Purpose/Significance To summarize the application progress of artificial intelligence (AI) in the field of digestive endoscopy, to analyze the key challenges and look forward to future trends, so as to provide guidance for clinical practice and research. Method/Process Domestic and international literature databases such as PubMed, Web of Science, and CNKI are retrieved. The application research of AI in the auxiliary diagnosis, process optimization and treatment precision of digestive endoscopy is sorted out. Result/Conclusion Although AI has significant clinical value in the field of digestive endoscopy, its application still faces major challenges, and its prospects and limitations need to be further discussed.

Purpose/Significance To analyze the characteristics and problems of the policy texts of hospital informatization in China,and to explore the methods of policy optimization.Method/Process Related policy documents of hospital informatization at the national level are re-trieved from March 17,2009 to August 31,2023,and the policy texts are coded and analyzed from two dimensions of policy tools and system theory.Result/Conclusion The policy of hospital informatization in China is mainly based on environment-oriented policy tools,and it is sug-gested to pay more attention to the use of demand-oriented and supply-oriented tools.In addition,it is necessary to scientifically optimize the internal structure of policy tools,strengthen the use of internal submodels,and improve the systematization of policy tools.

Objective/Significance To summarize the relevant policies,practical applications and promotion effects of hospital infor-mation systems(HIS)on the cloud in China,to analyze national policy orientation and application status,so as to put forward reasonable proposals on the next action and promotion strategy.Method/Process Relevant policy documents and applications of HIS on the cloud are retrieved from national and provincial government websites in China,and the policy development rules and opportunities and challen-ges faced are summarized.Relevant articles published from 2010 to 2023 are searched on CNKI to summarize the concrete practice of HIS on the cloud.Result/Conclusion It is suggested that hospitals with existing conditions can make full use of the current national poli-cy dividend and actual business expansion needs to migrate to the cloud as soon as possible,and relevant departments should also issue more targeted development strategies and supporting implementation guidelines to specifically guide hospitals to migrate to the cloud scien-tifically,effectively and safely,so as to accelerate the generation of new forms of medical industry and fully meet the needs of public health care in the new era.

Purpose/Significance To conduct the real world research on the application and impact of artificial intelligence(AI)technology in medical institutions,and to assist in intelligent governance decision-making in the field of medicine and health.Method/Process Taking Peking University Third Hospital as the research scene,the AI medical social experiment is carried out through literature meta-analysis,knowledge graph construction and mixed methodology research.Result/Conclusion Scholars at home and abroad are cautious and optimistic about the application of AI technology in the field of health.The research,development and application of AI technology in domestic public hospitals are very active,but small-scale field studies suggest that AI technology may lead to problems such as misleading decision-making and weakening of human subjectivity while improving the efficiency of diagnosis and treatment.In-telligent governance in the field of health,represented by AI technology,requires a long period and a wide range of sociological observa-tions.It is recommended to build a research base for medical AI technology R&D and supervision based on public hospitals,and continue to pay attention to issues such as human subjectivity,medical ethics and scientific and technological ethics in AI social governance.

Purpose/Significance The relative positions of causality words are utilized to assist deep learning models to improve cau-sality prediction and mine medical text gain information.Method/Process The relative position information of causality words in medical texts is represented as a relational feature layer embedded in a pre-trained language model,and the baseline model is integrated for enti-ty recognition and relationship extraction.Result/Conclusion The F1 value of the model embedded in the relational feature layer is im-proved by 2.92 percentage points and 6.41 percentage points compared with the baseline models BERT-BiLSTM-CRF and CasRel,re-spectively,with better causal prediction capacity.

Purpose/Significance To improve the classification and evaluation mode of medical safety incidents,and to improve work efficiency and timeliness.Method/Process The data of previous medical safety incidents are pre-processed,BERT model is used for training,testing and iterative optimization,and an intelligent classification and prediction model for medical safety incidents is built.Re-sult/Conclusion The model is used to classify 466 medical safety incidents reported by clinical departments from January to November 2022,and F1 value reaches 0.66.The application of BERT model in the classification and evaluation of medical safety incidents can im-prove work efficiency and timeliness,and help timely intervene in medical safety risks.

Purpose/Significance Achieving automatic generation of medical imaging reports is important for reducing the workload of radiologists and promoting the standardization of clinical workflow.Method/Process Focusing on finding the chest report generation mod-els with open source code in recent years,the paper develops an automatic medical image report generation method based on the CDGPT2 model.Result/Conclusion The advantages of the model in report generation are still to be explored,the quality of reports generated after modifications to the decoder inputs of the model is not high.Future research could improve the performance of the model by using large datasets and incorporating more clinical information.

Purpose/Significance To analyze the satisfaction,service effectiveness and willingness to participate in telemedicine services from the perspective of medical staff,and to identify the existing problems.Method/Process The research group conducts an e-lectronic questionnaire survey for medical institutions across the country,and collects a total of 1 524 valid questionnaires.Based on questionnaire survey data,logistic regression models are constructed to analyze the key factors that affect the evaluation and attitude of medical staff.Result/Conclusion The overall satisfaction and service effectiveness of medical staff to telemedicine services are at a high level,and their willingness to participate is strong.It is necessary to improve the telemedicine service system and promote the experience of medical staff by strengthening infrastructure construction,optimizing service process,and perfecting incentive mechanisms.

Purpose/Significance To review the knowledge discovery methods based on knowledge graph in the biomedical field,and to provide references for researchers.Methods/Process The paper summarizes the knowledge discovery methods based on knowledge graph by systematically searching and analyzing the relevant literatures,and compares the advantages and disadvantages of various knowl-edge discovery methods.It points out that the limitations and challenges of knowledge discovery methods based on knowledge graph in the biomedical field,and puts forward suggestions and prospects.Result/Conclusion In the future research,it is suggested to improve the in-terpretability of knowledge discovery results,build an effective result evaluation framework,and establish a standardized knowledge dis-covery process with multi-domain experts'collaboration,so as to improve the quality and efficiency of knowledge discovery research.

Purpose/Significance By using data mining methods,the medication rules and prescription characteristics of traditional Chinese medicine(TCM)for treating hypertension with preserved ejection fraction heart failure are discussed.Method/Process The da-tabase is established based on the TCMprescription information of hypertensive patients with preserved ejection fraction heart failure ad-mitted to the Cardiovascular Disease Department of the First Affiliated Hospital of Heilongjiang University of Chinese Medicine from Janu-ary 2019 to July 2022.SPSS Statistics and Moderler software are used to analyze the frequency,taste,meridian tropism,efficacy,associ-ation rules,clustering and factor analysis of the prescriptions to explore medication rules.Result/Conclusion TCMin the treatment of hy-pertension with preserved ejection fraction heart failure is mainly to replenish qi and spleen,nourish the heart and calm the mind,relieve phlegm,relieve cough and asthma,and pay attention to promoting blood circulation and removing blood stasis,promoting water infiltra-tion and dampness,which can reflect the overall concept of TCMand the characteristics of diagnosis and treatment based on syndrome dif-ferentiation and provide references for clinical medication.