ObjectiveTo realize automatic risk bias assessment for the randomized controlled trial (RCT) literature using BERT (Bidirectional Encoder Representations from Transformers) as an approach for feature representation and text classification.MethodsWe first searched The Cochrane Library to obtain risk bias assessment data and detailed information on RCTs, and constructed data sets for text classification. We assigned 80% of the data set as the training set, 10% as the test set, and 10% as the validation set. Then, we used BERT to extract features, construct text classification model, and evaluate the seven types of risk bias values (high and low). The results were compared with those from traditional machine learning methods using a combination of n-gram and TF-IDF as well as the Linear SVM classifier. The accuracy rate (P value), recall rate (R value) and F1 value were used to evaluate the performance of the models.ResultsOur BERT-based model achieved F1 values of 78.5% to 95.2% for the seven types of risk bias assessment tasks, which was 14.7% higher than the traditional machine learning method. F1 values of 85.7% to 92.8% were obtained in the extraction task of the other six types of biased descriptors except "other sources of bias", which was 18.2% higher than the traditional machine learning method.ConclusionsThe BERT-based automatic risk bias assessment model can realize higher accuracy in risk of bias assessment for RCT literature, and improve the efficiency of assessment.
Objective This article takes the construction of the Huaxi Hongyi Medical University model as the core, explores its application effect in assisting the generation of medical records, and provides a practical path for the construction and application of artificial intelligence in medical institutions. Methods Through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, a large-scale medical model 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. Results Taking the assisted generation of discharge records as an example, in the pilot department, the average completion time of writing was reduced from 21 minutes to 5 minutes (a decrease of 76.2%), the accuracy rate of the model output reached 92.4%, and the annotation consistency Kappa coefficient was 0.85. Conclusion The model of medical institutions constructing independently controllable large-scale medical models and incubating various applications based on them can provide a reference path for the artificial intelligence construction of similar institutions.