自动化的临床评估通过机器学习和成对比较(P4.205)

文摘

目标:开发一个自动化的运动功能障碍的临床评估方法培训机器学习算法与细粒度的临床判断来自两两比较患者的影像记录。背景:许多临床神经学评估尺度遭受可靠性和灵敏度问题,因为它们需要绝对,从临床医生定性判断。首页相反,量化替代措施可能不会传达相同的临床相关的信息。监督机器学习算法允许地图自动代理到临床评估量表测量,从而自动创建一个临床评级。然而,病人数量太有限了标准的机器学习方法,它不可能验证细粒度算法的输出和一个粗粒度的临床评估。在这里,我们专注于扩大残疾量表(eds)对多发性硬化(MS)运动功能障碍的评估。方法:eds小分预计将定制监督机器学习算法应用于运动模式从录像中提取的病人执行预定义的动作。细粒度的捕获的临床判断,我们使用成对比较耐心的视频由神经学家。避免比较所有可能的对视频,我们使用的一种变体TrueSkill™算法目前只有最信息对视频比较的神经学家。结果:我们的小说ensemble-based机器学习算法提供可靠的预测性能的eds小分Finger-to-Nose测试。 The paired comparisons of recorded movement videos by expert neurologists show a finer-grained clinical judgment than provided by the EDSS sub-scores, providing a new potential validation standard. Conclusions: Our generic approach to automate clinical assessment by combining depth sensor recordings with video analysis and supervised machine learning to produce clinically relevant information validated against fine-grained capture of neurological judgment from pairwise comparisons can overcome the limitations of current clinical ratings in reliably capturing subtle changes in disability.

披露:多恩博士已经收到个人补偿活动与诺华制药公司作为一个员工。D’索萨博士已经收到个人活动与拜耳公司补偿,Teva, Genzyme。D’索萨已收到博士研究巴塞尔大学的支持。莫里森博士已经收到个人补偿活动与微软研究作为一个员工。莫里森博士已经收到个人补偿活动与微软研究作为一个员工。Burggraaff博士已经收到个人活动与诺华公司补偿。卡姆博士已经收到个人活动与补偿Idec,诺华公司,拜耳医药、博士Genzyme,辉瑞公司,默克公司Serono Tewarie已收到个人活动与诺华公司补偿。沃格尔博士已经收到个人活动与诺华作为雇员补偿。Sellen博士已经收到个人补偿活动与微软研究作为一个员工。Criminisi博士获得了与微软作为一个员工个人补偿活动。 Dr. Dahlke has received personal compensation for activities with Novartis as an employee. Dr. Uitdehaag has received personal compensation for activities with Biogen Idec, Novartis, EMD Serono, Teva Neuroscience, Genzyme Corporation, and Roche Diagnostics Corporation. Dr. Kappos has received personal compensation for activities with Actelion Pharmaceuticals. Dr. Chin has received personal compensation for activities with Genentech, Inc. as an employee.