫生组织儿童生长标准研究中使用的方案进行手动测量。扫描结果随后由另一名枚举员使用装有定制软件AutoAnthro的三星Galaxy 8手机和英特尔RealSense 3D扫描仪捕获。扫描是用全自动算法处理的。采用多元逻辑回归模型来评估调整后的扫描成功率。测量的准确性使用Bland-Altman图进行视觉评估，并使用平均偏倚、一致限(LoAs)和个体差异的95%精度区间进行量化。调查人员和Body Surface Translations公司的开发人员远程采访了关键信息提供者，以了解beta测试、培训、数据获取和传输方面的挑战。结果: 539名符合条件的儿童获得了手工测量，其中234名(43.4%)成功处理了扫描衍生的测量。 Caregivers of at least 10.4% (56/539) of the children refused consent for scan capture; additional scans were unsuccessfully transmitted to the server. Neither the demographic characteristics of the children (age and sex), stature, nor MUAC were associated with availability of scan-derived measurements; team was significantly associated (P<.001). The average bias of scan-derived measurements in cm was −0.5 (95% CI −2.0 to 1.0) for stature and 0.7 (95% CI 0.4-1.0) for MUAC. For stature, the 95% LoA was −23.9 cm to 22.9 cm. For MUAC, the 95% LoA was −4.0 cm to 5.4 cm. All accuracy metrics varied considerably by team. The COVID-19 pandemic–related physical distancing and travel policies limited testing to validate the device algorithm and prevented developers from conducting in-person training and field oversight, negatively affecting the quality of scan capture, processing, and transmission. Conclusions: Scan-derived measurements were not sufficiently accurate for the widespread adoption of the current technology. Although the software shows promise, further investments in the software algorithms are needed to address issues with scan transmission and extreme field contexts as well as to enable improved field supervision. Differences in accuracy by team provide evidence that investment in training may also improve performance.

家庭自行车运动的远程监控:无线接口的评估

2022 - 10 - 12 - t09:15:03内

背景:远程康复在扩大康复服务可及性、提高患者生活质量和改善临床结果方面具有巨大潜力。固定自行车运动可以作为一个有效的有氧组成部分，以家庭为基础的身体康复计划。远程监测骑自行车锻炼为确保患者在家坚持锻炼和安全提供了必要的保障。目前对自行车运动解决方案的远程监测的可扩展性受到高成本的阻碍，这限制了患者获得这些服务，特别是在患有慢性疾病的老年人中。该项目的目的是设计和测试两个低成本的无线接口，用于家庭自行车运动的远程监控。我们设计了一个交互式自行车系统(iBikE)，该系统由平板电脑和低成本自行车组成。构建并测试了两个用于监控每分钟转数(RPM)的无线接口。第一个版本的iBikE系统使用蓝牙低功耗(BLE)将信息从iBikE发送到PC平板电脑，第二个版本使用Wi-Fi网络进行通信。这两种系统都为患者和他们的临床团队提供了使用简单的图形表示实时监控运动进度的能力。该自行车可用于上肢或下肢康复。 We developed two tablet applications with the same graphical user interfaces between the application and the bike sensors but with different communication protocols (BLE and Wi-Fi). For testing purposes, healthy adults were asked to use an arm bike for three separate subsessions (1 minute each at a slow, medium, and fast pace) with a 1-minute resting gap. While collecting speed values from the iBikE application, we used a tachometer to continuously measure the speed of the bikes during each subsession. Collected data were later used to assess the accuracy of the measured data from the iBikE system. Results: Collected RPM data in each subsession (slow, medium, and fast) from the iBikE and tachometer were further divided into 4 categories, including RPM in every 10-second bin (6 bins), RPM in every 20-second bin (3 bins), RPM in every 30-second bin (2 bins), and RPM in each 1-minute subsession (60 seconds, 1 bin). For each bin, the mean difference (iBikE and tachometer) was then calculated and averaged for all bins in each subsession. We saw a decreasing trend in the mean RPM difference from the 10-second to the 1-minute measurement. For the 10-second measurements during the slow and fast cycling, the mean discrepancy between the wireless interface and tachometer was 0.67 (SD 0.24) and 1.22 (SD 0.67) for the BLE iBike, and 0.66 (SD 0.48) and 0.87 (SD 0.91) for the Wi-Fi iBike system, respectively. For the 1-minute measurements during the slow and fast cycling, the mean discrepancy between the wireless interface and tachometer was 0.32 (SD 0.26) and 0.66 (SD 0.83) for the BLE iBike, and 0.21 (SD 0.21) and 0.47 (SD 0.52) for the Wi-Fi iBike system, respectively. Conclusions: We concluded that a low-cost wireless interface provides the necessary accuracy for the telemonitoring of home-based biking exercise.

手指运动的高维分析和非接触式传感器筛查颈脊髓病:诊断病例-对照研究

2022 - 10 - 03 - t09:15:02内

背景:颈髓病(CM)可引起手部笨拙等症状，通常需要手术治疗。CM的筛查和早期诊断很重要，因为有些患者不知道自己的早期症状，只有在病情变得严重后才去看外科医生。10秒的握放测试通常用于检查CM的存在。该检测方法简单，但如果能客观评价CM特有的运动变化，则对筛查更有用。此前的一项研究利用非接触式传感器Leap Motion分析了10秒握放测试中的手指运动，并开发了一种利用机器学习的高灵敏度和特异性诊断CM的系统。然而，以往的研究存在局限性，系统记录的参数很少，不能将CM与其他手部疾病区分开来。目的:本研究旨在建立一种具有更高灵敏度和特异性的CM诊断系统，并将CM与常见手部疾病腕管综合征(carpal tunnel syndrome, CTS)区分开来。然后，我们用改进的Leap Motion来验证系统，该系统可以记录每个手指的关节。方法: CM组、CTS组和对照组共招募了31、27和29名参与者。我们使用Leap Motion开发了一个系统，记录了参与者在尽可能快地抓住和释放手指时手指运动的229个参数。 A support vector machine was used for machine learning to develop the binary classification model and calculated the sensitivity, specificity, and area under the curve (AUC). We developed two models, one to diagnose CM among the CM and control groups (CM/control model), and the other to diagnose CM among the CM and non-CM groups (CM/non-CM model). Results: The CM/control model indexes were as follows: sensitivity 74.2%, specificity 89.7%, and AUC 0.82. The CM/non-CM model indexes were as follows: sensitivity 71%, specificity 72.87%, and AUC 0.74. Conclusions: We developed a screening system capable of diagnosing CM with higher sensitivity and specificity. This system can differentiate patients with CM from patients with CTS as well as healthy patients and has the potential to screen for CM in a variety of patients.

疼痛评估的贝叶斯网络概念

2022 - 09 - 29 - t09:30:03内

在这项研究中，我们提出了一种方法，提供了一个有用的数据总结与病人的疼痛经验。由于疼痛是一种非常重要但主观的现象，目前尚无可校准的方法来评估它，我们建议使用可校准的生物标志物传感器与患者对感知疼痛的自我评估。我们推测，这种方法可能只能清楚地区分现有证据一致的情况。然而，这些信息可能为临床医生提供有价值的见解，随着研究进展，生物标志物如何与疼痛相关，关于特定证据不一致如何指向特定疼痛原因的更具体的见解可能会出现。我们提供了疼痛科学的简要概述，包括疼痛的类型，当代疼痛理论，疼痛和疼痛评估技术。接下来，我们提出了疼痛传感器发展的新途径，包括疼痛相关生物标志物传感器的研究概况和人工智能方法的证据总结。然后，我们提供了我们的方法实现的一些示例。本文的方法部分介绍了一些具体内容。例如，在一组379例患者中，我们观察到80%的一致性证据和5种不一致性。关于报告疼痛的环氧化酶-2和诱导型一氧化氮合酶数据的性别和个体差异的信息可能导致不一致。 Different causes of inconsistencies are also attributed to cultural or temporal variability of cyclooxygenase-2 and inducible nitric oxide synthase (as well as their serum variation and half-life), visual analog scale, and other tools. We emphasize that this presentation is illustrative. Much work remains to be done before implementing and testing this approach in a clinically meaningful context.

使用基于雷达的睡眠监测仪(Somnofy)测量健康成人的非接触纵向呼吸频率:验证研究

2022 - 08 - 12 - t09:00:04内

背景:呼吸频率(RR)可以说是检测临床恶化最重要的生命体征。例如，RR的变化也可能与不同疾病的发作、阿片类药物过量、高强度锻炼或情绪有关。然而，与大多数其他重要参数不同，缺乏一种简单而准确的测量方法。目的:本研究旨在验证基于雷达的睡眠监测仪Somnofy用于测量RR，并研究影响RR的事件是否可以从夜间平均值计算的个性化基线中检测到。方法:首先，对37名健康成人在整晚睡眠期间使用Somnofy进行的rrr进行了呼吸感应体积脉搏图的广泛验证。然后，在一项初步研究中，6名健康参与者在家中使用Somnofy 3个月，研究人员分析了建议的过滤平均RR的夜间一致性。结果: Somnofy在84%的时间内测量了RR，平均绝对误差为0.18 (SD 0.05)每分钟呼吸，重复测量调整后的Bland-Altman 95%一致限范围为-0.99至0.85。深度睡眠和浅睡眠的准确性和覆盖率明显高于快速眼动睡眠和清醒状态。结果与年龄、性别和BMI无关，但在某些雷达方向上依赖于仰卧睡姿。对于夜间过滤平均值，95%的一致性限制范围为每分钟−0.07至−0.04次呼吸。 In the longitudinal part of the study, the nightly average was consistent from night to night, and all substantial deviations coincided with self-reported illnesses. Conclusions: RRs from Somnofy were more accurate than those from any other alternative method suitable for longitudinal measurements. Moreover, the nightly averages were consistent from night to night. Thus, several factors affecting RR should be detectable as anomalies from personalized baselines, enabling a range of applications. More studies are necessary to investigate its potential in children and older adults or in a clinical setting.

为精确公共卫生转变快速诊断测试:制造商和用户开放指南

2022 - 07 - 29 - t09:15:03内

背景:精确公共卫生(PPH)可以根据时间、空间和流行病学特征，通过有针对性的监测和干预措施，最大限度地发挥作用。尽管快速诊断测试(rdt)已经在资源匮乏的环境中实现了无处不在的护理点测试，但其影响不如预期，部分原因是缺乏简化数据捕获和分析的功能。我们的目标是通过定义信息和数据公理以及信息利用指数(IUI)，将RDT转变为PPH的工具;识别设计特征以最大化IUI;并为模块化RDT功能制定开放指南(OGs)，使其能够与数字健康工具联系起来，创建RDT- og系统。方法:我们回顾了已发表的论文，并与技术、制造和部署部门的rdt专家或用户进行了调查，以定义信息利用的特征和公理。我们制定了一个IUI，范围从0%到100%，并为33个世界卫生组织预审合格的rdt计算了该指数。制定了RDT-OG规范，以最大限度地提高IUI;通过开发在肯尼亚和印度尼西亚使用的基于ogg的疟疾和COVID-19快速诊断测试，评估了可行性和规格。结果:调查对象(n=33)包括16名研究人员，7名技术人员，3名制造商，2名医生或护士，5名其他用户。 They were most concerned about the proper use of RDTs (30/33, 91%), their interpretation (28/33, 85%), and reliability (26/33, 79%), and were confident that smartphone-based RDT readers could address some reliability concerns (28/33, 85%), and that readers were more important for complex or multiplex RDTs (33/33, 100%). The IUI of prequalified RDTs ranged from 13% to 75% (median 33%). In contrast, the IUI for an RDT-OG prototype was 91%. The RDT open guideline system that was developed was shown to be feasible by (1) creating a reference RDT-OG prototype; (2) implementing its features and capabilities on a smartphone RDT reader, cloud information system, and Fast Healthcare Interoperability Resources; and (3) analyzing the potential public health impact of RDT-OG integration with laboratory, surveillance, and vital statistics systems. Conclusions: Policy makers and manufacturers can define, adopt, and synergize with RDT-OGs and digital health initiatives. The RDT-OG approach could enable real-time diagnostic and epidemiological monitoring with adaptive interventions to facilitate control or elimination of current and emerging diseases through PPH.

异常手部运动的分类有助于自闭症的检测:机器学习研究

2022 - 06 - 06 - t09:30:02内

背景:正式的自闭症诊断可能是一个低效和漫长的过程。尽管有证据表明早期干预会带来更好的治疗效果，但家庭可能要等上几个月或更长时间才能得到孩子的诊断。检测自闭症相关行为的数字技术可以扩大儿科诊断的范围。自闭症存在的一个强有力的指标是自我刺激行为，如拍手。目的:本研究旨在证明深度学习技术在非结构化家庭视频中检测手部拍动的可行性，作为验证统计模型与数字技术相结合是否可以用于辅助自闭症自动行为分析的第一步。为了支持这种家庭视频的广泛共享，我们通过将每个视频转换为手部地标坐标来探索对输入空间的隐私保护修改，并测量相应时间序列分类器的性能。方法:我们使用了自刺激行为数据集(SSBD)，该数据集包含75个儿童拍手、撞头和旋转的视频。从这个数据集中，我们提取了100个拍手视频和100个控制视频，每个视频的持续时间在2到5秒之间。我们评估了五种独立的特征表示:由MediaPipe检测到的四个隐私保护的手部标志子集，以及从在SSBD上微调的MobileNetV2模型的第二层输出中获得的一个特征表示。我们将这些特征向量输入到一个长短期记忆网络中，该网络预测了每个视频片段中手部拍动的存在。 Results: The highest-performing model used MobileNetV2 to extract features and achieved a test F1 score of 84 (SD 3.7; precision 89.6, SD 4.3 and recall 80.4, SD 6) using 5-fold cross-validation for 100 random seeds on the SSBD data (500 total distinct folds). Of the models we trained on privacy-preserved data, the model trained with all hand landmarks reached an F1 score of 66.6 (SD 3.35). Another such model trained with a select 6 landmarks reached an F1 score of 68.3 (SD 3.6). A privacy-preserved model trained using a single landmark at the base of the hands and a model trained with the average of the locations of all the hand landmarks reached an F1 score of 64.9 (SD 6.5) and 64.2 (SD 6.8), respectively. Conclusions: We created five lightweight neural networks that can detect hand flapping from unstructured videos. Training a long short-term memory network with convolutional feature vectors outperformed training with feature vectors of hand coordinates and used almost 900,000 fewer model parameters. This study provides the first step toward developing precise deep learning methods for activity detection of autism-related behaviors.

一种基于混合现实的协作机器人控制新框架:开发研究

2022 - 05 - 17 - t09:15:02内

背景:机器人在日常生活中的应用越来越重要，因为它在不同领域创造了新的可能性，特别是在协作环境中。协作机器人的潜力是巨大的，因为它们可以和人类在同一个工作空间工作。采用顶尖技术的协作机器人框架肯定值得进一步研究。本研究旨在提出一种基于混合现实的新型协作机器人框架。该框架使用Unity和Unity Hub作为跨平台游戏引擎和项目管理工具，设计混合现实界面和数字孪生。它还使用Windows混合现实平台在全息显示器上显示数字材料，并使用Azure混合现实服务来捕获和暴露数字信息。最终，它使用全息设备(HoloLens 2)来执行基于混合现实的协作系统。结果:进行了全面的实验，验证了基于混合现实的协作机器人控制的新框架。该框架成功地应用于在混合现实环境中使用5自由度机器人(xArm-5)实现协作系统。该框架是稳定的，并且在整个协作过程中工作顺利。 Due to the distributed nature of cloud applications, there is a negligible latency between giving a command and the execution of the physical collaborative robot. Conclusions: Opportunities for collaborative robots in telerehabilitation and teleoperation are vital as in any other field. The proposed framework was successfully applied in a collaborative session, and it can also be applied in other similar potential applications for robust and more promising performance.

用于测量肤色校准外周血氧饱和度(OptoBeat)的公平驱动传感系统:开发，设计和评估研究

2022 - 04 - 22 - t13:30:28内

背景:许多商品脉搏血氧仪对肤色较深的患者校准不足。我们展示了通过对照实验定量测量外周血氧饱和度(SpO₂)的差异。为了缓解这种情况，我们提出了OptoBeat，这是一种基于智能手机的超低成本光学传感系统，可以在校准肤色差异的同时捕获SpO和心率。我们的传感系统可以由商品组件和3d打印剪辑构建，价格约为1美元。在我们的实验中，我们证明了OptoBeat系统的有效性，该系统可以在低至75%的水平下在1%的接地真值范围内测量SpO₂。目的:本工作的目的是测试以下假设，并实现一个超低成本的智能手机适配器来测量SpO₂:肤色对脉搏血氧仪测量结果有显著影响(假设1)，肤色图像可用于校准脉搏血氧仪误差(假设2)，SpO₂可通过智能手机摄像头以屏幕为光源测量(假设3)。方法:在离体实验中使用与人体皮肤具有相同光学特性的合成皮肤。肤色尺度被放置在图像中进行校准和地面真实性。为了实现大范围的SpO₂测量，我们对羊血进行再氧并通过合成动脉泵送。一个定制的光学系统从智能手机屏幕(闪烁红色和蓝色)连接到分析物，并连接到手机的摄像头进行测量。 Results: The 3 skin tones were accurately classified according to the Fitzpatrick scale as types 2, 3, and 5. Classification was performed using the Euclidean distance between the measured red, green, and blue values. Traditional pulse oximeter measurements (n=2000) showed significant differences between skin tones in both alternating current and direct current measurements using ANOVA (direct current: F_2,5997=3.1170 × 10⁵, P<.01; alternating current: F_2,5997=8.07 × 10⁶, P<.01). Continuous SpO₂ measurements (n=400; 10-second samples, 67 minutes total) from 95% to 75% were captured using OptoBeat in an ex vivo experiment. The accuracy was measured to be within 1% of the ground truth via quadratic support vector machine regression and 10-fold cross-validation (R²=0.97, root mean square error=0.7, mean square error=0.49, and mean absolute error=0.5). In the human-participant proof-of-concept experiment (N=3; samples=3 × N, duration=20-30 seconds per sample), SpO₂ measurements were accurate to within 0.5% of the ground truth, and pulse rate measurements were accurate to within 1.7% of the ground truth. Conclusions: In this work, we demonstrate that skin tone has a significant effect on SpO₂ measurements and the design and evaluation of OptoBeat. The ultra-low-cost OptoBeat system enables smartphones to classify skin tone for calibration, reliably measure SpO₂ as low as 75%, and normalize to avoid skin tone–based bias.

科尔松弛频率作为识别肺组织癌症的参数:初步动物和离体患者研究

2022 - 02 - 21 - t09:00:06凌晨

背景:肺癌是世界上癌症死亡的主要原因，诊断仍然具有挑战性。肺癌以小结节开始;早期准确的诊断可以及时手术切除恶性结节，同时避免良性结节患者不必要的手术。目的:科尔松弛频率(CRF)是一种衍生的电生物阻抗特征，可用于区分癌组织和正常组织。方法:在30名接受非小细胞肺癌切除术的志愿者新切除的肺组织中，使用NoduleScan进行了人体离体测试。将肿瘤和远端正常肺组织相对于肿瘤的CRF与组织病理学标本进行比较，以建立一种潜在的即时诊断算法。在动物体内实验中，将移植的人肺癌肿瘤细胞皮下注射于20只小鼠的右侧。对活体动物的肿瘤进行经皮和安乐死后的肿瘤进行频谱阻抗测量。将这些CRF测量值与健康小鼠肺组织进行比较。对于猪肺离体试验，猪肺与气管一起接受。 After removal of the vocal box, a ventilator was attached to pressurize the lung and simulate breathing. At different locations of the lobes, the lung's surface was cut to produce a pocket that could accommodate tumors obtained from in vivo animal testing. The tumors were placed in the subsurface of the lung, and the electrode was placed on top of the lung surface directly over the tumor but with lung tissue between the tumor and the electrode. Spectral impedance measurements were taken when the lungs were in the deflated state, inflated state, and also during the inflation-deflation process to simulate breathing. Results: Among 60 specimens evaluated in 30 patients, NoduleScan allowed ready discrimination in patients with clear separation of CRF in tumor and distant normal tissue with a high degree of sensitivity (97%) and specificity (87%). In the 25 xenograft small animal model specimens measured, the CRF aligns with the separation observed in the human in vivo measurements. The CRF was successfully measured of tumors implanted into ex vivo porcine lungs, and CRF measurements aligned with previous tests for pressurized and unpressurized lungs. Conclusions: As previously shown in breast tissue, CRF in the range of 1kHz-10MHz was able to distinguish nonsmall cell lung cancer versus normal tissue. Further, as evidenced by in vivo small animal studies, perfused tumors have the same CRF signature as shown in breast tissue and human ex vivo testing. Inflation and deflation of the lung have no effect on the CRF signature. With additional development, CRF derived from spectral impedance measurements may permit point-of-care diagnosis guiding surgical resection.