The rapid development of artificial intelligence (AI), especially generative AI (GenAI), has already brought, and will continue to bring, revolutionary changes to our daily production and life, as well as create new opportunities and challenges for diagnostic and therapeutic practices in the medical field. Haihe Hospital of Tianjin University collaborates with the National Supercomputer Center in Tianjin, Tianjin University, and other institutions to carry out research in areas such as smart healthcare, smart services, and smart management. We have conducted research and development of a full-process disease diagnosis and treatment assistance system based on GenAI in the field of smart healthcare. The development of this project is of great significance. The first goal is to upgrade and transform the hospital's information center, organically integrate it with existing information systems, and provide the necessary computing power storage support for intelligent services within the hospital. We have implemented the localized deployment of three models: Tianhe "Tianyuan", WiNGPT, and DeepSeek. The second is to create a digital avatar of the chief physician/chief physician's voice and image by integrating multimodal intelligent interaction technology. With generative intelligence as the core, this solution provides patients with a visual medical interaction solution. The third is to achieve deep adaptation between generative intelligence and the entire process of patient medical treatment. In this project, we have developed assistant tools such as intelligent inquiry, intelligent diagnosis and recognition, intelligent treatment plan generation, and intelligent assisted medical record generation to improve the safety, quality, and efficiency of the diagnosis and treatment process. This study introduces the content of a full-process disease diagnosis and treatment assistance system, aiming to provide references and insights for the digital transformation of the healthcare industry.
Artificial Intelligence ; Humans ; Delivery of Health Care ; Generative Artificial Intelligence

Objective:To investigate the expression of programmed cell death ligand 1 (PD-L1), clinicopathologic features, immunohistochemical expression and molecular characteristics in fumarate hydratase (FH)-deficient renal cell carcinoma and to explore the potential application of immunotherapy in the patients.Methods:There were six patients with FH-deficient renal cell carcinoma treated at the First Affiliated Hospital of Fujian Medical University between January 2020 and October 2022. The clinical data, histological morphology, immunophenotype, PD-L1 expression and next-generation sequencing results were tabulated and analyzed.Results:There were 6 patients, all male, age ranged from 37 to 72 years (mean 45.7 years). Four cases were high-grade (WHO/ISUP grade3-4) with 2 or more histologic patterns, including papillary (most common), glandular, tubular, vesicular, ethmoid, nest-like, cystic and solid structures. Two cases were low-grade which showed nest-like, glandular, or tubular arrangement with eosinophilic flocculent cytoplasm and small intracellular vacuoles. Immunohistochemical analysis revealed strong expression of 2SC in all 6 cases, negative expression of FH in 5 cases, and positive expression of GATA3 in 5 cases. In high-grade cases, the mean values of CD4 and CD8 positive T-lymphocytes in advanced tumor invasion were 180.3/mm 2 and 130.5/mm 2, respectively. PD-L1 combined positive scores (CPS) were 20, 50, 5 and 30, respectively. The Ki-67 proliferative index were 20%, 20%, 10% and 30%, respectively. In low-grade cases, the mean values of CD4 and CD8 positive T-lymphocytes were 123.0/mm 2 and 100.5/mm 2, respectively. The PD-L1 CPS score was 1, and the Ki-67 proliferation index was 3%. High-throughput sequencing showed FH gene somatic mutation in 3 cases, FH gene germline mutation in 2 cases, and FH gene mutation was not detected in one case. Conclusion:FH-deficient renal cell carcinoma is more commonly high-grade than low grade. FH and 2SC are immunohistochemical markers used in the diagnosis of FH-deficient renal cell carcinoma, and GATA3 positivity is supportive of the diagnosis. The tumor infiltration of high-grade FH-deficient renal cell carcinoma shows an increase in CD4 and CD8 positive T-lymphocytes, and high expression of PD-L1; thus, anti-PD-L1 immunotherapy can be used as a treatment option.

Objective:To analyze the risk factors and pathogen distribution of ventilator-associated pneumonia (VAP) in patients with acute respiratory distress syndrome (ARDS).Methods:A retrospective analysis was conducted on the clinical data of 118 patients with ARDS who received treatment at Xi'an International Medical Center Hospital from January 2020 to January 2023. The patients were divided into two groups: the VAP group ( n = 38) and the non-VAP group ( n = 80), based on the presence of concurrent VAP. Serological indicators, blood gas analysis parameters, and ventilator settings were compared between the two groups to identify the risk factors associated with the occurrence of VAP. Pathogenic bacteria in the patients' sputum were also detected. Results:Among the 118 patients, there were 79 males and 39 females, with an average age of (53.1 ± 9.6) years. The primary underlying conditions leading to ARDS included chronic obstructive pulmonary disease in 49 cases (41.53%), sepsis in 20 cases (16.95%), severe pneumonia in 17 cases (14.41%), and extensive stroke in 16 cases (13.56%). Univariate analysis revealed that, compared with the non-VAP group, the VAP group had significantly more severe ARDS ( Z = -4.73, P < 0.05). Compared with the non-VAP group, the levels of albumin, platelets, and procalcitonin in the VAP group were significantly lower ( t = 13.75, 3.11, 2.27, all P < 0.05), while levels of high-sensitivity C-reactive protein, transforming growth factor beta (TGF-β), and angiotensin Ⅱin the VAP group were significantly higher ( t = 2.51, 26.63, 27.50, all P < 0.05). The VAP group had a significantly higher proportion of patients who experienced coma, underwent tracheostomy, and received more than two types of antibiotics (χ2 = 14.84, 19.04, 11.22, all P < 0.05). The VAP group also had significantly longer duration of antibiotic use compared with the non-VAP group ( t = 6.88, P < 0.05). Multivariate analysis showed that albumin ( OR = 2.632, 95% CI: 1.398-3.749), high-sensitivity C-reactive protein ( OR = 2.358, 95% CI: 1.534-4.036), coma ( OR = 3.035, 95% CI: 2.034-3.834), and use of more than two types of antibiotics ( OR = 2.005, 95% CI: 1.363-2.846) were independent risk factors for the occurrence of VAP in patients with ARDS (all P < 0.05). In 38 patients with VAP, 63 pathogenic strains were isolated from sputum, while in 80 patients with non-VAP, 128 pathogenic strains were isolated. The most common pathogens identified were Pseudomonas aeruginosa, Klebsiella pneumoniae, Acinetobacter baumannii, and Staphylococcus aureus. In the VAP group, a single pathogen was identified in 16 cases (42.11%), whereas in the non-VAP group, a single pathogen was identified in 51 cases (63.75%). Two types of pathogens were found in 14 cases (36.84%) of the VAP group and 25 cases (31.25%) of the non-VAP group, while three or more pathogens were detected in 8 cases (21.05%) of the VAP group and 4 cases (5.00%) of the non-VAP group. The survival rates for the VAP and non-VAP groups were 57.9% (22/38) and 85.0% (68/80), respectively, with the non-VAP group showing a significantly higher survival rate (χ2 = 22.67, P < 0.001). Conclusion:The risk of VAP in patients with ARDS is high, with two or more pathogen infections being predominant. Clinical interventions should be strengthened.

To evaluate the advantages of using PBL case library in teaching circulatory system diseases to clinical medicine undergraduate students, a PBL case library was established and applied in teaching practice in the reform of circulatory system teaching. The PBL case library achieved the characteristics of combining theories with cases, morphology with functions, and basic knowledge with clinical knowledge. The PBL case library also realized the informatization, query, and update of cases. Preliminary application showed that the median practical score of students in the case library group was 94.00 points, which was significantly higher than the 92.00 points in the control group ( P=0.005). The average lesson preparation time for teachers in the case library group was (5.00±1.00) hours, which was significantly shorter than the (6.89±0.42) hours in the control group ( P<0.001). The difficulty score for lesson preparation among teachers in the case library group was significantly lower than that of the control group [(1.89±1.05) vs. (3.22±0.44), P<0.001]. However, there were no significant difference in theoretical scores and student satisfaction with teachers and courses. These results suggest that the construction of case library can improve practical teaching effectiveness and enhance the efficiency of lesson preparation for teachers.

AIM: To observe the clinical efficacy of Fuzheng Xiaoliu Granules in the treatment of stage II primary liver cancer and to explore its mechanism of action from the perspective of metabolomics. METHODS: Sixty patients with stage II primary liver cancer who achieved complete remission (CR) after comprehensive interventional therapy were randomly divided into treatment group and placebo group, with 30 patients in each group. They were treated for one year and observed for one year. The one-year recurrence rate, traditional chinese medicine (TCM) syndrome score, alpha-fetoprotein and child-pugh grade were compared between the two groups. The serum metabolites of the two groups before and after treatment were screened by ultra-high liquid chromatography-mass spectrometry technology, and the metabolic pathways and related biological pathways were analyzed. RESULTS: The one-year recurrence rate of the treatment group was significantly lower than that of the placebo group, and the overall improvement rate of TCM syndrome score was significantly better than that of the placebo group (P<0.05). There was no statistical significance in the comparison of alpha-fetoprotein and child-pugh grade between the two groups after treatment (P>0.05). Metabolomics results showed that there were 39 and 33 different metabolites in the treatment group before and after treatment and in the two groups after treatment, respectively. After enrichment analysis and topological analysis of the different metabolites, it was found that Fuzheng Xiaoliu Granules could affect amino acid metabolism, fatty acid metabolism and purine metabolism and other metabolic pathways. Before and after treatment in the treatment group and after treatment in the two groups, there were the same differential metabolites and metabolic pathways in the two comparison results. The same differential metabolites with FOLD CHANGE>1 include Stearic acid, Hypoxanthine, Kynurenic acid, Arachidonic acid, and N-Arachidonoyl Dopamine. The same metabolic pathways with Impact>0.1 include Arachidonic acid metabolism and Histidine metabolism. CONCLUSION: Fuzheng xiaoliu granules can effectively reduce the recurrence rate of stage II liver cancer patients after comprehensive intervention and improve the TCM syndrome. It may inhibit the activation of PI3K/Akt and ERK signaling pathways by regulating the content of metabolites involved in metabolic pathways such as amino acids and fatty acids, thereby delaying tumor recurrence.

Objective    To evaluate the safety and efficacy of mitral valve surgery and cryoablation in elderly patients with mitral valve disease and persistent or long-term persistent atrial fibrillation. Methods    From May 2014 to July 2018, 144 patients with mitral valve diseases combined with persistent or long-term persistent atrial fibrillation in the Department of Cardiothoracic Surgery, General Hospital of Northern Theater Command were selected. Among them, there were 69 patients in a non-elderly group (<60 years) including 18 males and 51 females aged 52.07±5.56 years, and 75 patients in an elderly group (≥60 years) including 32 males and 43 females aged 65.23±4.29 years. A propensity-score matching (PSM) study was conducted to eliminate confounding factors. Both groups underwent mitral valve surgery and cryoablation at the same time. A 2-year follow-up was conducted after discharge from the hospital, and the perioperative and postoperative efficacy indexes were compared between the two groups. Results    After PSM analysis, there were 56 patients in each group. The sinus rhythm conversion rate of the two groups at each follow-up time point was above 85%, and the cardiac function was graded asⅠorⅡ, which was significantly improved compared with that before the surgery, but there was no statistical difference between the two groups (P>0.05). Among the perioperative indicators of the two groups, the elderly group had more coronary artery bypass graft surgeries and longer postoperative ICU stay time compared with the non-elderly group (P<0.05), and the differences in other indicators were not statistically different (P>0.05). Conclusion    The mitral valve surgery and cryoablation in elderly patients with mitral valve diseases combined with persistent or long-term persistent atrial fibrillation are safe, and the short-term outcome is satisfactory.

Purpose: Platelet-related indices, including mean platelet volume (MPV) and plateletocrit (PCT), have been reported as new prognostic factors of overall survival (OS) in many cancers, but not yet in biliary tract cancer (BTC). We intended to assess these indices in predicting OS in BTC patients with the aim to build a new prognostic model for patients with BTC after surgical resection. Materials and Methods: Survival analysis and time receiver operating characteristic analysis were applied to screen the platelet indices. Univariate and multivariate Cox analyses were used to identify independent prognostic factors and develop a new prognostic model. Harrell’s C-statistics, calibration curves, and decisive curve analysis were used to assess the model. Results: MPV and platelet distribution width (PDW)/PCT showed the best prognostic accuracy among the platelet indices. In multivariable analysis, factors predictive of poor OS were presence of nodal involvement, Non-radical surgery, poor tumor differentiation, carbohydrate antigen 19-9 > 100 U/mL, MPV > 8.1 fl, and PDW/PCT > 190. The new model was found to be superior to the TNM staging system and our new staging system showed higher discriminative power. Conclusion MPV and PDW/PCT have high prognostic value in BTC patients, and the novel staging system based on these two indices showed good discrimination and accuracy compared with the American Joint Committee on Cancer 7th TNM staging system.

Purpose: Platelet-related indices, including mean platelet volume (MPV) and plateletocrit (PCT), have been reported as new prognostic factors of overall survival (OS) in many cancers, but not yet in biliary tract cancer (BTC). We intended to assess these indices in predicting OS in BTC patients with the aim to build a new prognostic model for patients with BTC after surgical resection. Materials and Methods: Survival analysis and time receiver operating characteristic analysis were applied to screen the platelet indices. Univariate and multivariate Cox analyses were used to identify independent prognostic factors and develop a new prognostic model. Harrell’s C-statistics, calibration curves, and decisive curve analysis were used to assess the model. Results: MPV and platelet distribution width (PDW)/PCT showed the best prognostic accuracy among the platelet indices. In multivariable analysis, factors predictive of poor OS were presence of nodal involvement, Non-radical surgery, poor tumor differentiation, carbohydrate antigen 19-9 > 100 U/mL, MPV > 8.1 fl, and PDW/PCT > 190. The new model was found to be superior to the TNM staging system and our new staging system showed higher discriminative power. Conclusion MPV and PDW/PCT have high prognostic value in BTC patients, and the novel staging system based on these two indices showed good discrimination and accuracy compared with the American Joint Committee on Cancer 7th TNM staging system.

Objective To investigate the distribution characteristics of ABA (Acinetobacter baumannii) and to analyze the influencing factors of the prognosis of elderly patients with COPD (chronic obstructive pulmonary disease) and lung infection in Shaanxi. Methods A retrospective single-center survey was conducted on 1 078 elderly patients with COPD admitted to our hospital from January 2015 to November 2019. According to the presence or absence of ABA infection, the patients were divided into infection group (n=63) and non-infection group (n=1 015). Through the electronic medical record system, the basic information of all patients was collected, including name, sex, age, case number, length of stay in ICU, index of auxiliary examination, combined diseases and prognosis. The prognostic outcomes of the two groups of patients were compared. Univariate analysis was performed on the baseline data of the two groups of the patients, and unconditional logistic multivariate regression analysis was used to further analyze the single factors with statistical difference, to explore the distribution and influencing factors of ABA in elderly COPD patients with pulmonary infection in Shaanxi. Results The mortality rate of the infected group was significantly higher than that of the non-infected group (χ²=8.670, P=0.003). Univariate analysis showed that there were significant differences in age, Apache II score, diabetes, PCT and ICU length of stay between the infected and non-infected groups (P<0.05), while there were no significant differences in sex, cerebrovascular disease, malnutrition, bed rest and tumor (P<0.05). In the infection group, 55 patients survived, 42 patients were discharged, 13 patients received extended hospitalization and 8 patients died. Of those who died, 5 were resistant to cefoperazone and all were resistant to carbapenems. Of those remaining hospitalized, 3 patients were resistant to cefoperazone sulbactam and 7 were resistant to carbapenems. Patients discharged from the hospital were more sensitive to carbapenems, minocycline and cefoperazone. According to multiple logistic regression analysis, apache II score (OR=3.480，95%CI 1.154-10.491), diabetes mellitus (OR=2.732，95%CI 1.297-5.753), high serum PCT (OR=6.334，95%CI 1.142-35.129) and ICU hospitalization (OR=3.773，95%CI 1.087-13.100) were independent risk factors influencing the prognosis of elderly patients with COPD in Shaanxi. Conclusion ABA Infection was correlated with age, Apache II score, diabetes Mellitus, PCT and length of stay in ICU, which could influence prognosis of elderly patients with COPD.

Purpose: The systemic inflammation response index (SIRI) has been reported to have prognostic ability in various solid tumors but has not been studied in gallbladder cancer (GBC). We aimed to determine its prognostic value in GBC. Materials and Methods: From 2003 to 2017, patients with confirmed GBC were recruited. To determine the SIRI’s optimal cutoff value, a time-dependent receiver operating characteristic curve was applied. Univariate and multivariate Cox analyses were performed for the recognition of significant factors. Then the cohort was randomly divided into the training and the validation set. A nomogram was constructed using the SIRI and other selected indicators in the training set, and compared with the TNM staging system. C-index, calibration plots, and decision curve analysis were performed to assess the nomogram’s clinical utility. Results: One hundred twenty-four patients were included. The SIRI’s optimal cutoff value divided patients into high (≥ 0.89) and low SIRI (< 0.89) groups. Kaplan-Meier curves according to SIRI levels were significantly different (p < 0.001). The high SIRI group tended to stay longer in hospital and lost more blood during surgery. SIRI, body mass index, weight loss, carbohydrate antigen 19-9, radical surgery, and TNM stage were combined to generate a nomogram (C-index, 0.821 in the training cohort, 0.828 in the validation cohort) that was significantly superior to the TNM staging system both in the training (C-index, 0.655) and validation cohort (C-index, 0.649). Conclusion The SIRI is an independent predictor of prognosis in GBC. A nomogram based on the SIRI may help physicians to precisely stratify patients and implement individualized treatment.