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.

Based on LI Gao's theory of "heavy obstruction" and "blockage of the nine orifices"， this paper proposes the pathological concept of "heavy obstruction and orifice blockage". It is suggested that the core pathogenesis of functional constipation （FC） lies in simultaneous sinking of spleen and lung， together with accumulation and obstruction of dampness and turbidity， resulting in impaired movement of intestinal qi. Within this framework， spleen deficiency with sinking of dampness is considered as the primary pathological mechanism of outlet obstructive constipation （OOC）， while sinking of lung qi is regarded as the key mechanism underlying slow transit constipation （STC）. When both pathological mechanisms coexist， mixed constipation （MC） develops. Guided by this theory， FC is classified into three patterns for syndrome-based treatment. OOC is treated by promoting bowel movement， descending turbid pathogens， and opening the orifices to restore function， with self-formulated Shengxian Tongqiao Decoction （升陷通窍汤）. STC is treated by diffusing lung qi， regulating spleen function， raising sinking qi， and promoting transportation， with self-formulated Xuanfei Yunpi Decoction （宣肺运脾汤）. MC is treated by regulating lung and spleen function， simultaneously raising clear qi and descending turbidity， with self-formulated Xuanyun Tongqiao Decoction （宣运通窍汤）. In clinical practice， modifications should be made according to accompanying syndromes and individual conditions.

Natural products (NPs) have long held a significant position in various fields such as medicine, food, agriculture, and materials. The chemical space covered by NPs is extensive but often underexplored. Therefore, high-throughput and efficient methodologies for the annotation and discovery of NPs are desired to address the complexity and diversity of NP-based systems. Mass spectrometry (MS) has emerged as a powerful platform for the annotation and discovery of NPs. MS databases provide vital support for the structural characterization of NPs by integrating extensive mass spectral data and sample information. Additionally, the released annotation methodologies, based on a variety of informatics tools, continuously improve the ability to annotate the structure and properties of compounds. This review examines the current mainstream databases and annotation methodologies, focusing on their advantages and limitations. Prospects for future technological advancements are then discussed in terms of novel applications and research objectives. Through a systematic overview, this review aims to provide valuable insights and a reference for MS-based NPs annotation, thereby promoting the discovery of novel natural entities.
Biological Products/chemistry* ; Mass Spectrometry/methods* ; Databases, Factual ; Drug Discovery/methods* ; Humans

Objective To analyze the law of acupoint selection and compatibility of acupuncture and moxibustion and the application law of acupuncture and moxibustion in the treatment of lactational mastitis using complex network technology.Methods The clinical research literature about acupuncture and moxibustion treatment of lactational mastitis was retrieved from CNKI,CBM,Wanfang Data,VIP and PubMed from the establishment of the databases to March 15,2025.The literature was screened according to the standards to build a prescription database of acupuncture and moxibustion treatment of lactational mastitis.SPSS Modeler 18.0 software was used to analyze association rules,and Gephi 0.9 software was used for complex network analysis.Results A total of 108 articles were included.141 acupuncture and moxibustion prescriptions were extracted,involving 74 acupoints,with a total use frequency of 677 times.The high-frequency acupoints were Jianjing,Danzhong,Rugen,Zusanli,Neiguan,etc.Specific acupoints were mainly composed of Wushu acupoints(169 times,21.10%);the acupoints were mainly distributed in the limbs(36);the most frequently used meridian was stomach meridian(168 times,24.82%).The combination of acupoints with the highest correlation was Jianjing-Neiguan-Rugen.Complex network analysis identified 22 core acupoints,with the most commonly used acupuncture method being filiform needle acupuncture(79 times).Conclusion Acupuncture and moxibustion treatment of lactational mastitis pays special attention to the selection of stomach meridian.The compatibility mode is mainly from top to bottom,and the corresponding acupoints are selected according to syndrome differentiation.

Objective: To analyze the current status of clinical trial registration for childhood and adolescent obesity, so as to provide insights for the registration and implementation of related trials. Methods: ClinicalTrials.gov and the ChiCTR database were searched for obesity related clinical trial registrations up to 1 June 2025. Data included basic characteristics (registration region, date, funding source, status, sample size), trial design features, participant demographics, interventions, outcome measures, methodology, and reporting quality. Statistical and descriptive analyses were conducted. Results: A total of 1 450 registered studies were included, covering 59 regions globally. North America hosted the highest number of registrations (876, 60.41%), with the United States accounting for the largest share (771, 53.17%). The earliest registered study dated to 1985, while 2016 saw the highest annual registrations ( n =87). Funding sources predominantly originated from universities (834 studies, 57.52%). Currently, completed trials accounted for the majority (1 003 trials, 69.17%). Globally, the majority of studies employed sample sizes within the 11-50 range (331 studies, 22.83%). Interventional studies predominated in design type (1 186, 81.79%), predominantly employing randomized parallel group controlled trials. Main interventions included comprehensive lifestyle interventions, physical activity and exercise interventions, and diet and nutrition interventions. High frequency outcome indicators primarily involved body composition and anthropometric measurements, metabolic and biochemical indicators, etc. Methodology and reporting quality required improvement. Conclusions The registration of clinical trials related to childhood and adolescent obesity globally shows a positive development trend, but issues of regional imbalance and methodological limitations exist. It is necessary to strengthen clinical trial registration norms, optimize study designs, and focus on the innovation of interventions and the systematicity of outcome indicators.

Objective To explore the potential clinical value of the ratio of glycated albumin to albumin(GA/ALB)in the occurrence of heart failure(HF)among patients with coronary atherosclerotic heart disease(CHD).Methods A total of 337 CHD patients admitted to the Department of Cardiology in Shanxi Provincial People's Hospital from July 2023 to June 2024 were selected in this study.CHD patients were divided into HF group and non-HF group based on whether they progressed to HF.The clinical data and laboratory parame-ters of the two groups were compared.Restricted cubic spline curve was used to analyze the relationship be-tween GA/ALB levels and the risk of HF in CHD patients.Receiver operating characteristic curve was applied to evaluate the diagnostic efficacy of GA/ALB,GA,platelet to lymphocyte ratio(PLR),and monocyte to lym-phocyte ratio(MLR)in CHD patients with the occurrence of HF.Logistic regression was used to explore the relationship between serum GA/ALB levels and the risk of CHD patients occurrence of HF,and to analyze the degree of influence and stability of subgroup variables on results.Results There were statistically significant differences in GA/ALB,GA,PLR,MLR,and other indicators between the HF group and the non-HF group in CHD patients(P＜0.05).A non-linear relationship was observed between GA/ALB levels and the risk of HF in CHD patients.When the value of GA/ALB multiplied by 10 was less than 5.751,the risk of HF in CHD pa-tients increased with the increase of GA/ALB levels(P＜0.001).GA/ALB was an effective predictor for HF occurrence in CHD patients.Multivariable Logistic regression model showed that GA/ALB was an independ-ent risk factor for CHD patients with occurrence of HF.Subgroup analysis also confirmed the stability of GA/ALB in predicting the occurrence of HF in CHD patients.Conclusion GA/ALB is an independent risk factor for the occurrence of HF in CHD patients,and monitoring GA/ALB levels provides predictive value for the oc-currence of HF in these patients.

Objective:To screen the optimal machine learning model for predicting the recurrence condition of hepatocellular carcinoma (HCC) at different time points post-surgery, based on the cutoff value of the Ki67 positive proliferation index condition calculated from recurrence-free survival and combined with various clinical features.Methods:retrospective study included initially treated patients with solitary HCC who underwent radical surgery at the Fifth Medical Center of the PLA General Hospital from January 2013 to March 2023. Data included general clinical data, preoperative laboratory parameters, and surgical pathology information about the subjects. The postoperative recurrence status was assessed by querying the medical record system or by telephone follow-up. The Ki67 positive index cutoff value was determined by the X-tile software based on the patient's recurrence-free survival status and time analysis. Survival rates were calculated using the Kaplan-Meier method, and survival curves were plotted. The study population was randomly divided into training and testing groups in a 7:3 ratio using a computer-generated random number method. The minimum redundancy maximum relevance (mRMR) method was used for feature variable selection. Predictive models for postoperative HCC recurrence conditions in patients with HCC were constructed using random forest, support vector machine, logistic regression, and gradient boosting decision tree machine learning algorithms. Inter-group comparisons for continuous data were performed using the t-test or Mann-Whitney U test. Inter-group comparisons of enumeration data were performed using the Pearson χ2 test, continuity-corrected χ2 test, or Fisher's exact test. Results:The cutoff values for the Ki67 positivity index were 0.3 and 0.5 in 510 cases, with a follow-up time ranging from 1.2 to 11.4 years (median: 6.2 years). The recurrence-free survival time was between 1 and 135 months (median: 32 months), with recurrence-free survival rates post-surgery at 1, 2, 3, and 5 years were 87.5%, 77.1%, 61.2%, and 54.5%, respectively. The top five variables predicted HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years, in accordance with information obtained by the mRMR screen out. The Ki67 positivity index screened a successfully constructed machine learning model to predict HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years. The machine learning model based on the gradient boosting decision tree algorithm had the best prediction performance among them (areas under the receiver operating characteristic curves for predicting HCC recurrence within six months in the training and validation sets were 0.996 and 0.946, and accuracies were 0.972 and 0.935, respectively).Conclusion:A machine learning model was successfully constructed using the Ki67 positivity index combined with four readily available clinical features to predict HCC recurrence. The machine learning model based on the gradient boosting decision tree algorithm demonstrated the best performance in terms of predicting HCC recurrence within six months after surgery.

Objective:To screen the optimal machine learning model for predicting the recurrence condition of hepatocellular carcinoma (HCC) at different time points post-surgery, based on the cutoff value of the Ki67 positive proliferation index condition calculated from recurrence-free survival and combined with various clinical features.Methods:retrospective study included initially treated patients with solitary HCC who underwent radical surgery at the Fifth Medical Center of the PLA General Hospital from January 2013 to March 2023. Data included general clinical data, preoperative laboratory parameters, and surgical pathology information about the subjects. The postoperative recurrence status was assessed by querying the medical record system or by telephone follow-up. The Ki67 positive index cutoff value was determined by the X-tile software based on the patient's recurrence-free survival status and time analysis. Survival rates were calculated using the Kaplan-Meier method, and survival curves were plotted. The study population was randomly divided into training and testing groups in a 7:3 ratio using a computer-generated random number method. The minimum redundancy maximum relevance (mRMR) method was used for feature variable selection. Predictive models for postoperative HCC recurrence conditions in patients with HCC were constructed using random forest, support vector machine, logistic regression, and gradient boosting decision tree machine learning algorithms. Inter-group comparisons for continuous data were performed using the t-test or Mann-Whitney U test. Inter-group comparisons of enumeration data were performed using the Pearson χ2 test, continuity-corrected χ2 test, or Fisher's exact test. Results:The cutoff values for the Ki67 positivity index were 0.3 and 0.5 in 510 cases, with a follow-up time ranging from 1.2 to 11.4 years (median: 6.2 years). The recurrence-free survival time was between 1 and 135 months (median: 32 months), with recurrence-free survival rates post-surgery at 1, 2, 3, and 5 years were 87.5%, 77.1%, 61.2%, and 54.5%, respectively. The top five variables predicted HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years, in accordance with information obtained by the mRMR screen out. The Ki67 positivity index screened a successfully constructed machine learning model to predict HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years. The machine learning model based on the gradient boosting decision tree algorithm had the best prediction performance among them (areas under the receiver operating characteristic curves for predicting HCC recurrence within six months in the training and validation sets were 0.996 and 0.946, and accuracies were 0.972 and 0.935, respectively).Conclusion:A machine learning model was successfully constructed using the Ki67 positivity index combined with four readily available clinical features to predict HCC recurrence. The machine learning model based on the gradient boosting decision tree algorithm demonstrated the best performance in terms of predicting HCC recurrence within six months after surgery.

Kidney transplantation is an effective treatment for end-stage renal disease.However,post transplantation diabetes mellitus(PTDM)is a common complication after kidney transplantation,affecting 10%to 40%of recipients and increasing the risk of cardiovascular disease,infections,sepsis and other conditions.The pathogenesis of PTDM is complex,including pancreatic β-cell dysfunction and insulin resistance.Tacrolimus,a commonly used immunosuppressive drug,is an independent risk factor for PTDM.Its mechanisms include damaging pancreatic β-cells,mediating impaired mitochondrial autophagy,etc.In addition,tacrolimus also raises blood glucose levels through various pathways,such as affecting gut microbiota metabolism and activating bile acid signaling pathways.In recent years,some new anti-diabetic drugs have shown certain application prospects in kidney transplant recipients,but the evidence-based medical evidence for their combined use still needs further exploration.In the future,it is necessary to conduct in-depth research on the multiple sites of action of tacrolimus to reduce the occurrence of PTDM and improve the prognosis of kidney transplant recipients.

Objective To analyze the law of acupoint selection and compatibility of acupuncture and moxibustion and the application law of acupuncture and moxibustion in the treatment of lactational mastitis using complex network technology.Methods The clinical research literature about acupuncture and moxibustion treatment of lactational mastitis was retrieved from CNKI,CBM,Wanfang Data,VIP and PubMed from the establishment of the databases to March 15,2025.The literature was screened according to the standards to build a prescription database of acupuncture and moxibustion treatment of lactational mastitis.SPSS Modeler 18.0 software was used to analyze association rules,and Gephi 0.9 software was used for complex network analysis.Results A total of 108 articles were included.141 acupuncture and moxibustion prescriptions were extracted,involving 74 acupoints,with a total use frequency of 677 times.The high-frequency acupoints were Jianjing,Danzhong,Rugen,Zusanli,Neiguan,etc.Specific acupoints were mainly composed of Wushu acupoints(169 times,21.10%);the acupoints were mainly distributed in the limbs(36);the most frequently used meridian was stomach meridian(168 times,24.82%).The combination of acupoints with the highest correlation was Jianjing-Neiguan-Rugen.Complex network analysis identified 22 core acupoints,with the most commonly used acupuncture method being filiform needle acupuncture(79 times).Conclusion Acupuncture and moxibustion treatment of lactational mastitis pays special attention to the selection of stomach meridian.The compatibility mode is mainly from top to bottom,and the corresponding acupoints are selected according to syndrome differentiation.