Ludwig Maximilian University of Munich (LMU), Hauner Children's Hospital, Department of Paediatric Neurology and Developmental Medicine, Munich, Germany; Ludwig Maximilian University of Munich (LMU), Comprehensive Developmental Care (CDeC), Munich, Germany.
Swiss Children's Rehab, University Children's Hospital Zurich, Affoltern am Albis, Switzerland.
Early Hum Dev. 2020 May;144:104967. doi: 10.1016/j.earlhumdev.2020.104967. Epub 2020 Apr 15.
General Movement Assessment (GMA) is a powerful tool to predict Cerebral Palsy (CP). Yet, GMA requires substantial training challenging its broad implementation in clinical routine. This inspired a world-wide quest for automated GMA.
To test whether a low-cost, marker-less system for three-dimensional motion capture from RGB depth sequences using a whole body infant model may serve as the basis for automated GMA.
Clinical case study at an academic neurodevelopmental outpatient clinic.
Twenty-nine high risk infants were assessed at their clinical follow-up at 2-4 month corrected age (CA). Their neurodevelopmental outcome was assessed regularly up to 12-31 months CA.
GMA according to Hadders-Algra by a masked GMA-expert of conventional and computed 3D body model ("SMIL motion") videos of the same GMs. Agreement between both GMAs was tested using dichotomous and graded scaling with Kappa and intraclass correlations, respectively. Sensitivity and specificity to predict CP at ≥12 months CA were assessed.
Agreement of the two GMA ratings was moderate-good for GM-complexity (κ = 0.58; ICC = 0.874 [95%CI 0.730; 0.941]) and substantial-good for fidgety movements (FMs; Kappa = 0.78, ICC = 0.926 [95%CI 0.843; 0.965]). Five children were diagnosed with CP (four bilateral, one unilateral CP). The GMs of the child with unilateral CP were twice rated as mildly abnormal with FMs. GM-complexity and somewhat less FMs, of both conventional and SMIL motion videos predicted bilateral CP comparably to published literature.
Our computed infant 3D full body model is an attractive starting point for automated GMA in infants at risk of CP.
全身运动评估（GMA）是预测脑瘫（CP）的有力工具。然而，GMA 需要大量的培训，这使其难以在临床常规中广泛应用。这激发了全球对自动 GMA 的探索。
测试使用基于全身婴儿模型的 RGB 深度序列的低成本、无标记三维运动捕捉系统是否可作为自动 GMA 的基础。
在学术神经发育门诊进行的临床病例研究。
29 名高危婴儿在 2-4 个月校正年龄（CA）时进行临床随访评估。他们的神经发育情况在 12-31 个月 CA 时定期进行评估。
由一位经过 GMA 培训的专家对传统和计算的 3D 身体模型（“SMIL 运动”）视频进行盲法 GMA 评估，以评估 GMA 复杂性和烦躁运动（FM）。使用二项式和分级评分以及 Kappa 和组内相关系数分别测试两种 GMAs 的一致性。评估其在≥12 个月 CA 预测 CP 的敏感性和特异性。
对于 GM 复杂性（κ=0.58；ICC=0.874 [95%CI 0.730；0.941]）和烦躁运动（FM）（Kappa=0.78，ICC=0.926 [95%CI 0.843；0.965]），两种 GMA 评分的一致性为中等至良好。5 名儿童被诊断为 CP（4 例双侧 CP，1 例单侧 CP）。患有单侧 CP 的儿童的 GM 两次被评为 FM 轻度异常。GM 复杂性和 FM 略少，对于双侧 CP，传统和 SMIL 运动视频的预测能力与已发表文献相当。
我们的计算婴儿 3D 全身模型是自动 GMA 在 CP 高危婴儿中的一个有吸引力的起点。
