Objective To develop a system for retrieving information from clinical records of Traditional Chinese Medicine(TCM)based on generative large language models(LLMs).Methods Applicational needs of the system were analyzed,and entity types to be retrieved were identified.The functions,workflows,and architecture of the system were designed by combining the automatic retrieval capabilities of LLMs with human-in-the-loop(HITL).The software was developed using such frameworks as vLLM and Node.js.Interaction of multiple commercial/open source LLMs was implemented using OpenAI-compatible interfaces.The quality of information retrieved from LLMs was enhanced by prompt engineering.Results This system supported task allocation,automatic retrieval of structured information,and manual review.To evaluate its performance,the moonshot-v1-8k model was used to retrieve clinical records of TCM before manual edition was performed.Combining large language model pre-annotation with meticulous annotator edits improved accuracy by 26.6％compared to the BERT-BiLSTM-CRF model,and enhanced extraction efficiency by 1.6-fold relative to purely manual methods.Conclusion General generative LLMs can retrieve a wide range of entity information from TCM records with high accuracy and scalability.The design and implementation of this system approach may provide a useful reference for developing other biomedical information retrieval systems.

A 43-year-old male was admitted to General Hospital of Northern Theater Command with exacerbation of chest pain for 10 d. Computed tomographic angiography (CTA) showed an irregular aortic arch aneurysm involving the left subclavian artery (LSA), with penetrating aortic ulcer and intramural hematoma. A modified fenestrated thoracic endovascular aortic repair (TEVAR) technique was performed successfully. Follow-up CTA showed that stent grafts were well-apposed, without endoleaks, migration, or branch artery occlusion, and the hematoma was almost completely absorbed. In this case, precise fenestrations were created by measurements based on three-dimensional CT reconstruction and angiography. Furthermore, the physician chose an LSA approach to catch the guide wire and deployed branched stent grafts, considering the oblique direction of this branch and the small size of the fenestration. This case shows that pre-fenestrated and inner bare stent enhancing TEVAR is a safe and feasible technique for repair of complicated aortic arch aneurysm.

A 43-year-old male was admitted to General Hospital of Northern Theater Command with exacerbation of chest pain for 10 d. Computed tomographic angiography (CTA) showed an irregular aortic arch aneurysm involving the left subclavian artery (LSA), with penetrating aortic ulcer and intramural hematoma. A modified fenestrated thoracic endovascular aortic repair (TEVAR) technique was performed successfully. Follow-up CTA showed that stent grafts were well-apposed, without endoleaks, migration, or branch artery occlusion, and the hematoma was almost completely absorbed. In this case, precise fenestrations were created by measurements based on three-dimensional CT reconstruction and angiography. Furthermore, the physician chose an LSA approach to catch the guide wire and deployed branched stent grafts, considering the oblique direction of this branch and the small size of the fenestration. This case shows that pre-fenestrated and inner bare stent enhancing TEVAR is a safe and feasible technique for repair of complicated aortic arch aneurysm.