Objective To address the challenges of constructing large language models for traditional Chinese medicine(TCM)classics,which are complex and expensive to fine-tune,this study explores a lightweight fine-tuning method for such models,aiming to develop a question-answering model centered on TCM classics,particularly various editions of Shang Han Lun through the ages.Methods Dataset construction involved designing prompts to guide GPT-4 in generating Q&A pairs based on Shang Han Lun and integrating them with the ShenNong_TCM_Dataset and cMedQA2 datasets.Five general-purpose large models were selected for Lora fine-tuning.The best model was chosen through evaluation,and the performance of multiple quantized versions was validated.Results After fine-tuning,the BLEU,ROUGE-1,ROUGE-2,and ROUGE-L metrics for the Qwen-7B-Chat model improved by 17.61,19.63,14.3,and 21.4,respectively,compared to the base model.Conclusion The selected model in this study is capable of effectively understanding and utilizing professional terms and concepts from TCM classics,such as Shang Han Lun,to provide accurate answers to user queries.Compared to similar models,it requires lower fine-tuning costs and computational power,contributing to the dissemination of TCM knowledge and the development of intelligent systems.

Objective To address the challenges of constructing large language models for traditional Chinese medicine(TCM)classics,which are complex and expensive to fine-tune,this study explores a lightweight fine-tuning method for such models,aiming to develop a question-answering model centered on TCM classics,particularly various editions of Shang Han Lun through the ages.Methods Dataset construction involved designing prompts to guide GPT-4 in generating Q&A pairs based on Shang Han Lun and integrating them with the ShenNong_TCM_Dataset and cMedQA2 datasets.Five general-purpose large models were selected for Lora fine-tuning.The best model was chosen through evaluation,and the performance of multiple quantized versions was validated.Results After fine-tuning,the BLEU,ROUGE-1,ROUGE-2,and ROUGE-L metrics for the Qwen-7B-Chat model improved by 17.61,19.63,14.3,and 21.4,respectively,compared to the base model.Conclusion The selected model in this study is capable of effectively understanding and utilizing professional terms and concepts from TCM classics,such as Shang Han Lun,to provide accurate answers to user queries.Compared to similar models,it requires lower fine-tuning costs and computational power,contributing to the dissemination of TCM knowledge and the development of intelligent systems.

Objective:To explore the effectiveness of a modified puncture method in hemodialysis patients with difficult internal fistula.Methods:From January 2022 to October 2023, patients with difficult internal fistula undergoing dialysis at the Blood Purification Center of Qingdao Municipal Hospital were selected for the study using the convenience sampling method. According to the hemodialysis time, patients dialyzed on Mondays, Wednesdays, and Fridays were included in the conventional group, and patients dialyzed on Tuesdays, Thursdays, and Saturdays were included in the experimental group, with 56 cases in each group. Internal fistula puncture was performed in the conventional group using the traditional puncture method and in the experimental group using the modified puncture method. The success rate of one-time puncture of internal fistula and the injury rate of internal fistula were compared between the two groups of patients.Results:The success rate of one-time puncture of internal fistula in the experimental group was higher than that in the conventional group, with a statistical difference ( P<0.05). The injury rate of the internal fistula vessel of the experimental group was lower than that of the conventional group, and the difference was statistically significant ( P<0.05) . Conclusions:Modified puncture methods have a positive effect on increasing the success rate of a one-time puncture of the internal fistula and decreasing the rate of internal fistula injuries in patients with difficult internal fistula.

OBJECTIVE To standardize the strategies for prevention and control of Chikungunya(CHIK)in healthcare in-stitutions so as to reduce the risk of transmission in the institutions.METHODS A working group comprising the ex-perts in hospital infection control,infectious diseases,and microbiology systematically reviewed domestic and international evidence and current guidelines,integrated China's vector ecology and healthcare realities,conducted two rounds of Delphi to achieve expert consensus,and graded the evidence and recommendation strength using the Oxford Centre for Evidence Based Medicine system.RESULTS The consensus issues 18 actionable recommendations on triage,patient mosquito-proof isolation,integrated vector control,protection of susceptible populations,environmental cleaning and disinfection,specimen management,medical textile handling,and outbreak emergency response,with each statement assigned an evi-dence level and recommendation strength.CONCLUSION This consensus is for the first time in China to provide evidence-graded strategies for control of CHIK in healthcare institutions,offering work flow-oriented,implementable guidance for clinicians,laboratorians,and infection-control personnel under different risk scenarios and enhancing the comprehensive coping capacity of the healthcare institutions.

OBJECTIVE To investigate the distribution and drug resistance of multidrug-resistant bacteria in the neonatal intensive care unit of a three-A children's hospital in Henan Province,and to provide reference for ational drug use in clinical practice.METHODS Clinical specimens from hospitalized newborns in neonatal intensive care unit from a three-A children's hospital from Jan.1,2019 to Dec.31,2023 were subjected to etiological exam-ination and drug sensitivity test,and to analyze the distribution and drug resistance of multidrug-resistant bacteri-a in hospitalized newborns.RESULTS During the 5-year period,1139 strains of multidrug-resistant bacteria were i-solated,including 229 gram-positive bacteria(20.11％)and 910 gram-negative bacteria(79.89％).There were 92 strains of methicillin-resistant Staphylococcus aureus(MRSA)(accounting for 8.08％),57 strains(accounting for 5.00％)of methicillin-resistant coagulase-negative Staphylococcus epidermidis and 28 strains(accounting for 2.46％)of methicillin-resistant coagulase-negative human Staphylococcus.370 strains(accounting for 32.48)of carbapenem-resistant Klebsiella pneumoniae(CRKP),268 strains(accounting for 23.53％)of extenspectrum β-lactamase-producing Escherichia coli and 85 strains(accounting for 7.46％)of K.pneumoniae,there were 767 sputum specimens(67.34％),160 blood specimens from peripheral intravenous puncture and central venous cath-eterization(PICC)(14.05％),63 bronchoalveolar lavage fluid specimens(5.53％),29 secretion specimens(eye and wound secretions)(2.54％),and 120 other specimens(10.54％).K.pneumoniae and E.coli producing su-per-broad spectrum β-lactamase,CRKP and MRSA were the main drug-resistant bacteria.CONCLUSION The sit-uation of drug resistance in neonatal intensive care unit is serious,therefore monitoring bacterial resistance should be strengthened according to the clinical laboratory results,and antibiotics should be applied rationally.

Objective:To explore the effectiveness of a modified puncture method in hemodialysis patients with difficult internal fistula.Methods:From January 2022 to October 2023, patients with difficult internal fistula undergoing dialysis at the Blood Purification Center of Qingdao Municipal Hospital were selected for the study using the convenience sampling method. According to the hemodialysis time, patients dialyzed on Mondays, Wednesdays, and Fridays were included in the conventional group, and patients dialyzed on Tuesdays, Thursdays, and Saturdays were included in the experimental group, with 56 cases in each group. Internal fistula puncture was performed in the conventional group using the traditional puncture method and in the experimental group using the modified puncture method. The success rate of one-time puncture of internal fistula and the injury rate of internal fistula were compared between the two groups of patients.Results:The success rate of one-time puncture of internal fistula in the experimental group was higher than that in the conventional group, with a statistical difference ( P<0.05). The injury rate of the internal fistula vessel of the experimental group was lower than that of the conventional group, and the difference was statistically significant ( P<0.05) . Conclusions:Modified puncture methods have a positive effect on increasing the success rate of a one-time puncture of the internal fistula and decreasing the rate of internal fistula injuries in patients with difficult internal fistula.

OBJECTIVE To investigate the distribution and drug resistance of multidrug-resistant bacteria in the neonatal intensive care unit of a three-A children's hospital in Henan Province,and to provide reference for ational drug use in clinical practice.METHODS Clinical specimens from hospitalized newborns in neonatal intensive care unit from a three-A children's hospital from Jan.1,2019 to Dec.31,2023 were subjected to etiological exam-ination and drug sensitivity test,and to analyze the distribution and drug resistance of multidrug-resistant bacteri-a in hospitalized newborns.RESULTS During the 5-year period,1139 strains of multidrug-resistant bacteria were i-solated,including 229 gram-positive bacteria(20.11％)and 910 gram-negative bacteria(79.89％).There were 92 strains of methicillin-resistant Staphylococcus aureus(MRSA)(accounting for 8.08％),57 strains(accounting for 5.00％)of methicillin-resistant coagulase-negative Staphylococcus epidermidis and 28 strains(accounting for 2.46％)of methicillin-resistant coagulase-negative human Staphylococcus.370 strains(accounting for 32.48)of carbapenem-resistant Klebsiella pneumoniae(CRKP),268 strains(accounting for 23.53％)of extenspectrum β-lactamase-producing Escherichia coli and 85 strains(accounting for 7.46％)of K.pneumoniae,there were 767 sputum specimens(67.34％),160 blood specimens from peripheral intravenous puncture and central venous cath-eterization(PICC)(14.05％),63 bronchoalveolar lavage fluid specimens(5.53％),29 secretion specimens(eye and wound secretions)(2.54％),and 120 other specimens(10.54％).K.pneumoniae and E.coli producing su-per-broad spectrum β-lactamase,CRKP and MRSA were the main drug-resistant bacteria.CONCLUSION The sit-uation of drug resistance in neonatal intensive care unit is serious,therefore monitoring bacterial resistance should be strengthened according to the clinical laboratory results,and antibiotics should be applied rationally.

OBJECTIVE To standardize the strategies for prevention and control of Chikungunya(CHIK)in healthcare in-stitutions so as to reduce the risk of transmission in the institutions.METHODS A working group comprising the ex-perts in hospital infection control,infectious diseases,and microbiology systematically reviewed domestic and international evidence and current guidelines,integrated China's vector ecology and healthcare realities,conducted two rounds of Delphi to achieve expert consensus,and graded the evidence and recommendation strength using the Oxford Centre for Evidence Based Medicine system.RESULTS The consensus issues 18 actionable recommendations on triage,patient mosquito-proof isolation,integrated vector control,protection of susceptible populations,environmental cleaning and disinfection,specimen management,medical textile handling,and outbreak emergency response,with each statement assigned an evi-dence level and recommendation strength.CONCLUSION This consensus is for the first time in China to provide evidence-graded strategies for control of CHIK in healthcare institutions,offering work flow-oriented,implementable guidance for clinicians,laboratorians,and infection-control personnel under different risk scenarios and enhancing the comprehensive coping capacity of the healthcare institutions.

OBJECTIVE Treatise on Cold Damage is one of the"Four Classics of Traditional Chinese Medicine,"containing a wealth of medical practice experience and medication rules.However,there has been insufficient data mining in the ancient literature of Treatise on Cold Damage,particularly due to the complex contextual semantics,making it challenging to fully grasp the interrelation-ships.This study aims to conduct entity recognition in Treatise on Cold Damage to facilitate comprehensive knowledge extraction.METHODS A Bert-BiLSTM-RPRSA-CRF model was constructed based on the specialized terminology and concise sentence struc-ture of the ancient literature.By incorporating a relative position representation self-attention(RPRSA)layer,this named entity recog-nition model aimed to identify entities within the text while learning information at different levels,thereby enhancing accuracy.RE-SULTS Experimental verification demonstrated that our named entity recognition model achieved F1-Score,precision,and recall rates of 88.24%,88.48%,and 88.00%respectively on the Treatise on Cold Damage dataset,outperforming other commonly used models.CONCLUSION Our method outperforms other models in identifying entities within Treatise on Cold Damage,providing a foundation for information extraction from traditional Chinese medicine ancient texts such as Treatise on Cold Damage while offering ef-fective means for intelligent assisted diagnosis and treatment in traditional Chinese medicine.

OBJECTIVE To construct a large language model for TCM question-answering.METHODS TCM corpora were built by collecting TCM classics such as Treatise on Cold Damage,TCM textbooks,prescriptions from famous TCM doctors,and other manually annotated TCM datasets.A TCM knowledge vector library was constructed.The RAG technology was fused with the P-Tuning v2 fine-tuning method and the large language model(ChatGLM2-6B)to build the TCM question-answering large language model.RESULTS Recision,Recall,and F1 score were used as evaluation metrics for knowledge question-answering tasks.The model achieved over 90%accuracy in simple TCM question-answering,with the highest accuracy in component-type questions,reac-hing an F1 score of 0.928.The accuracy of medium to high difficulty questions ranged from 75.8%to 87.7%,with F1 scores all ex-ceeding 0.766.Expert ratings based on diversity and accuracy were used as evaluation metrics for TCM question generation tasks,and the model in this paper scored 9.5 points higher than the baseline model.CONCLUSION The model in this paper demonstrates good semantic understanding and high reliability,effectively alleviating model hallucinations and helping patients clarify their question intentions.It is of great significance for advancing research on TCM knowledge and providing personalized interactive answers.It also provides an innovative approach to promoting the inheritance and popularization of TCM experience and the intelligent construction of TCM diagnosis and treatment.