Objective To explore an artificial intelligence (AI)-based method for automated hand hygiene monitoring and to compare the effectiveness of three algorithms (UniFormerV2, TDN, C3D) in recognizing hand hygiene steps in surgical settings, thereby aiding hospital infection control. Methods From April to October 2024, we non-invasively collected 641 video recordings of healthcare staff performing hand hygiene at four-bay scrub sinks in two tertiary hospitals using overhead HD cameras. The dataset was annotated by five trained experts for model training and validation. Results Following training on 385 samples, internal validation (n=119) showed the C3D model achieved 81% accuracy, 87% recall, and an 83% F1-score. The TDN model achieved 93%, 91%, and 92% for the same metrics. The UniFormerV2 model outperformed both, with an accuracy, recall, and F1-score of 93%—an improvement of over 10 percentage points compared to traditional CNNs (TDN, C3D). It also achieved an 84% accuracy in external validation, demonstrating strong generalization. Conclusion The UniFormerV2 model is more accurate than CNN-based models for hand hygiene step recognition and shows robust performance in external validation. It presents a viable tool for healthcare facilities to enhance hand hygiene management, ultimately improving medical quality and patient safety.

OBJECTIVE To explore the transformation of the dispensing and drug pickup process in traditional Chinese medicine pharmacy （TCM Pharmacy） in our hospital based on data-intelligence-driven， aiming to improve pharmacists’ work efficiency and patients’ drug pickup experience. METHODS Value stream mapping and journey mapping were used to systematically identify non-value-added links in pharmacists’ dispensing process and key pain points in patients’ drug pickup under the traditional process. An intelligent dispensing and drug pickup system for the TCM Pharmacy was developed based on the C# and Android television platforms， and a machine-learning model was adopted to predict patients’ drug pickup waiting time. A comprehensive evaluation was performed from three perspectives： system performance， prediction accuracy， and satisfaction of pharmacists and patients. RESULTS The system successfully streamlined non-value-added links such as “waiting for writing on the board” and “searching for drugs”， and realized multimodal dynamic prompts of dispensing status through auditory （number calling） and visual （television terminal） channels. The constructed model for predicting drug pickup waiting time exhibited good fitting degree and generalization ability （mean absolute error＝4.28 min， R 2 ＝0.882）. The comprehensive satisfaction scores of pharmacists and patients in the traditional mode were significantly increased from （70.99±1.74） and （73.58±1.98） to （90.02±1.30） and （88.61±2.08） in the new system， respectively （ P ＜0.01）. CONCLUSIONS The transformation of the intelligent drug dispensing and pickup system for TCM pharmacy based on data-intelligence-driven effectively improves the efficiency of pharmacists’ dispensing work， realizes process transparency and waiting time predictability， and significantly enhances patients’ drug pickup experience.

By consulting ancient and modern literature， this article systematically reviews and verifies the historical evolution of the herbal medicine known as Baijiang across various dimensions， including name， origin， scientific name verification， medicinal parts， production area， quality， harvesting and processing， as well as its nature， taste， and therapeutic effects， in order to provide a reference for the development and utilization of famous classical formulas containing Patriniae Herba. Patriniae Herba has a long history of use. It derives its name from the distinctive musty odor of its roots， which resembles spoiled soy sauce. However， due to its alias Kucai， there has been much confusion with other plants. Since the Ming dynasty， various plants have been used interchangeably as Baijiang. Herbal textual research showed that Patriniae Herba was first recorded in Shennong Bencaojing， and throughout history， Baijiang has been recognized as its standard name， though it has also been known by alternative names such as Luchang， Lujiang， and Suanyi. The main sources used throughout the ages were Patrinia scabiosaefolia or P. villosa， which is consistent with the 1977 edition of the Pharmacopoeia of the People's Republic of China. However， while the roots were traditionally used medicinally， the whole plant is now more commonly used in modern practice. In addition， the whole plants of Thlaspi arvense from the Cruciferae family and Sonchus brachyotus from the Compositae family are commonly used as regional substitutes for Baijiang. According to ancient records， Patriniae Herba was primarily found in Jiangxia（present-day eastern Hubei province） and Jiangdong（the region south of the lower reaches of the Yangtze River）， but modern literature shows that it is distributed throughout the country without a distinct geographical origin. In ancient times， the roots were harvested in August and sun-dried， today， the whole plant is typically dug up in summer or autumn and sun-dried. In recent times， the quality has been summarized as being best when the roots are long， the leaves are abundant and green， and the aroma is strong. Regarding the processing， ancient methods often involved baking（drying over fire）， while modern methods typically involve removing impurities， washing， and then cutting and drying the segments. The effects of Patriniae Herba are to clear heat and detoxify， eliminate blood stasis and drain pus. During the Han and Northern and Southern dynasties， it was used to treat skin diseases caused by heat， abscesses， postpartum diseases， and rheumatism， during the Five dynasties period， its therapeutic applications expanded to include diseases of the five senses， and by the modern era， conditions such as neurasthenia and insomnia were added. Regarding its properties and taste， it was recorded as bitter and neutral during the Han dynasty. By the Tang dynasty， it was slightly cold， with a taste of acrid and bitter. During the Yuan and Ming dynasties， it was mostly slightly cold and neutral， with a bitter and salty taste. In the Qing dynasty and modern times， it was mostly bitter and neutral， and in contemporary times， it has evolved to a taste of acrid， bitter， and cool. Based on the results of this study， it is recommended that when developing and utilizing famous classical formulas containing Patriniae Herba， one should select the entire herb of the historically mainstream sources， P. scabiosaefolia or P. villosa from the Valerianaceae family， and choose the processing method according to the prescription requirements. It is recommended to use raw products without specific requirements.

By consulting ancient and modern literature， this article systematically reviews and verifies the historical evolution of the herbal medicine known as Baijiang across various dimensions， including name， origin， scientific name verification， medicinal parts， production area， quality， harvesting and processing， as well as its nature， taste， and therapeutic effects， in order to provide a reference for the development and utilization of famous classical formulas containing Patriniae Herba. Patriniae Herba has a long history of use. It derives its name from the distinctive musty odor of its roots， which resembles spoiled soy sauce. However， due to its alias Kucai， there has been much confusion with other plants. Since the Ming dynasty， various plants have been used interchangeably as Baijiang. Herbal textual research showed that Patriniae Herba was first recorded in Shennong Bencaojing， and throughout history， Baijiang has been recognized as its standard name， though it has also been known by alternative names such as Luchang， Lujiang， and Suanyi. The main sources used throughout the ages were Patrinia scabiosaefolia or P. villosa， which is consistent with the 1977 edition of the Pharmacopoeia of the People's Republic of China. However， while the roots were traditionally used medicinally， the whole plant is now more commonly used in modern practice. In addition， the whole plants of Thlaspi arvense from the Cruciferae family and Sonchus brachyotus from the Compositae family are commonly used as regional substitutes for Baijiang. According to ancient records， Patriniae Herba was primarily found in Jiangxia（present-day eastern Hubei province） and Jiangdong（the region south of the lower reaches of the Yangtze River）， but modern literature shows that it is distributed throughout the country without a distinct geographical origin. In ancient times， the roots were harvested in August and sun-dried， today， the whole plant is typically dug up in summer or autumn and sun-dried. In recent times， the quality has been summarized as being best when the roots are long， the leaves are abundant and green， and the aroma is strong. Regarding the processing， ancient methods often involved baking（drying over fire）， while modern methods typically involve removing impurities， washing， and then cutting and drying the segments. The effects of Patriniae Herba are to clear heat and detoxify， eliminate blood stasis and drain pus. During the Han and Northern and Southern dynasties， it was used to treat skin diseases caused by heat， abscesses， postpartum diseases， and rheumatism， during the Five dynasties period， its therapeutic applications expanded to include diseases of the five senses， and by the modern era， conditions such as neurasthenia and insomnia were added. Regarding its properties and taste， it was recorded as bitter and neutral during the Han dynasty. By the Tang dynasty， it was slightly cold， with a taste of acrid and bitter. During the Yuan and Ming dynasties， it was mostly slightly cold and neutral， with a bitter and salty taste. In the Qing dynasty and modern times， it was mostly bitter and neutral， and in contemporary times， it has evolved to a taste of acrid， bitter， and cool. Based on the results of this study， it is recommended that when developing and utilizing famous classical formulas containing Patriniae Herba， one should select the entire herb of the historically mainstream sources， P. scabiosaefolia or P. villosa from the Valerianaceae family， and choose the processing method according to the prescription requirements. It is recommended to use raw products without specific requirements.

The integration of large language model （LLM） and traditional Chinese medicine （TCM） promotes the informatization of TCM，and also provides a new direction for the inheritance and innovation of TCM in the new era. Based on the research background of LLM，the development process of LLM based on the Transformer architecture is summarized，and the research progress of LLM in TCM is reviewed. The main process of constructing TCM LLMs and the key techniques used by researchers during model development are summarized. Based on the related literature， the main application scenarios of TCM LLMs and the research explorations conducted by TCM researchers using LLMs are outlined. Meanwhile，the current challenges faced in the development of TCM LLMs are analyzed. Further improvements are urgently needed in the construction of high-quality data，the evaluation methodology of TCM LLMs，the interpretability of the model， multimodal fusion of TCM LLMs， and the development of TCM prescription recommendation models. Looking forward to the future development of LLM in TCM，it is expected to provide a reference for the deeper integration of LLMs and TCM，and facilitate the modernization of TCM.

Objective To explore the technical process and clinical application of laparoscopic combined upper midline incision minimally invasive liver transplantation. Methods A retrospective analysis was conducted on 30 cases of laparoscopic combined upper midline incision minimally invasive liver transplantation. The cases were divided into cirrhosis group (15 cases) and liver failure group (15 cases) based on the primary disease. The surgical and postoperative conditions of the two groups were compared. Results All patients successfully underwent laparoscopic "clockwise" liver resection, with no cases of passive conversion to open surgery or intolerance to pneumoperitoneum. In 6 cases, the right lobe was relatively large, and the right hepatic ligaments could not be completely mobilized. One case required an additional reverse "L" incision during open surgery. All patients successfully completed the liver transplantation, with no major intraoperative bleeding, cardiovascular events, or other occurrences in the 30 patients. The model for end-stage liver disease (MELD) score in the cirrhosis group was lower than that in the liver failure group (P<0.001). There were no statistically significant differences between the two groups in terms of age, surgical time, blood loss, anhepatic phase, or cold ischemia time (all P>0.05). During the perioperative period, there was 1 case of hepatic artery embolism, 1 case of portal vein anastomotic stenosis, no complications of hepatic vein and inferior vena cava, and 3 cases of biliary anastomotic stenosis, all of which occurred in the liver failure group. Conclusions In strictly selected cases, the minimally invasive liver transplantation technique combining laparoscopic hepatectomy with upper midline incision for graft implantation has the advantages of smaller incisions, less bleeding, relatively easier operation, and faster postoperative recovery, which is worthy of clinical promotion and application.

[Objective] To establish a new scoring system to predict the perioperative outcomes (operation time, intraoperative blood loss, and trifecta achievement) in patients undergoing robot-assisted partial nephrectomy (RAPN) by integrating the RENAL and Mayo adhesive probability (MAP) scores. [Methods] Clinical data of 178 patients with renal cell carcinoma who underwent RAPN performed by the same surgeon in our hospital during Jan.2015 and Jan.2022 were retrospectively analyzed.The RENAL and MAP scores of all patients were calculated.Linear regression and logistic regression were used to evaluate the associations between the components of the RENAL and MAP scores (a total of 6 variables) and perioperative outcomes.The factors with significant associations were then included into logistic regression analysis to identify independent predictors for constructing an assessment system for perioperative outcomes, and the receiver operating characteristic (ROC) curve was plotted to calculate the area under the curve (AUC) to predict its efficacy. [Results] Multivariate linear regression analysis showed that tumor size (β=6.14, 95%CI: 1.93—10.34, P=0.004), exophytic rate (β=10.60, 95%CI: 3.44—17.76, P=0.004), and perinephric fat thickness (β=16.48, 95%CI: 8.52—24.45, P<0.001) were significantly associated with operation time.Tumor size (β=10.55 95%CI: 5.60—15.49, P<0.001) was associated with both intraoperative blood loss and trifecta achievement (OR=1.73, 95%CI: 1.26—2.36, P=0.001). Multivariate logistic regression analysis of these 3 factors identified tumor size (OR=9.07, 95% CI: 1.18—69.45, P=0.03) and perinephric fat thickness (OR=2.28, 95%CI: 1.86—6.04, P=0.01) as independent predictors of perioperative outcomes.Based on these findings, the tumor size and perinephric fat thickness (RP) scoring was constructed, which demonstrated better predictive ability than RENAL score or MAP score alone (RP vs.RENAL vs.MAP: 0.766 vs.0.548 vs.0.684). [Conclusion] The RP score includes fewer variables than the RENAL and MAP scores but outperforms them.

In 2022， Hainan provincial government launched the project for the prevention and control of viral hepatitis with the goals of a hepatitis B screening rate of 90%， a diagnostic rate of 90%， and a treatment rate of 80% among people aged 18 years and above by the year 2025， and the main intervention measures include population-based prevention， case screening， antiviral therapy， and health management. As of December 31， 2024， a total of 6.875 million individuals in the general population had been screened for hepatitis B， with a screening rate of 95.6%. A total of 184 710 individuals with positive HBsAg were identified， among whom 156 772 were diagnosed through serological reexamination， resulting in a diagnostic rate of 84.9%. A total of 50 742 patients with chronic hepatitis B were identified， among whom 42 921 had hepatitis B-specific health records established for health management， with a file establishment rate of 84.6%. A total of 31 553 individuals received antiviral therapy， with a treatment rate of 62.2%. A total of 2.503 million individuals at a high risk of hepatitis C were screened， among whom 4 870 tested positive for HCV antibody and 3 858 underwent HCV RNA testing， resulting in a diagnostic rate of 79.2%， and 1 824 individuals with positive HCV RNA were identified， among whom 1 194 received antiviral therapy， with a treatment rate of 65.5%. In addition， 159 301 individuals with negative HBsAg and anti-HBs and an age of 20 — 40 years were inoculated with hepatitis B vaccine free of charge. Through the implementation of the project for the prevention and control of viral hepatitis， a large number of hepatitis patients have been identified， treated， and managed in the province within a short period of time， which significantly accelerates the efforts to eliminate the crisis of viral hepatitis.

ObjectiveThis study aims to investigate the dynamic changes in general body parameters, blood glucose, and blood lipid profiles in obese cynomolgus monkeys, exploring the correlations among these parameters and providing a reference for research on the obese cynomolgus monkey model. Methods30 normal male cynomolgus monkeys aged 5 - 17 years old (with body mass index < 35 kg/m² and glycated hemoglobin content < 4.50%) and 99 spontaneously obese male cynomolgus monkeys (with body mass index ≥35 kg/m² and glycated hemoglobin content < 4.50%) were selected. Over a period of three years, their abdominal circumference, skinfold thickness, body weight, body mass index, fasting blood glucose, glycated hemoglobin, and four blood lipid indicators were monitored. The correlations between each indicator were analyzed using repeated measurement ANOVA, simple linear regression, and multiple linear regression correlation analysis method. Results Compared to the control group, the obese group exhibited significantly higher levels of abdominal circumference, skinfold thickness, body weight, body mass index, and triglyceride (P＜0.05). In the control group, skinfold thickness increased annually, while other indicators remained stable. Compared with the first year, the obese group showed significantly increased abdominal circumference, skinfold thickness, body weight, body mass index, triglyceride, and fasting blood glucose in the second year(P＜0.05), with this increasing trend persisting in the third year (P＜0.05). In the control group, the obesity incidence rates in the second and third years were 16.67% and 23.33%, respectively, while the prevalence of diabetes remained at 16.67%. In the obese group, the diabetes incidence rates were 29.29% and 44.44% in years 2 and 3, respectively. Among the 11-13 year age group, the incidence rates were 36.36% and 44.68%, while for the group older than 13 years, the rates were 28.13% and 51.35%. Correlation analysis revealed significant associations (P＜0.05) between fasting blood glucose and age, abdominal circumference, skinfold thickness, body weight, and triglyceride in the diabetic monkeys. Conclusion Long-term obesity can lead to the increases in general physical indicators and fasting blood glucose levels in cynomolgus monkeys, and an increase in the incidence of diabetes. In diabetic cynomolgus monkeys caused by obesity, there is a high correlation between their fasting blood glucose and age, weight, abdominal circumference, skinfold thickness, and triglyceride levels, which is of some significance for predicting the occurrence of spontaneous diabetes.

OBJECTIVE To construct a predictive model for timely medication retrieval of outpatients， accurately identify high-risk patients with delayed medication retrieval， and provide data support for the development of differentiated registration strategies and resource optimization allocation in smart pharmacies. METHODS Based on 680 568 valid outpatient prescription records from January to March 2025 at the First Affiliated Hospital of Xi’an Jiaotong University， a dual-clustering analysis was conducted using K-means algorithm and Gaussian mixture model （GMM）. An adaptive threshold for medication retrieval time difference was determined by combining contour coefficients， and “timely medication retrieval” and “delayed medication retrieval” were divided to construct binary objective variables； six types of features were screened through a multi-method fusion strategy； the performance of 6 kinds of base learners and 4 kinds of ensemble learning models were evaluated from three dimensions： discrimination， overall performance， and calibration， and explanatory analysis of the models were conducted. RESULTS The results of the dual-clustering analysis showed that the silhouette coefficient of GMM was better than K-means （0.702 4 vs. 0.698 8）， and the final adaptive threshold was determined to be 49.82 min. Among the prescriptions included， 74.99% were for timely medication retrieval and 25.01% were for delayed medication retrieval. Among the 10 candidate models， the Stacking model performed the best， with an area under the test set curve of 0.954 4， F1 score of 0.942 4， accuracy of 0.911 5， Brier score of 0.066， and good discrimination and calibration. The explanatory analysis results of the model showed that its predictions were driven by multiple factors such as patient historical behavior， and diagnostic related characteristics. CONCLUSION This study constructed a timely medication retrieval prediction model for outpatients based on a two-stage adaptive threshold ensemble learning algorithm， which has high accuracy and stability， and can achieve dynamic judgment of patient medication retrieval behavior.