ObjectivesTo systematically review the efficacy of kinesio taping on post stroke shoulder pain.MethodsPubMed, EMbase, The Cochrane Library, Web of Science, PEDro, CNKI and WanFang Data databases were electronically searched to collect randomized controlled trials (RCTs) of kinesio taping on shoulder pain after stroke from inception to November, 2018. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies, then, meta-analysis was performed by using RevMan 5.3 software.ResultsA total of 8 RCTs involving 525 patients were included. The results of meta-analysis showed that, compared with the control group, kinesio taping group for 4 weeks treatment significantly reduced shoulder pain (SMD=−0.81, 95%CI −0.58 to −0.04, P=0.04), increased range of motion of shoulder flexion (SMD=0.59, 95%CI 0.17 to 1.01, P=0.006) and abduction (SMD=0.67, 95%CI 0.24 to 1.09, P=0.002). It also improved Fugl-Meyer upper limb function (SMD=1.00, 95%CI 0.25 to 1.76, P=0.009).ConclusionsCurrent evidence shows that the kinesio taping for 4 weeks duration can effectively reduce shoulder pain after stroke. Due to limited quality and quantity of the included studies, more high-quality studies are required to verify above conclusions.
Objective To construct large medical model named by "Huaxi HongYi"and explore its application effectiveness in assisting medical record generation. Methods By the way of a full-chain medical large model construction paradigm of "data annotation - model training - scenario incubation", through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, "Huaxi HongYi" with 72 billion parameters was constructed. Combined with technologies such as speech recognition, knowledge graphs, and reinforcement learning, an application system for assisting in the generation of medical records was developed. ResultsTaking the assisted generation of discharge records as an example, in the pilot department, after using the application system, the average completion times of writing a medical records shortened (21 min vs. 5 min) with efficiency increased by 3.2 time, the accuracy rate of the model output reached 92.4%. Conclusion It is feasible for medical institutions to build independently controllable medical large models and incubate various applications based on these models, providing a reference pathway for artificial intelligence development in similar institutions.