Data analytics interrogates robotic surgical performance using a microsurgery-specific haptic device
收藏Taylor & Francis Group2021-05-07 更新2026-04-16 收录
下载链接:
https://tandf.figshare.com/articles/dataset/Data_analytics_interrogates_robotic_surgical_performance_using_a_microsurgery-specific_haptic_device/12850358/1
下载链接
链接失效反馈官方服务:
资源简介:
With the increase in robot-assisted cases, recording the quantifiable dexterity of surgeons is essential for proficiency evaluations. The present study employs sensor-based kinematics and recorded surgeon experience for evaluating a new haptic device. Thirty surgeons performed a task simulating micromanipulation with neuroArmPLUS<sup>HD</sup> and two commercially available hand-controllers. The surgical performance was evaluated based on subjective measures obtained from survey and objective features derived from the sensors. Statistical analyses were performed to assess the hand-controllers and regression analysis was used to identify the key features and develop a machine learning model for surgical skill assessment. MANCOVA tests on objective features demonstrated significance (α = 0.05) for time (p = 0.02), errors (p = 0.01), distance (p = 0.03), clutch incidents (p = 0.03), and forces (p = 0.00). The majority of metrics were in favor of neuroArmPLUS<sup>HD</sup>. The surgeons found it smoother, more comfortable, less tiring, and easier to maneuver with more realistic force feedback. The ensemble machine learning model trained with 5-fold cross-validation showed an accuracy (SD) of 0.78 (0.15) in surgeon skill classification. This study validates the importance of incorporating a superior haptic device in telerobotic surgery for standardization of surgical education and patient care.
随着机器人辅助手术病例的不断增加,记录外科医生可量化的操作灵巧性,对于其手术熟练度评估而言至关重要。本研究采用基于传感器的运动学数据结合外科医生从业经验数据,对一款新型触觉设备(haptic device)展开评估。30名外科医生分别使用neuroArmPLUS<sup>HD</sup>与两款商用手部控制器,完成一项显微操作模拟任务。手术操作性能的评估,基于问卷调查获取的主观测评指标以及传感器提取的客观特征两方面展开。研究开展了统计分析以对比不同手部控制器的表现,并通过回归分析识别核心特征,同时构建了用于外科手术技能评估的机器学习模型。针对客观特征开展的多变量协方差分析(MANCOVA)结果显示,在显著性水平α=0.05下,操作耗时(p=0.02)、失误次数(p=0.01)、操作距离(p=0.03)、离合触发次数(p=0.03)以及操作受力(p=0.00)均表现出显著统计学差异。多数测评指标均显示neuroArmPLUS<sup>HD</sup>的表现更优。外科医生反馈,该设备操作更为流畅、体感更舒适、不易产生疲劳,且在更逼真的力反馈支持下操控更加简易。采用5折交叉验证(5-fold cross-validation)训练的集成机器学习模型,在外科手术技能分类任务中实现了0.78(标准差为0.15)的准确率。本研究证实,在远程机器人手术中采用高性能触觉设备,对于手术教育标准化与患者诊疗质量提升均具有重要意义。
提供机构:
Hamidreza Hoshyarmanesh; Sanju Lama
创建时间:
2020-08-24



