Early rehabilitation with the right intensity contributes to the physical recovery of stroke survivors. In clinical practice, physicians determine whether the training intensity is suitable for rehabilitation based on patients’ narratives, training scores, and evaluation scales, which puts tremendous pressure on medical resources. In this study, a lightweight facial expression recognition algorithm is proposed to diagnose stroke patients’ training motivations automatically. First, the properties of convolution are introduced into the Vision Transformer’s structure, allowing the model to extract both local and global features of facial expressions. Second, the pyramid-shaped feature output mode in Convolutional Neural Networks is also introduced to reduce the model’s parameters and calculation costs significantly. Moreover, a classifier that can better classify facial expressions of stroke patients is designed to improve performance further. We verified the proposed algorithm on the Real-world Affective Faces Database (RAF-DB), the Face Expression Recognition Plus Dataset (FER+), and a private dataset for stroke patients. Experiments show that the backbone network of the proposed algorithm achieves better performance than Pyramid Vision Transformer (PvT) and Convolutional Vision Transformer (CvT) with fewer parameters and Floating-point Operations Per Second (FLOPs). In addition, the algorithm reaches an 89.44% accuracy on the RAF-DB dataset, which is higher than other recent studies. In particular, it obtains an accuracy of 99.81% on the private dataset, with only 4.10M parameters.

Neurogenic bladder (NB) is a frequently encountered post-stroke complication, characterized by symptoms, such as urinary incontinence, dysuria, increased frequency, and urgency. Here, we present a case of a 75-year-old male with urgent urination, frequent urination, urinary incontinence, conspicuous discomfort during urination, and an unpleasant smell in the urine following a stroke. By reviewing the patient's previous medical records of stroke and ruling out other potential causes for bladder dysfunction, a diagnosis of NB could be established. We implemented conventional physical therapy, pelvic floor muscle training with the electromyography biofeedback device, and continuous theta burst stimulation (cTBS) on the contralesional primary motor cortex area to manage bladder function. To the best of our knowledge, this is the first case report on cTBS applied to manage NB after stroke. Our treatment has demonstrated remarkable efficacy in enhancing bladder and kidney function, improving the overall quality of life, and alleviating anxiety and depression symptoms in this patient. This case study concludes that the noninvasive neuromodulation approach exhibits significant potential in the clinical field when addressing this specific patient population.

Early weight-bearing and trunk control training are essential components for promoting lower limb motor recovery in individuals with stroke. In this case study, we presented the successful implementation of a three-week wearable self-balancing exoskeleton robot training program for a 57-year-old male patient who had suffered from a stroke. After carefully reviewing the patient's previous medical records, conducting a thorough assessment, and excluding other potential contraindications, we introduced wearable selfbalancing exoskeleton robot training to complement conventional rehabilitation in managing balance and lower limb function. The training program included early initiation of weight bearing and trunk control training following an ischemic stroke, aimed at promoting motor recovery and improving functional independence. The findings indicated that training with a wearable self-balancing exoskeleton robot enhanced the balance and motor function of the hemiplegic patient, with commendable adherence. Furthermore, the participants consistently reported increased satisfaction and confidence during the training sessions. This case report not only provided preliminary evidence of the effectiveness of the wearable self-balancing exoskeleton robot in promoting functional recovery following a stroke but also outlined a comprehensive training program that may hold value for future clinical application.

Article: Effects of self-directed game-based virtual reality program on upper-limb motor recovery in mild-to-moderate ischemic stroke: a randomized controlled trial - European Journal of Physical and Rehabilitation Medicine 2026 Feb 02 - Minerva Medica - Journals