While automatic monitoring and coaching of exercises are showing encouraging
results in non-medical applications, they still have limitations such as errors
and limited use contexts. To allow the development and assessment of physical
rehabilitation by an intelligent tutoring system, we identify in this article
four challenges to address and propose a medical dataset of clinical patients
carrying out low back-pain rehabilitation exercises. The dataset includes 3D
Kinect skeleton positions and orientations, RGB videos, 2D skeleton data, and
medical annotations to assess the correctness, and error classification and
localisation of body part and timespan. Along this dataset, we perform a
complete research path, from data collection to processing, and finally a small
benchmark. We evaluated on the dataset two baseline movement recognition
algorithms, pertaining to two different approaches: the probabilistic approach
with a Gaussian Mixture Model (GMM), and the deep learning approach with a
Long-Short Term Memory (LSTM).
This dataset is valuable because it includes rehabilitation relevant motions
in a clinical setting with patients in their rehabilitation program, using a
cost-effective, portable, and convenient sensor, and because it shows the
potential for improvement on these challenges.

通过医疗数据集，我们提出了医学患者进行腰背疼痛康复锻炼的四个挑战，并在数据集上进行了数据收集、处理和小规模基准评估，同时评估了两种基准运动识别算法：高斯混合模型 (GMM) 和长短时记忆 (LSTM)。

一个医学腰背疼痛身体康复数据集的人体运动分析

A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body  Movement Analysis

Physical rehabilitation plays a crucial role in the recovery process of
post-stroke patients. By personalizing therapies for patients leveraging
predictive modeling and electronic health records (EHRs), healthcare providers
can make the rehabilitation process more efficient. Before predictive modeling
can provide decision support for the assignment of treatment plans, automated
methods are necessary to extract physical rehabilitation exercise information
from unstructured EHRs. We introduce a rule-based natural language processing
algorithm to annotate therapeutic procedures for stroke patients and compare it
to several small machine learning models. We find that our algorithm
outperforms these models in extracting half of the concepts where sufficient
data is available, and individual exercise descriptions can be assigned binary
labels with an f-score of no less than 0.75 per concept. More research needs to
be done before these algorithms can be deployed on unlabeled documents, but
current progress gives promise to the potential of precision rehabilitation
research.

本研究介绍一种基于规则的自然语言处理算法，可以从非结构化的电子健康记录中标注中风患者的治疗过程，与几个小型机器学习模型进行比较，并发现我们的算法在提取足够数据可用的一半概念方面表现优异，并且每个概念的个别运动描述可以分配二进制标签，f-score 不低于 0.75。

从临床记录中提取物理康复运动信息：基于规则和机器学习自然语言处理技术的比较

Extracting Physical Rehabilitation Exercise Information from Clinical Notes: a Comparison of Rule-Based and Machine Learning Natural Language Processing Techniques

Physical rehabilitation programs frequently begin with a brief stay in the
hospital and continue with home-based rehabilitation. Lack of feedback on
exercise correctness is a significant issue in home-based rehabilitation.
Automated movement quality assessment (MQA) using skeletal movement data
(hereafter referred to as skeletal data) collected via depth imaging devices
can assist with home-based rehabilitation by providing the necessary
quantitative feedback. This paper aims to use recent advances in deep learning
to address the problem of MQA. Movement quality score generation is an
essential component of MQA. We propose three novel skeletal data augmentation
schemes. We show that using the proposed augmentations for generating movement
quality scores result in significant performance boosts over existing methods.
Finally, we propose a novel transformer based architecture for MQA. Four novel
feature extractors are proposed and studied that allow the transformer network
to operate on skeletal data. We show that adding the attention mechanism in the
design of the proposed feature extractor allows the transformer network to pay
attention to specific body parts that make a significant contribution towards
executing a movement. We report an improvement in movement quality score
prediction of 12% on UI-PRMD dataset and 21% on KIMORE dataset compared to the
existing methods.

使用深度学习与骨骼数据增强技术，提高自动化运动质量评估的准确性来辅助物理康复训练。