Objective: To develop a clinical decision and prescription generation system (CDPGS) specifically for diarrhea in traditional Chinese medicine (TCM), utilizing a specialized large language model (LLM), Qwen-TCM-Dia, to standardize diagnostic processes and prescription generation. Methods: Two primary datasets were constructed: an evaluation benchmark and a fine-tuning dataset consisting of fundamental diarrhea knowledge, medical records, and chain-of-thought (CoT) reasoning datasets. After an initial evaluation of 16 open-source LLMs across inference time, accuracy, and output quality, Qwen2.5 was selected as the base model due to its superior overall performance. We then employed a two-stage low-rank adaptation (LoRA) fine-tuning strategy, integrating continued pre-training on domain-specific knowledge with instruction fine-tuning using CoT-enriched medical records. This approach was designed to embed the clinical logic (symptoms → pathogenesis → therapeutic principles → prescriptions) into the model’s reasoning capabilities. The resulting fine-tuned model, specialized for TCM diarrhea, was designated as Qwen-TCM-Dia. Model performance was evaluated for disease diagnosis and syndrome type differentiation using accuracy, precision, recall, and F1-score. Furthermore, the quality of the generated prescriptions was compared with that of established open-source TCM LLMs. Results: Qwen-TCM-Dia achieved peak performance compared to both the base Qwen2.5 model and five other open-source TCM LLMs. It achieved 97.05% accuracy and 91.48% F1-score in disease diagnosis, and 74.54% accuracy and 74.21% F1-score in syndrome type differentiation. Compared with existing open-source TCM LLMs (BianCang, HuangDi, LingDan, TCMLLM-PR, and ZhongJing), Qwen-TCM-Dia exhibited higher fidelity in reconstructing the “symptoms → pathogenesis → therapeutic principles → prescriptions” logic chain. It provided complete prescriptions, whereas other models often omitted dosages or generated mismatched prescriptions. Conclusion By integrating continued pre-training, CoT reasoning, and a two-stage fine-tuning strategy, this study establishes a CDPGS for diarrhea in TCM. The results demonstrate the synergistic effect of strengthening domain representation through pre-training and activating logical reasoning via CoT. This research not only provides critical technical support for the standardized diagnosis and treatment of diarrhea but also offers a scalable paradigm for the digital inheritance of expert TCM experience and the intelligent transformation of TCM.

Objective:To study the causes of hemorrhage after laparoscopic pancreaticoduodenectomy (LPD) and to develop countermeasures in its prevention.Methods:The clinical data of 215 patients who underwent LPD at the Department of Hepatobiliary and Pancreatic Surgery of Zhejiang Provincial People's Hospital from December 2013 to May 2020 were reviewed. The patients’ clinical data including gender, age, comorbidities and postoperative complications such as bleeding, pancreatic fistula, biliary fistula and intraperitoneal infection were studied, with the aims to analyze the causes, clinical manifestations and treatment results of post-pancreaticoduodenectomy hemorrhage (PPH) after LPD.Results:Of 215 patients, there were 132 males and 83 females, aged (60.7±10.3) years. PPH occurred in 20 patients, incidence rate was 9.30%(20/215). Early hemorrhage was mainly caused by inadequate hemostasis or loosening of vascular clips, while delayed hemorrhage was mainly caused by gastrointestinal fistula with vascular erosion, arterial injury by intraoperative energy instruments or pseudoaneurysms. Among the 20 patients, 6 patients had early hemorrhage and 14 delayed hemorrhage. There was 1 patient with grade A, 10 with grade B and 9 with grade C hemorrhage. Thirteen patients developed pancreatic fistula, 1 biliary fistula, and 2 intraperitoneal infection. One patient responded well to conservative treatment. Hemostasis was successfully achieved by gastroscopy ( n=1) and interventional therapy ( n=7). Eleven patients required laparotomy for hemostasis. In this study, 14 of 20 patients survivied PPH and 6 patients died. The mortality rate was 30% (6 of 20 patients with PPH). Conclusions:Early hemorrhage was caused by inadequate hemostasis or loosening vascular clips, while delayed hemorrhage was related to gastrointestinal fistula with vascular erosion, arterial injury by intraoperative energy instrument or pseudoaneurysm. Careful hemostasis, adequate protection of blood vessels, and accurate anastomosis should be performed in LPD. DSA angiography should be used for arterial hemorrhage which progressed very rapidly. Interventional therapy including embolism and stenting were means to control arterial bleeding in PPH. Decisive surgical exploration when interventional therapy failed was important in reducing the mortality rate of these patients.

Objective To investigate gender differences of plasma glial cell line-derived neurotro-phic factor (GDNF) levels in patients with major depressive disorder (MDD). Methods MDD subjects (male 20,female 36) and healthy controls (HCs) (male 35,female 45) were divided into four groups by gender. Plasma levels of GDNF were measured and compared in different gender groups. The clinical symp-tom severity of MDD patients was evaluated by 17-item Hamilton Depression Scale (HAMD-17) and Hamil-ton Anxiety Scale (HAMA-17). Results (1)The plasma GDNF level in male patients with major depres-sive disorder (( 1. 55 ± 0. 43 ) pg/ml ) was significantly lower than that in healthy controls (( 1. 86 ± 0. 50)pg/ml,F=4. 64,P=0. 036). There was no significant difference in GDNF level between female de-pression patients((1.62±0.46)pg/ml)) and female healthy control((1. 64±0. 48)pg/ml,F=0. 18,P=0. 672). In HCs,the GDNF level of male was significantly higher than that of female((1. 86±0. 50)pg/ml, (1. 64±0. 48)pg/ml,F=2. 04,P=0. 045). There was no significant difference in GDNF level between male and female patients(P>0. 05). (2) GDNF level in male patients with major depressive disorder was nega-tively correlated with HAMA score(r=-0. 388,P=0. 034). Conclusion The expression of GDNF is affect-ed by sex factors,which may be related to the different pathogenesis of MDD.