srBERT: automatic article classification model for systematic review using BERT.

BACKGROUND: Systematic reviews (SRs) are recognized as reliable evidence, which enables evidence-based medicine to be applied to clinical practice. However, owing to the significant efforts required for an SR, its creation is time-consuming, which often leads to out-of-date results. To support SR tasks, tools for automating these SR tasks have been considered; however, applying a general natural language processing model to domain-specific articles and insufficient text data for training poses challenges. METHODS: The research objective is to automate the classification of included articles using the Bidirectional Encoder Representations from Transformers (BERT) algorithm. In particular, srBERT models based on the BERT algorithm are pre-trained using abstracts of articles from two types of datasets, and the resulting model is then fine-tuned using the article titles. The performances of our proposed models are compared with those of existing general machine-learning models. RESULTS: Our results indicate that the proposed srBERTmy model, pre-trained with abstracts of articles and a generated vocabulary, achieved state-of-the-art performance in both classification and relation-extraction tasks; for the first task, it achieved an accuracy of 94.35% (89.38%), F1 score of 66.12 (78.64), and area under the receiver operating characteristic curve of 0.77 (0.9) on the original and (generated) datasets, respectively. In the second task, the model achieved an accuracy of 93.5% with a loss of 27%, thereby outperforming the other evaluated models, including the original BERT model. CONCLUSIONS: Our research shows the possibility of automatic article classification using machine-learning approaches to support SR tasks and its broad applicability. However, because the performance of our model depends on the size and class ratio of the training dataset, it is important to secure a dataset of sufficient quality, which may pose challenges.

Moxibustion for cognitive impairment: a systematic review and meta-analysis of animal studies.

BACKGROUND: Cognitive impairment is an age-dependent chronic disorder that exponentially worsens with age; however, its treatment is mostly symptomatic. Moxibustion is widely accepted in East Asia as a treatment for cognitive impairment. This systematic review aimed to verify the efficacy and underlying mechanism of moxibustion in treating cognitive impairment. METHODS: Sixteen trials involving 324 animals obtained from MEDLINE (PubMed), EMBASE, the Cochrane library, the Chinese National Knowledge Infrastructure, Wan-Fang, Cqvip, the Korean Studies Information Service System, and the Oriental Medicine Advanced Searching Integrated System met the inclusion criteria. We extracted the results of behavioral tests and immunohistochemical biomarkers from the included articles and evaluated the risk of bias and reporting quality. RESULTS: The moxibustion group showed significantly decreased escape latency, increased crossing times, and prolonged dwelling times in the Morris water maze test. There was a significantly enhanced latency period and reduced error time in the step-down test and nerve behavior score. The effects of moxibustion were found to be mediated by suppression of oxidative stress and apoptosis, modulation of inflammation and Aß genesis activation of vascular endothelial growth factor, and adjustment of metabolites in the tricarboxylic acid cycle and fatty acid metabolism. CONCLUSION: Our results demonstrated the therapeutic efficacy of moxibustion on cognitive impairment and suggested the putative mechanism. However, considering the small number of included studies, high bias risk, low reporting quality, and the limitations of animal experimentation, our results need to be confirmed by more detailed studies.