School of Engineering, Cardiff University, Cardiff, United Kingdom.
School of Healthcare Sciences, Cardiff University, Cardiff, United Kingdom.
PLoS One. 2024 May 10;19(5):e0302899. doi: 10.1371/journal.pone.0302899. eCollection 2024.
Low back pain (LBP) is a major global disability contributor with profound health and socio-economic implications. The predominant form is non-specific LBP (NSLBP), lacking treatable pathology. Active physical interventions tailored to individual needs and capabilities are crucial for its management. However, the intricate nature of NSLBP and complexity of clinical classification systems necessitating extensive clinical training, hinder customised treatment access. Recent advancements in machine learning and computer vision demonstrate promise in characterising NSLBP altered movement patters through wearable sensors and optical motion capture. This study aimed to develop and evaluate a machine learning model (i.e., 'BACK-to-MOVE') for NSLBP classification trained with expert clinical classification, spinal motion data from a standard video alongside patient-reported outcome measures (PROMs).
Synchronised video and three-dimensional (3D) motion data was collected during forward spinal flexion from 83 NSLBP patients. Two physiotherapists independently classified them as motor control impairment (MCI) or movement impairment (MI), with conflicts resolved by a third expert. The Convolutional Neural Networks (CNNs) architecture, HigherHRNet, was chosen for effective pose estimation from video data. The model was validated against 3D motion data (subset of 62) and trained on the freely available MS-COCO dataset for feature extraction. The Back-to-Move classifier underwent fine-tuning through feed-forward neural networks using labelled examples from the training dataset. Evaluation utilised 5-fold cross-validation to assess accuracy, specificity, sensitivity, and F1 measure.
Pose estimation's Mean Square Error of 0.35 degrees against 3D motion data demonstrated strong criterion validity. Back-to-Move proficiently differentiated MI and MCI classes, yielding 93.98% accuracy, 96.49% sensitivity (MI detection), 88.46% specificity (MCI detection), and an F1 measure of .957. Incorporating PROMs curtailed classifier performance (accuracy: 68.67%, sensitivity: 91.23%, specificity: 18.52%, F1: .800).
This study is the first to demonstrate automated clinical classification of NSLBP using computer vision and machine learning with standard video data, achieving accuracy comparable to expert consensus. Automated classification of NSLBP based on altered movement patters video-recorded during routine clinical examination could expedite personalised NSLBP rehabilitation management, circumventing existing healthcare constraints. This advancement holds significant promise for patients and healthcare services alike.
下腰痛（LBP）是全球主要的残疾因素，对健康和社会经济有着深远的影响。主要形式是非特异性下腰痛（NSLBP），缺乏可治疗的病理。针对个体需求和能力进行主动的身体干预对于其管理至关重要。然而，NSLBP 的复杂性质和临床分类系统的复杂性需要广泛的临床培训，阻碍了个性化治疗的实施。最近机器学习和计算机视觉的进展表明，通过可穿戴传感器和光学运动捕捉来描述 NSLBP 改变的运动模式具有很大的潜力。本研究旨在开发和评估一种基于机器学习的模型（即“BACK-to-MOVE”），用于 NSLBP 分类，该模型经过专家临床分类、标准视频中的脊柱运动数据以及患者报告的结果测量（PROMs）进行训练。
从 83 名 NSLBP 患者的脊柱前屈运动中同步采集视频和三维（3D）运动数据。两名物理治疗师独立将其分类为运动控制障碍（MCI）或运动障碍（MI），并由第三位专家解决冲突。选择卷积神经网络（CNN）架构 HigherHRNet 从视频数据中进行有效的姿势估计。该模型通过使用训练数据集的正向神经网络对 3D 运动数据（62 个数据子集）进行验证，并在自由获取的 MS-COCO 数据集上进行特征提取进行训练。通过使用来自训练数据集的标记示例，通过前馈神经网络对 Back-to-Move 分类器进行微调。评估使用 5 折交叉验证来评估准确性、特异性、敏感性和 F1 度量。
与 3D 运动数据相比，姿势估计的均方误差为 0.35 度，表现出很强的准则有效性。Back-to-Move 能够熟练地区分 MI 和 MCI 类，准确率为 93.98%，敏感性（MI 检测）为 96.49%，特异性（MCI 检测）为 88.46%，F1 测量值为.957。纳入 PROM 降低了分类器的性能（准确性：68.67%，敏感性：91.23%，特异性：18.52%，F1：.800）。
本研究首次使用标准视频数据和计算机视觉演示了基于机器学习的 NSLBP 的自动临床分类，其准确性可与专家共识相媲美。基于常规临床检查期间记录的改变的运动模式的 NSLBP 的自动分类可以加快个性化 NSLBP 康复管理，避免现有的医疗保健限制。这一进展对患者和医疗服务都具有重要意义。
