Light is an easy acquired, effective and non-invasive external stimulus with great flexibility and focusability. Thus, light responsive hydrogels are of particular interests to researchers in developing accurate and controlled drug delivery systems. Light responsive hydrogels are obtained by incorporating photosensitive moieties into their polymeric structures. Drug release can be realized through three major mechanisms: photoisomerization, photochemical reaction and photothermal reaction. Recent advances in material science have resulted in great development of photosensitizers, such as rare metal nanostructures and black phosphorus nanoparticles, in order to respond to a variety of light sources. Hydrogels incorporated with photosensitizers are crucial for clinical applications, and the use of ultraviolet and near-infrared light as well as up-conversion nanoparticles has greatly increased the therapeutic effects. Existing light responsive drug delivery systems have been utilized in delivering drugs, proteins and genes for chemotherapy, immunotherapy, photodynamic therapy, gene therapy, wound healing and other applications. Principles associated with site-specific targeting, metabolism, and toxicity are used to optimize efficacy and safety, and to improve patient compliance and convenience. In view of the importance of this field, we review current development, challenges and future perspectives of light responsive hydrogels for controlled drug delivery.

Introduction: Balance impairment is an important indicator to a variety of diseases. Early detection of balance impairment enables doctors to provide timely treatments to patients, thus reduce their fall risk and prevent related disease progression. Currently, balance abilities are usually assessed by balance scales, which depend heavily on the subjective judgement of assessors.Methods: To address this issue, we specifically designed a method combining 3D skeleton data and deep convolutional neural network (DCNN) for automated balance abilities assessment during walking. A 3D skeleton dataset with three standardized balance ability levels were collected and used to establish the proposed method. To obtain better performance, different skeleton-node selections and different DCNN hyperparameters setting were compared. Leave-one-subject-out-cross-validation was used in training and validation of the networks.Results and Discussion: Results showed that the proposed deep learning method was able to achieve 93.33% accuracy, 94.44% precision and 94.46% F1 score, which outperformed four other commonly used machine learning methods and CNN-based methods. We also found that data from body trunk and lower limbs are the most important while data from upper limbs may reduce model accuracy. To further validate the performance of the proposed method, we migrated and applied a state-of-the-art posture classification method to the walking balance ability assessment task. Results showed that the proposed DCNN model improved the accuracy of walking balance ability assessment. Layer-wise Relevance Propagation (LRP) was used to interpret the output of the proposed DCNN model. Our results suggest that DCNN classifier is a fast and accurate method for balance assessment during walking.

Telerehabilitation (TR) is a new model to provide rehabilitation services to stroke survivors. It is a promising approach to deliver mainstream interventions for movement, cognitive, speech and language, and other disorders. TR has two major components: information and communication technologies (ICTs) and stroke interventions. ICTs provide a platform on which interventions are delivered and subsequently result in stroke recovery. In this mini-review, we went over features of ICTs that facilitate TR, as well as stroke interventions that can be delivered via TR platforms. Then, we reviewed the effects of TR on various stroke disorders. In most studies, TR is a feasible and effective solution in delivering interventions to patients. It is not inferior to usual care and in-clinic therapy with matching dose and intensity. With new technologies, TR may result in better outcomes than usual care for some disorders. One the other hand, TR also have many limitations that could lead to worse outcomes than traditional rehabilitation. In the end, we discussed major concerns and possible solutions related to TR, and also discussed potential directions for TR development.