Objective To construct large medical model named by "Huaxi HongYi"and explore its application effectiveness in assisting medical record generation. Methods By the way of a full-chain medical large model construction paradigm of "data annotation - model training - scenario incubation", through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, "Huaxi HongYi" with 72 billion parameters was constructed. Combined with technologies such as speech recognition, knowledge graphs, and reinforcement learning, an application system for assisting in the generation of medical records was developed. Results Taking the assisted generation of discharge records as an example, in the pilot department, after using the application system, the average completion times of writing a medical records shortened (21 min vs. 5 min) with efficiency increased by 3.2 time, the accuracy rate of the model output reached 92.4%. Conclusion It is feasible for medical institutions to build independently controllable medical large models and incubate various applications based on these models, providing a reference pathway for artificial intelligence development in similar institutions.

OBJECTIVE: To explore, identify, and develop novel blood-based indicators using machine learning algorithms for accurate preoperative assessment and effective prediction of postoperative complication risks in patients with rheumatoid arthritis (RA) undergoing total knee arthroplasty (TKA). METHODS: A retrospective cohort study was conducted including RA patients who underwent unilateral TKA between January 2019 and December 2024. Inpatient and 30-day postoperative outpatient follow-up data were collected. Six machine learning algorithms, including decision tree, random forest, logistic regression, support vector machine, extreme gradient boosting, and light gradient boosting machine, were used to construct predictive models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall. SHapley Additive exPlanations (SHAP) values were employed to interpret and rank the importance of individual variables. RESULTS: According to the inclusion criteria, a total of 1 548 patients were enrolled. Ultimately, 18 preoperative indicators were identified as effective predictive features, and 8 postoperative complications were defined as prediction labels for inclusion in the study. Within 30 days after surgery, 453 patients (29.2%) developed one or more complications. Considering overall accuracy, precision, recall, and F1-score, the random forest model [AUC=0.930, 95% CI (0.910, 0.950)] and the extreme gradient boosting model [AUC=0.909, 95% CI (0.880, 0.938)] demonstrated the best predictive performance. SHAP analysis revealed that anti-cyclic citrullinated peptide antibody, C-reactive protein, rheumatoid factor, interleukin-6, body mass index, age, and smoking status made significant contributions to the overall prediction of postoperative complications. CONCLUSION Machine learning-based models enable accurate prediction of postoperative complication risks among RA patients undergoing TKA. Inflammatory and immune-related blood biomarkers, such as anti-cyclic citrullinated peptide antibody, C-reactive protein, and rheumatoid factor, interleukin-6, play key predictive roles, highlighting their potential value in perioperative risk stratification and individualized management.
Humans ; Arthroplasty, Replacement, Knee/adverse effects* ; Arthritis, Rheumatoid/blood* ; Machine Learning ; Postoperative Complications/blood* ; Female ; Male ; Retrospective Studies ; Middle Aged ; Aged ; Risk Factors ; Preoperative Period ; C-Reactive Protein/analysis* ; Risk Assessment

Objective To evaluate the clinical efficacy of Shenshi Jiangzhuo Formula(composed of Poria,Atractylodis Rhizoma,Magnoliae Officinalis Cortex,Pinelliae Rhizoma Praeparatum,Aurantii Fructus Immaturus,Arecae Semen,Talcum,Tetrapanacis Medulla,Notoginseng Radix et Rhizoma,Paeoniae Radix Rubra,Rubiae Radix et Rhizoma,Broussonetiae Fructus,etc.)in treating non-alcoholic fatty liver disease(NAFLD)with phlegm blended with stasis syndrome.Methods A total of 76 NAFLD patients with phlegm blended with stasis syndrome from the Seventh School of Clinical Medicine,Guangzhou University of Chinese Medicine(Shenzhen Bao'an Traditional Chinese Medicine Hospital)were enrolled between February 2024 and December 2024.The patients were randomly assigned(via random number table)to either the trial group(n=38,treated with Silibinin Meglumine Tablets plus Shenshi Jiangzhuo Formula)or the control group(n=38,treated with Silibinin Meglumine Tablets alone)for 8 weeks.The changes in liver controlled attenuation parameter(CAP),liver function markers[alanine aminotransferase(ALT),aspartate aminotransferase(AST),gamma-glutamyl transferase(GGT)],lipid profiles[triglycerides(TG),total cholesterol(TC),low-density lipoprotein cholesterol(LDL-C)],and traditional Chinese medicine(TCM)syndrome scores were observed before and after treatment.Clinical efficacy and safety were evaluated.Results(1)One case dropped out from each group during the study and 37 cases in each group were included for final statistics.(2)After 8 weeks of treatment,the overall response rate in the trial group was 94.59％(35/37),compared with 62.16％(23/37)in the control group.Intergroup comparison revealed that the trial group demonstrated significantly superior overall therapeutic efficacy(by rank-sum test)and overall response rate(by chi-square test)compared with the control group(P＜0.01).(3)Both groups showed improved CAP values after treatment,and the trial group demonstrated significantly greater improvement compared to the control group(P＜0.01).(4)Post-treatment improvements in alanine aminotransferase(ALT),aspartate aminotransferase(AST),and gamma-glutamyl transferase(GGT)were improved in both groups(P＜0.01),with the trial group showing significantly superior improvements(P＜0.05 or P＜0.01).(5)Triglycerides(TG),total cholesterol(TC),and low-density lipoprotein cholesterol(LDL-C)were improved in both groups after treatment,and the trial group exhibited significantly better outcomes(P＜0.01).(6)Both groups presented reduced TCM syndrome scores after treatment,and the trial group showed greater reduction(P＜0.01).(7)No significant adverse recations were observed in both groups,showing high safety.Conclusion Integrative therapy with Shenshi Jiangzhuo Formula exerts certain effects in improving CAP values,liver function,lipid metabolism,and TCM symptoms in NAFLD patients with phlegm blended with stasis syndrome,demonstrating robust clinical value.

AIM:This study aim to investigate the effects of lipopolysaccharide(LPS)-induced inflammation on the aging phenotype of hematopoietic stem/progenitor cells(HSPCs)in the bone marrow(BM)and spleen of mice.METHODS:(1)Young(2-month old)wild-type(WT)mice were treated with LPS to establish an actue inflammation model.The percentage of HSPCs in the BM and spleen of mice after LPS stimulation,as well as the ratio of mature cells in peripheral blood(PB)and spleen,were analyzed using flow cytometry.The proliferation of HSPCs in the BM and spleen was evaluated by examining the expression of the proliferation marker Ki67.In addition,changes in CD45 expression on HSPCs in the spleen of mice following LPS exposure were investigated by flow cytometry.(2)The percentage of HSPCs in BM and mature cells in PB and spleen of both young(2-month old)and old(24-month old)WT mice were analyzed by flow cytometry.(3)The transcriptome changes of hematopoietic stem cells(HSCs)after LPS stimulation was performed by an in silico analysis.RESULTS:(1)Mice exposed to LPS exhibited a significant increase in the percentage of HSPCs in BM and a marked elevation in the percentages of myeloid cells in PB and spleen compared to the mice in control group(P<0.05).(2)LPS exposure resulted in increased spleen weight and cell counts(P<0.05),along with a higher per-centage of HSPCs in the spleen compared to controls(P<0.05).(3)LPS stimulation promoted the proliferation of HSPCs in the BM and spleen(P<0.05).(4)The expression of CD45 was reduced on HSPCs from spleen of mice after LPS stimu-lation(P<0.01).(5)In comparison to young mice,aged mice showed an increase in spleen weight and a higher percent-age of HSPCs in the spleen(P<0.05).(6)Aged mice,in comparison to young mice,demonstrated a significantly higher percentage of HSPCs in the BM and myeloid skewing in the PB and spleen(P<0.01).(7)The silico analysis revealed up-regualtion of reactive oxygen species(ROS)and apoptosis signaling in HSPCs following LPS stimulation.CONCLU-SION:Young HSPCs stimulated by LPS exhibited an increase in cell number,a bias towards myeloid differentiation,en-hanced extramedullary hematopoiesis,and elevated levels of ROS and apoptosis,all of which collectively manifested the aging phenotype of HSPCs.

Objective:To develop and validate a predictive model of 28-day mortality in sepsis based on lactate dehydrogenase-to-albumin ratio (LAR).Methods:Sepsis patients diagnosed in the department of intensive care medicine of the First Affiliated Hospital of Soochow University from August 1, 2017 to September 1, 2022 were retrospective selected. Clinical data, laboratory indicators, disease severity scores [acute physiology and chronic health evaluation Ⅱ(APACHEⅡ), sequential organ failure assessment (SOFA)] were collected. Patients were divided into death group and survival group according to whether they died at 28 days, and the difference between the two groups was compared. The dataset was randomly divided into training set and validation set according to 7∶3. Lasso regression method was used to screen the risk factors affecting the 28-day death of sepsis patients, and incorporating multivariate Logistic regression analysis (stepwise regression) were included, a prediction model was constructed based on the independent risk factors obtained, and a nomogram was drawn. The nomogram prediction model was established. Receiver operator characteristic curve (ROC curve) was drawn to analyze and evaluate the predictive efficacy of the model. Hosmer-Lemeshow test, calibration curve and decision curve analysis (DCA) were used to evaluate the accuracy and clinical practicability of the model, respectively.Results:A total of 394 patients with sepsis were included, with 248 survivors and 146 non-survivors at 28 days. Compared with the survival group, the age, proportion of chronic obstructive pneumonia, respiratory rate, lactic acid, red blood cell distribution width, prothrombin time, activated partial thromboplastin time, alanine aminotransferase, aspartate aminotransferase, blood urea nitrogen, creatinine, blood potassium, blood phosphorus, LAR, SOFA score, and APACHEⅡ score in the death group were significantly increased, while oxygenation index, monocyte count, platelet count, fibrinogen, total cholesterol, triglycerides, high-density lipoprotein, low-density lipoprotein, and blood calcium were significantly reduced. In the training set, LAR, age, oxygenation index, blood urea nitrogen, lactic acid, total cholesterol, fibrinogen, blood potassium and blood phosphorus were screened by Lasso regression. Multivariate Logistic regression analysis finally included LAR [odds ratio ( OR) = 1.029, 95% confidence interval (95% CI) was 1.014-1.047, P < 0.001], age ( OR = 1.023, 95% CI was 1.005-1.043, P = 0.012), lactic acid ( OR = 1.089, 95% CI was 1.003-1.186, P = 0.043), oxygenation index ( OR = 0.996, 95% CI was 0.993-0.998, P = 0.002), total cholesterol ( OR = 0.662, 95% CI was 0.496-0.865, P = 0.003) and blood potassium ( OR = 1.852, 95% CI was 1.169-2.996, P = 0.010). A total of 6 predictor variables were used to establish a prediction model. ROC curve showed that the area under the curve (AUC) of the model in the training set and validation set were 0.773 (95% CI was 0.715-0.831) and 0.793 (95% CI was 0.703-0.884), which was better than APACHEⅡ score (AUC were 0.699 and 0.745) and SOFA score (AUC were 0.644 and 0.650), and the cut-off values were 0.421 and 0.309, the sensitivity were 62.4% and 82.2%, and the specificity were 82.2% and 68.9%, respectively. The results of Hosmer-Lemeshow test and calibration curve showed that the predicted results of the model were in good agreement with the actual clinical observation results, and the DCA showed that the model had good clinical application value. Conclusion:The prediction model based on LAR has a good predictive value for 28-day mortality in patients with sepsis and can guide clinical decision-making.

Objective:To investigate the clinical value of endoscopic ultrasound elastography versus contrast-enhanced computed tomography in the risk stratification of gastrointestinal stromal tumors (GISTs). Methods:Clinical and imaging data were obtained from 77 patients who were confirmed to have GISTs and underwent endoscopic or surgical treatment at Wenzhou Central Hospital between May 2019 and April 2021. Endoscopic ultrasound elastography based on a five-point scoring system and hypotonic gastrointestinal contrast-enhanced computed tomography were performed for preoperative risk stratification of GISTs. The two techniques were compared in terms of the accuracy of preoperative risk stratification of GISTs. The imaging features of the two techniques were summarized.Results:According to the postoperative pathological results, 13 patients were at high risk, 13 patients were at medium risk, 35 patients were at low risk, and 16 patients were at extremely low risk. These patients were divided into two groups according to postoperative pathological results: a low-risk group (low risk + extremely low risk) and a medium- and high-risk group (high + medium risk). In the low-risk group ( n = 51), 42 patients were identified by endoscopic ultrasound elastography to have low-risk GISTs and were recommended to receive endoscopic treatment, while the rest 9 patients were identified to have medium-risk GISTs. Contrast-enhanced computed tomography findings revealed that 30 patients had low-risk GISTs and were recommended to receive endoscopic treatment, and 21 patients had medium-risk GISTs. In the medium- and high-risk group ( n = 26), 4 patients were identified by endoscopic ultrasound elastography to have low-risk GISTs, and 22 patients had medium- or high-risk GISTs. Contrast-enhanced computed tomography findings revealed that 9 patients were identified to have low-risk GISTs, and 17 patients had medium- or high-risk GISTs. Endoscopic ultrasound elastography yielded an overall diagnostic accuracy of 83.11% (64/77), while contrast-enhanced computed tomography had an overall diagnostic accuracy of 61.04% (47/77). Endoscopic ultrasound elastography outperformed contrast-enhanced computed tomography in accurate risk stratification of GISTs ( χ2 = 4.66, P < 0.05). In terms of predicting high-risk GISTs, endoscopic ultrasound elastography had a sensitivity of 84.62% and a specificity of 82.35%, both were higher than those of contrast-enhanced computed tomography (sensitivity: 65.38%; specificity: 58.82%), but the differences in sensitivity and specificity between the two techniques were not significant (sensitivity: Fisher's exact test P = 0.590, specificity: χ2 = 0.93, P > 0.05). Conclusion:Endoscopic ultrasound elastography appears to have a better overall diagnostic accuracy in the risk stratification of GISTs compared with contrast-enhanced computed tomography. The combined use of these two techniques may offer a better comprehensive understanding of the perilesional structure and organ involvements and distant metastasis than a single technique, thereby providing a reliable reference for the choice of treatment for GISTs.

Sodium-glucose cotransporter 2 (SGLT2) inhibitors have been reapproved for heart failure (HF) therapy in patients with and without diabetes. However, the initial glucose-lowering indication of SGLT2i has impeded their uses in cardiovascular clinical practice. A challenge of SGLT2i then becomes how to separate their anti-HF activity from glucose-lowering side-effect. To address this issue, we conducted structural repurposing of EMPA, a representative SGLT2 inhibitor, to strengthen anti-HF activity and reduce the SGLT2-inhibitory activity according to structural basis of inhibition of SGLT2. Compared to EMPA, the optimal derivative JX01, which was produced by methylation of C2-OH of the glucose ring, exhibited weaker SGLT2-inhibitory activity (IC₅₀ > 100 nmol/L), and lower glycosuria and glucose-lowering side-effect, better NHE1-inhibitory activity and cardioprotective effect in HF mice. Furthermore, JX01 showed good safety profiles in respect of single-dose/repeat-dose toxicity and hERG activity, and good pharmacokinetic properties in both mouse and rat species. Collectively, the present study provided a paradigm of drug repurposing to discover novel anti-HF drugs, and indirectly demonstrated that SGLT2-independent molecular mechanisms play an important role in cardioprotective effects of SGLT2 inhibitors.

Objective:To investigate the efficacy of Modified Banxia Xiexin Decoction on patients with functional dyspepsia (FD) and its impact on gastric function.Methods:From June 2021 to December 2022, at the Department of Gastroenterology, Wenzhou Central Hospital, a total of 56 patients with FD who met the diagnostic criteria of Rome Ⅳ were prospectively enrolled. The patients were treated with Modified Banxia Xiexin Decoction for 4 weeks. The clinical efficacy was evaluated by the upper gastrointestinal symptom severity index score. The gastric function was assessed by standard gastric loading test of liquid nutrient meal and standard gastric emptying test of solid meal. The total scores of dyspeptic symptoms, the maximal satiety threshold of proximal stomach, the initial satiety threshold of proximal stomach and 5-hour solid gastric emptying rate were compared before and after the treatment. During the treatment and in 4-week follow-up after treatment, the adverse events (such as nausea, diarrhea, dizziness and rash) were observed. Wilcoxon rank sum test and paired sample t-test were used for statistical analysis. Results:After the treatment, 14 FD patients were cured, 22 patients showed significant improvement, 12 patients had response, and 8 patients showed no improvement. The total efficacy rate was 85.71%(48/56). The total score of dyspepsia symptoms after the treatment was lower than that before treatment (3.00(1.00, 4.00) vs. 13.00(8.00, 18.00)), and the difference was statistically significant ( Z=-7.96, P<0.001). After the treatment, the maximal satiety threshold of proximal stomach and 5-hour solid gastric emptying rate were both higher than those before treatment ( (897.45±98.82) mL vs. (588.46±60.26) mL, (87.59±12.74)% vs. (36.59±15.95)%), and the differences were statistically significant ( t=19.98 and 18.70, both P<0.001). The initial satiety threshold of proximal stomach before and after treatment was compared((131.84±52.91) mL vs. (130.0±47.61) mL), and the difference was not statistically significant( P>0.05). No adverse events related to this study were observed during treatment period and in the 4-week follow-up. Conclusions:The Modified Banxia Xiexin Decoction can improve proximal gastric compliance and gastric emptying function in patients with FD. Additionally, it can alleviate dyspeptic symptoms and have good clinical efficacy and high safety.

Objective:To investigate the risk of occupational hearing loss caused by noise exposure in an automobile parts manufacturing enterprise.Methods:In June 2019, an automobile parts manufacturing enterprise in Huizhou City was selected to conduct occupational hygiene field investigation, and occupational health investigation and occupational hazards detection were carried out in the workplace. 395 workers with 8-hour working day equivalent sound level (L ex·8 h) ≥85 dB (a) were selected as the research objects. The occupational noise exposure risk assessment method was used to assess the noise exposure risk of L ex·8 h≥85 dB (a) , and the risk of high-frequency hearing loss and occupational noise deafness caused by noise exposure were evaluated when the working years were 10, 20, 30, 35 and 40. Results:When the exposure years were less than or equal to 30 years, the risk of high-frequency hearing loss of bearing pedestal final examiners was medium risk, and the risk of other positions was acceptable; the highest risk of noise deafness was the bearing pedestal final examiner, and the risk classification was higher, and the other types of work were negligible risk and acceptable risk. When the exposure years are more than 30 years, the risk classification of high-frequency hearing loss of bearing pedestal final inspection workers is high-risk, and the risk classification of other types of work is medium risk; the highest risk of noise deafness is the bearing pedestal final inspection workers, and the risk classification is higher risk, and the other types of work are medium risk.Conclusion:The enterprise should pay attention to the risk of occupational hearing loss caused by noise exposure, especially the bearing pedestal final inspection workers, and strengthen the hearing protection of noise exposed people.

Objective:To investigate the risk of occupational hearing loss caused by noise exposure in an automobile parts manufacturing enterprise.Methods:In June 2019, an automobile parts manufacturing enterprise in Huizhou City was selected to conduct occupational hygiene field investigation, and occupational health investigation and occupational hazards detection were carried out in the workplace. 395 workers with 8-hour working day equivalent sound level (L ex·8 h) ≥85 dB (a) were selected as the research objects. The occupational noise exposure risk assessment method was used to assess the noise exposure risk of L ex·8 h≥85 dB (a) , and the risk of high-frequency hearing loss and occupational noise deafness caused by noise exposure were evaluated when the working years were 10, 20, 30, 35 and 40. Results:When the exposure years were less than or equal to 30 years, the risk of high-frequency hearing loss of bearing pedestal final examiners was medium risk, and the risk of other positions was acceptable; the highest risk of noise deafness was the bearing pedestal final examiner, and the risk classification was higher, and the other types of work were negligible risk and acceptable risk. When the exposure years are more than 30 years, the risk classification of high-frequency hearing loss of bearing pedestal final inspection workers is high-risk, and the risk classification of other types of work is medium risk; the highest risk of noise deafness is the bearing pedestal final inspection workers, and the risk classification is higher risk, and the other types of work are medium risk.Conclusion:The enterprise should pay attention to the risk of occupational hearing loss caused by noise exposure, especially the bearing pedestal final inspection workers, and strengthen the hearing protection of noise exposed people.