ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

OBJECTIVE To summarize the current situation of pharmaceutical clinic service in our hospital over the past five years， and explore sustainable development strategies for service models of pharmaceutical clinics. METHODS A retrospective analysis was conducted on the consultation records of patients who registered and established files at the pharmaceutical clinic in our hospital from January 2019 to December 2023. Statistical analysis was performed on patients’ general information， medication- related problems， and types of pharmaceutical services provided by pharmacists. RESULTS A total of 963 consultation records were included， among which females aged 20-39 years accounted for the highest proportion （66.04%）； obstetrics and gynecology- related consultations accounted for the largest number of cases. Additionally， 80 patients attended follow-up visits at our hospital’s pharmaceutical clinic. A total of 1 029 medication-related issues were resolved， including 538 cases of drug consultations （52.28%）， 453 medication recommendations （44.02%）， 22 medication restructuring（2.14%）， and 16 medication education （1.55%）； the most common types of medication-related problems identified were adverse drug events（70.07%）. CONCLUSIONS Although the pharmaceutical clinic has achieved recognition from clinicians and patients， challenges such as low awareness among healthcare providers and the public persist. Future efforts should focus on strengthening information technology construction， enhancing pharmacist training， and establishing various forms of outpatient pharmaceutical service models.

Combined with elastic network model(ENM),the perturbation response scanning(PRS)has emerged as a robust technique for pinpointing allosteric interactions within proteins.Here,we proposed the PRS analysis of drug-target networks(DTNs),which could provide a promising avenue in network medicine.We demonstrated the utility of the method by introducing a deep learning and network perturbation-based framework,for drug repurposing of multiple sclerosis(MS).First,the MS comorbidity network was constructed by performing a random walk with restart algorithm based on shared genes between MS and other diseases as seed nodes.Then,based on topological analysis and functional annotation,the neurotransmission module was identified as the"therapeutic module"of MS.Further,perturbation scores of drugs on the module were calculated by constructing the DTN and introducing the PRS analysis,giving a list of repurposable drugs for MS.Mechanism of action analysis both at pathway and structural levels screened dihydroergocristine as a candidate drug of MS by targeting a serotonin receptor of se-rotonin 2B receptor(HTR2B).Finally,we established a cuprizone-induced chronic mouse model to evaluate the alteration of HTR2B in mouse brain regions and observed that HTR2B was significantly reduced in the cuprizone-induced mouse cortex.These findings proved that the network perturbation modeling is a promising avenue for drug repurposing of MS.As a useful systematic method,our approach can also be used to discover the new molecular mechanism and provide effective candidate drugs for other complex diseases.

PURPOSE: To investigate the incidence and influencing factors of bone loss in patients with spinal cord injury (SCI). METHODS: A retrospective case-control study was conducted. Patients with SCI in our hospital from January 2019 to March 2023 were collected. According to the correlation between bone mineral density (BMD) at different sites, the patients were divided into the lumbar spine group and the hip joint group. According to the BMD value, the patients were divided into the normal bone mass group (t > -1.0 standard deviation) and the osteopenia group (t ≤ -1.0 standard deviation). The influencing factors accumulated as follows: gender, age, height, weight, cause of injury, injury segment, injury degree, time after injury, start time of rehabilitation, motor score, sensory score, spasticity, serum value of alkaline phosphatase, calcium, and phosphorus. The trend chart was drawn and the influencing factors were analyzed. SPSS 26.0 was used for statistical analysis. Correlation analysis was used to test the correlation between the BMD values of the lumbar spine and bilateral hips. Binary logistic regression analysis was used to explore the influencing factors of osteoporosis after SCI. p < 0.05 was considered statistically significant. RESULTS: The incidence of bone loss in patients with SCI was 66.3%. There was a low concordance between bone loss in the lumbar spine and the hip, and the hip was particularly susceptible to bone loss after SCI, with an upward trend in incidence (36% - 82%). In this study, patients with SCI were divided into the lumbar spine group (n = 100) and the hip group (n = 185) according to the BMD values of different sites. Then, the lumbar spine group was divided into the normal bone mass group (n = 53) and the osteopenia group (n = 47); the hip joint group was divided into the normal bone mass group (n = 83) and the osteopenia group (n = 102). Of these, lumbar bone loss after SCI is correlated with gender and weight (p = 0.032 and < 0.001, respectively), and hip bone loss is correlated with gender, height, weight, and time since injury (p < 0.001, p = 0.015, 0.009, and 0.012, respectively). CONCLUSIONS The incidence of bone loss after SCI was high, especially in the hip. The incidence and influencing factors of bone loss in the lumbar spine and hip were different. Patients with SCI who are male, low height, lightweight, and long time after injury were more likely to have bone loss.
Humans ; Spinal Cord Injuries/complications* ; Male ; Female ; Retrospective Studies ; Incidence ; Adult ; Bone Density ; Middle Aged ; Case-Control Studies ; Osteoporosis/etiology* ; Lumbar Vertebrae ; Bone Diseases, Metabolic/etiology* ; Aged ; Risk Factors

BACKGROUND: The association between uric acid-albumin ratio (UAR) with different diseases has been evaluated before. However, the association between UAR with spontaneous reperfusion (SR) in patients with ST-segment elevation myocardial infarction (STEMI) has not been explored. METHODS: STEMI patients admitted to our department and underwent primary coronary angiography between 1^st November 2018 and 31^st December 2020 were retrospectively enrolled. The patients were divided into the SR group and the non-SR group according to the index coronary angiography results. The association between UAR and SR was evaluated by uni-variable and multi-variable logistic analysis. Receiver operating characteristic curve analysis was used to determine the optimum cut-off level of UAR in predicting SR. RESULTS: Three hundred and fifty-seven patients were finally enrolled in our study, 55 patients were divided into the SR group and 302 patients were divided into the non-SR group. In uni-variable analysis, patients with SR were older (P = 0.032), with higher red blood cell distribution width (P < 0.001) and red blood cell distribution width-to-platelet ratio (P < 0.001), higher level of C-reactive protein (P = 0.046), higher level of uric acid (P < 0.001) compared with patients without SR. Patients with SR had a lower level of platelets (P = 0.008), lower level of on-admission B-type natriuretic peptide (P < 0.001). As for the level of UAR, STEMI patients with SR had significantly higher levels of UAR compared with STEMI patients without SR [11.1 (8.9-13.4) vs. 8.3 (6.6-10.0), P < 0.001]. Further multi-variable logistic analysis reveals that UAR was the independent risk factor of SR in different models after adjusting different variables. Receiver operating characteristic analysis showed that UAR had good predictive value in SR (AUC = 0.75, 95% CI: 0.702-0.794, P < 0.01). CONCLUSIONS Our study shows that UAR is an independent risk factor for predicting SR in STEMI patients.

BACKGROUND: Atrial fibrillation (AF) is a common cardiac arrhythmia in the elderly. This study aimed to evaluate urban-rural disparities in its prevalence and management in elderly Chinese. METHODS: Consecutive participants aged ≥ 65 years attending outpatient clinics were enrolled for AF screening using handheld single-lead electrocardiogram (ECG) from April 2017 to December 2022. Each ECG rhythm strip was reviewed from the research team. AF or uninterpretable single-lead ECGs were referred for 12-lead ECG. Primary study outcome comparison was between rural and urban areas for the prevalence of AF. The Student's t-test was used to compare mean values of clinical characteristics between rural and urban participants, while the Pearson's chi-square test was used to compare between-group proportions. Multivariate stepwise logistic regression analysis was performed to estimate the association between AF and various patient characteristics. RESULTS: The 29,166 study participants included 13,253 men (45.4%) and had a mean age of 72.2 years. The 7073 rural participants differed significantly (P ≤ 0.02) from the 22,093 urban participants in several major characteristics, such as older age, greater body mass index, and so on. The overall prevalence of AF was 4.6% (n = 1347). AF was more prevalent in 7073 rural participants than 22,093 urban participants (5.6% vs. 4.3%, P < 0.01), before and after adjustment for age, body mass index, blood pressure, pulse rate, cigarette smoking, alcohol consumption and prior medical history. Multivariate logistic regression analysis identified overweight/obesity (OR = 1.35, 95% CI: 1.17-1.54) in urban areas and cigarette smoking (OR = 1.62, 95% CI: 1.20-2.17) and alcohol consumption (OR = 1.42, 95% CI: 1.04-1.93) in rural areas as specific risk factors for prevalent AF. In patients with known AF in urban areas (n = 781) and rural areas (n = 338), 60.6% and 45.9%, respectively, received AF treatment (P < 0.01), and only 22.4% and 17.2%, respectively, received anticoagulation therapy (P = 0.05). CONCLUSIONS In China, there are urban-rural disparities in AF in the elderly, with a higher prevalence and worse management in rural areas than urban areas. Our study findings provide insight for health policymakers to consider urban-rural disparity in the prevention and treatment of AF.

BACKGROUND: Quantitative flow ratio (QFR) holds significant value in guiding drug-coated balloon (DCB) treatment and enhancing outcomes. However, the predictive capability of post-angioplasty QFR for long-term clinical events in patients with de novo lesions who receive DCB treatment remains uncertain. The aim of this study was to explore the potential significance of post-angioplasty QFR measurements in predicting clinical outcomes in patients underwent DCB treatment for de novo lesions. METHODS: Patients who underwent DCB-only intervention for de novo lesions were enrolled. QFR was conducted after DCB treatment. The patients were then categorized based on post-angioplasty QFR. The primary endpoint was major adverse cardiac events (MACE), encompassing all-cause death, cardiovascular death, nonfatal myocardial infarction, stroke, and target vessel revascularization. RESULTS: A total of 553 patients with 561 lesions were included. The median follow-up period was 505 days, during which 66 (11.8%) MACEs occurred. Based on post-procedural QFR grouping, there were 259 cases in the high QFR group (QFR > 0.93) and 302 cases in the low QFR group (QFR ≤ 0.93). Kaplan-Meier analysis revealed a significantly higher cumulative incidence of MACE in the low QFR group (log-rank P = 0.004). The multivariate Cox proportional hazards model demonstrated a significant inverse correlation between QFR and the occurrence of MACEs (HR = 0.522, 95%CI: 0.289-0.942, P = 0.031). Landmark analysis indicated that high QFR had a significant reducing effect on the cumulative incidence of MACEs within 1 year (log-rank P = 0.016) and 1-5 years (log-rank P = 0.026). CONCLUSIONS In patients who underwent DCB-only treatment for de novo lesions, higher post-procedural QFR values (> 0.93) were identified as an independent protective factor against adverse prognosis.

Objective To investigate the risk factors for pneumonia complicating infectious mononucleosis(IM)in adults and construct a nomogram prediction model.Methods A retrospective analysis was conducted on 198 IM patients admitted to the Second Affiliated Hospital of Air Force Medical University from January 2015 to December 2021.Patients were divided into pneumonia group(n=52)and non-pneumonia group(n=146)based on whether pulmonary infection occurred during hospitalization.The baseline data(age,gender,place of onset,etc.),clinical manifestations(maximum body temperature,lymph node enlargement,splenomegaly,etc.),and inflammatory indicators[white blood cell count(WBC),C-reactive protein(CRP),etc.]were compared between the two groups.Kaplan-Meier curves were plotted to analyze the key indicators affecting the hospital stay of IM patients.Multivariate logistic regression was used to analyze the independent risk factors for pneumonia complicating IM in adults and construct a nomogram prediction model based on the identified risk factors.The predictive efficacy of the model was evaluated using the receiver operating characteristic(ROC)curve and the consistency of the model was assessed using the calibration curve.The fit of the model was evaluated using the Hosmer-Lemeshow test.Additionally,the sensitivity,specificity,and accuracy of the model were assessed using confusion matrix.Results Compared with non-pneumonia group,the pneumonia group had a significantly higher proportion of patients from rural areas,with body mass index(BMI)≥24 kg/m2,smoking history,hepatomegaly,fever duration of≥7 d,as well as increased total hospitalization costs and average daily hospitalization costs,and prolonged hospital stay(P<0.05).The proportion of patients with a history of antibiotic use was lower in the pneumonia group(P<0.05).Kaplan-Meier survival analysis showed that patients from rural areas,with BMI≥24 kg/m2,smoking history,no prophylactic use of antibiotics,fever duration≥7 d,and hepatomegaly had significantly prolonged hospital stays(P<0.05).Multivariate logistic regression analysis revealed that living in a rural area(OR=4.089,P<0.05),hepatomegaly(OR=4.082,P<0.05),and elevated WBC(OR=1.205,P<0.05)were independent risk factors for pneumonia complicating IM in adults,while the prophylactic use of antibiotics(OR=0.142,P<0.05)was an independent protective factor.The area under the ROC curve of the constructed nomogram prediction model was 0.827(95%CI 0.762-0.892),and the slope of the calibration curve was close to 1,and the Hosmer-Lemeshow test showed χ2=5.299,P=0.725,indicating good consistency and fit of the prediction model.The results of the confusion matrix assessment showed that the sensitivity of the model was 0.669(0.624-0.773),the specificity was 0.827(0.724-0.930),and the accuracy was 0.732(0.665-0.793).Conclusion The nomogram prediction model based on place of onset,hepatomegaly,the prophylactic use of antibiotics and WBC has excellent fit and discrimination,providing an effective quantitative tool for prognosis assessment of IM.

Prostate cancer (PCa) ranks as the second most prevalent malignancy among men worldwide. Early diagnosis, personalized treatment, and prognosis prediction of PCa play a crucial role in improving patients' survival rates. The advancement of artificial intelligence (AI), particularly the utilization of deep learning (DL) algorithms, has brought about substantial progress in assisting the diagnosis, treatment, and prognosis prediction of PCa. The introduction of the foundation model has revolutionized the application of AI in medical treatment and facilitated its integration into clinical practice. This review emphasizes the clinical application of AI in PCa by discussing recent advancements from both pathological and imaging perspectives. Furthermore, it explores the current challenges faced by AI in clinical applications while also considering future developments, aiming to provide a valuable point of reference for the integration of AI and clinical applications.
Humans ; Prostatic Neoplasms/diagnosis* ; Male ; Artificial Intelligence ; Deep Learning ; Prognosis