ObjectiveTo examine the influences of Shenfu injection on the endogenous metabolic byproducts in the myocardium of the rat model exhibiting chronic heart failure， thus deciphering the therapeutic mechanism of the Qi-reinforcing and Yang-warming method. MethodsSD rats were randomly allocated into a control group and a modeling group. Chronic heart failure with heart-Yang deficiency syndrome in rats was modeled by multi-point subcutaneous injection of isoproterenol， and the rats were fed for 14 days after modeling. The successfully modeled rats were randomized into model， Shenfu injection （6.0 mL·kg^-1）， and trimetazidine （10 mg·kg^-1） groups and treated with corresponding agents for 15 days. The control group and the model group were injected with equal doses of normal saline， and the samples were collected after the intervention was completed. Cardiac color ultrasound was performed. Hematoxylin-eosin （HE） staining was used to observe histopathological morphology， and the serum level of N-terminal pro-brain natriuretic peptide （NT-proBNP） was assessed by enzyme-linked immunosorbent assay （ELISA）. The mitochondrial morphological and structural changes of cardiomyocytes were observed by transmission electron microscopy， and the metabolic profiling was carried out by ultra high performance liquid chromatography-quantitative exactive-mass spectrometry （UHPLC-QE-MS）. Differential metabolites were screened and identified by orthogonal partial least squares-discriminant analysis （OPLS-DA） and other methods， and then the MetaboAnalyst database was used for further screening. The relevant biological pathways were obtained through pathway enrichment analysis. The receiver operating characteristic （ROC） curve was established to evaluate the diagnostic value of each potential biomarker for myocardial injury and the evaluation value for drug efficacy. ResultsThe results of color ultrasound showed that Shenfu Injection improved the cardiac function indexes of model rats （P<0.05）. The results of HE staining showed that Shenfu injection effectively alleviated the pathological phenomena such as myocardial tissue structure disorder and inflammatory cell infiltration in model rats. The results of ELISA showed that Shenfu injection effectively regulated the serum NT-proBNP level in the model rats. Transmission electron microscopy （TEM） showed that Shenfu injection effectively restored the mitochondrial morphological structure. The results of metabolomics showed that the metabolic phenotypes of myocardial samples presented markedly differences between groups. Nine differential metabolites could be significantly reversed in the Shenfu injection group， involving three metabolic pathways： pyruvate metabolism， histidine metabolism， and citric acid cycle （TCA cycle）. The results of ROC analysis showed that the area under the curve （AUC） values of all metabolites were between 0.75 and 1.0， indicating that the differential metabolites had high diagnostic accuracy for myocardial injury， and the changes in their expression levels could be used as potential markers for efficacy evaluation. ConclusionShenfu injection significantly alleviated the damage of cardiac function， myocardium， and mitochondrial structure in the rat model of chronic heart failure with heart-Yang deficiency syndrome by ameliorating energy metabolism remodeling. Reinforcing Qi and warming Yang is a key method for treating chronic heart failure with heart-Yang deficiency syndrome.

Traditional Chinese medicine(TCM) decoction pieces are a core carrier for the inheritance and innovation of TCM, and their quality and safety are critical to public health and the sustainable development of the industry. Conventional quality control models, while having established a well-developed system through long-term practice, still face challenges such as relatively long inspection cycles, insufficient objectivity in characterizing complex traits, and urgent needs for improving the efficiency of integrating multidimensional quality information when confronted with the dual demands of large-scale production and precision quality control. With the rapid development of artificial intelligence, machine learning can deeply analyze multidimensional data of the morphology, spectroscopy, and chemical fingerprints of decoction pieces by constructing high-dimensional feature space analysis models, significantly improving the standardization level and decision-making efficiency of quality evaluation. This article reviews the research progress in the application of machine learning in the processing, production, and rapid quality evaluation of TCM decoction pieces. It further analyzes current challenges in technological implementation and proposes potential solutions, offering theoretical and technical references to advance the digital and intelligent transformation of the industry.
Machine Learning ; Drugs, Chinese Herbal/standards* ; Quality Control ; Medicine, Chinese Traditional/standards* ; Humans

Metabolomics covers a wide range of applications in life sciences, biomedicine, and phytology. Data acquisition (to achieve high coverage and efficiency) and analysis (to pursue good classification) are two key segments involved in metabolomics workflows. Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups. However, insufficient feature extraction, inappropriate feature selection, overfitting, or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused. Using two ginseng varieties, namely Panax japonicus (PJ) and Panax japonicus var. major (PJvm), containing the similar ginsenosides, we integrated pseudo-targeted metabolomics and deep neural network (DNN) modeling to achieve accurate species differentiation. A pseudo-targeted metabolomics approach was optimized through data acquisition mode, ion pairs generation, comparison between multiple reaction monitoring (MRM) and scheduled MRM (sMRM), and chromatographic elution gradient. In total, 1980 ion pairs were monitored within 23 min, allowing for the most comprehensive ginseng metabolome analysis. The established DNN model demonstrated excellent classification performance (in terms of accuracy, precision, recall, F1 score, area under the curve, and receiver operating characteristic (ROC)) using the entire metabolome data and feature-selection dataset, exhibiting superior advantages over random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and multilayer perceptron (MLP). Moreover, DNNs were advantageous for automated feature learning, nonlinear modeling, adaptability, and generalization. This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples. This established approach holds promise for plant metabolomics and is not limited to ginseng.

BACKGROUND:Allogeneic hematopoietic stem cell transplantation is an important treatment for malignant hematological diseases,and delayed postoperative platelet implantation is a common complication that seriously affects the quality of patient survival;however,there are no standard protocols to improve platelet implantation rates and prevent platelet implantation delays. OBJECTIVE:To compare the safety and efficacy of oral Herombopag Olamine versus subcutaneous recombinant human thrombopoietin for promoting platelet implantation in patients with malignant hematological diseases undergoing haploid hematopoietic stem cell transplantation. METHODS:Clinical data of 163 patients with malignant hematological diseases who underwent haploidentical hematopoietic stem cell transplantation from January 2016 to October 2022 were retrospectively analyzed.A total of 72 patients who started to subcutaneously inject recombinant human thrombopoietin at+2 days were categorized into the recombinant human thrombopoietin group;a total of 27 patients who started to orally take Herombopag Olamine at+2 days were categorized into the Herombopag Olamine group;and 64 patients who did not apply Herombopag Olamine or recombinant human thrombopoietin were categorized into the blank control group.The implantation status,incidence of acute graft-versus-host disease of degree II-IV within 100 days,1-year survival rate,1-year recurrence rate,and safety were analyzed in the three groups. RESULTS AND CONCLUSION:(1)The average follow-up time was 52(12-87)months.The implantation time of neutrophils in the blank control group,recombinant human thrombopoietin group,and Herombopag Olamine group was(12.95±3.88)days,(14.04±3.71)days,and(13.89±2.74)days,respectively,with no statistically significant difference(P=0.352);the implantation time of platelets was(15.16±6.27)days,(17.67±6.52)days,and(17.00±4.75)days,with no statistically significant difference(P=0.287).(2)The complete platelet implantation rate on day 60 was 64.06%,90.28%,and 92.59%,respectively,and the difference was statistically significant(P<0.001).The subgroup analysis showed that the difference between the blank control group and the recombinant human thrombopoietin group was statistically significant(P<0.001),and the difference between the blank control group and the Herombopag Olamine group was statistically significant(P=0.004).The difference was not statistically significant between the recombinant human thrombopoietin group and Herombopag Olamine group(P=0.535).(3)100-day II-IV degree acute graft-versus-host disease incidence in the blank control group,recombinant human thrombopoietin group,and Herombopag Olamine group were 25.00%,30.56%,and 25.93%,respectively,and the difference was not statistically significant(P=0.752).(4)The incidence of cytomegalovirus anemia,cytomegalovirus pneumonia,and hepatic function injury had no statistical difference among the three groups(P>0.05).(5)During the follow-up period,there was no thrombotic event in any of the three groups of patients.(6)The results showed that recombinant human thrombopoietin and Herombopag Olamine could improve the platelet implantation rate of malignant hematological disease patients after haploidentical hematopoietic stem cell transplantation,with comparable efficacy and good safety.

Objective: To investigate the current status and trends of depressive symptoms among middle school and college students in Hunan Province, and to explore the primary related factors of depressive symptoms, so as to provide a scientific basis for strengthening mental health among students. Methods: A total of 279 382 students in Hunan Province were selected through a stratified cluster random sampling method from 2021 to 2023. National Survey Questionnaire on Common Diseases and Health Influencing Factors among Students was adopted for the survey, and the Center for Epidemiological Studies Depression Scale was used to assess their depressive symptoms. The χ 2 test and trend χ 2 test were used to analyze depressive symptoms prevalence and trends, and multivariable Logistic regression was used to analyze the related factors of depressive symptoms. Results: The prevalence of depressive symptoms among students in Hunan Province from 2021 to 2023 were 19.66%, 20.17% and 21.47%, respectively, showing an upward trend ( χ 2 trend =9.07, P <0.01). In addition, the results of the multivariable Logistic regression analysis showed that students with healthy diet ( OR=0.43, 95%CI =0.40-0.45), adequate sleep ( OR=0.88, 95%CI =0.86-0.90), and acceptable screen time ( OR=0.61, 95%CI =0.60-0.62) had lower risks in depressive symptoms detection, while students with smoking ( OR= 1.95, 95%CI =1.88-2.02), secondhand smoke exposure ( OR=1.33, 95%CI =1.30-1.36) and Internet addiction ( OR= 4.19 , 95%CI =4.05-4.34) had higher risks in depressive symptoms detection, with differences in the degree of association among different genders, educational stages and urban rural groups ( OR=0.40-6.04, Z =-12.69-11.98) ( P <0.05). Conclusions There is an increasing trend of depressive symptoms among middle school and college students in Hunan Province from 2021 to 2023.Targeted depression prevention measures should be taken for students with different demographic characteristics to promote their mental health.

Objective To develop an artificial intelligence (AI)-driven lung cancer database by structuring and standardizing clinical data, enabling advanced data mining for lung cancer research, and providing high-quality data for real-world studies. Methods Building on the extensive clinical data resources of the Department of Thoracic Surgery at Peking Union Medical College Hospital, this study utilized machine learning techniques, particularly natural language processing (NLP), to automatically process unstructured data from electronic medical records, examination reports, and pathology reports, converting them into structured formats. Data governance and automated cleaning methods were employed to ensure data integrity and consistency. Results As of September 2024, the database included comprehensive data from 18 811 patients, encompassing inpatient and outpatient records, examination and pathology reports, physician orders, and follow-up information, creating a well-structured, multi-dimensional dataset with rich variables. The database’s real-time querying and multi-layer filtering functions enabled researchers to efficiently retrieve study data that meet specific criteria, significantly enhancing data processing speed and advancing research progress. In a real-world application exploring the prognosis of non-small cell lung cancer, the database facilitated the rapid analysis of prognostic factors. Research findings indicated that factors such as tumor staging and comorbidities had a significant impact on patient survival rates, further demonstrating the database’s value in clinical big data mining. Conclusion The AI-driven lung cancer database enhances data management and analysis efficiency, providing strong support for large-scale clinical research, retrospective studies, and disease management. With the ongoing integration of large language models and multi-modal data, the database’s precision and analytical capabilities are expected to improve further, providing stronger support for big data mining and real-world research of lung cancer.

OBJECTIVE To systematically evaluate the efficacy and safety of tislelizumab in the treatment of advanced non- small cell lung cancer （NSCLC）. METHODS Computerized searches were conducted in PubMed， Embase， the Cochrane Library， CNKI， Wanfang and other Chinese and English databases to collect randomized controlled trials （RCTs） on tislelizumab for advanced NSCLC. The search period was from the establishment of the databases to December 2024. After strictly screening the literature， extracting data and conducting quality evaluations in accordance with the inclusion and exclusion criteria， a meta-analysis was performed using RevMan 5.3 and Stata 16.0 software. RESULTS A total of 18 RCTs involving 2 337 patients were included， with 1 283 in the experimental group and 1 054 in the control group. The meta-analysis results showed that the objective response rate [RR＝1.61， 95%CI （1.48， 1.75）， P＜0.000 01]， disease control rate [RR＝1.21， 95%CI （1.13， 1.29）， P＜0.000 01]， progression free survival [HR＝0.55， 95%CI （0.45， 0.66）， P＜0.000 01]， and overall survival [HR＝0.78， 95%CI（0.62， 0.97）， P＝0.03] were significantly better in the experimental group than in the control group. There was no statistically significant difference in the incidence of adverse reactions between the two groups [RR＝1.00， 95%CI （0.73， 1.37）， P＝1.00]； among the common adverse reactions， only the incidence of liver function impairment was significantly higher in the experimental group than in the control group [RR＝1.30， 95%CI （1.10， 1.54）， P＜0.01]. CONCLUSIONS Tislelizumab in combination with chemotherapy or targeted drugs significantly improves the efficacy in patients with advanced NSCLC without increasing the risk of adverse reactions overall. However， liver function should be closely monitored during treatment.

Background In recent years, the increasingly widespread application of nuclear and medical radiation technologies has resulted in a large number of occupational populations exposed to low-dose ionizing radiation (LDIR). At present, there is no consistent conclusion on the effects of long-term exposure to LDIR on the metabolic health of the occupational population. Objective To explore the association between long-term exposure to LDIR and metabolic syndrome (MetS) among medical radiologists. Methods A cross-sectional study was conducted to enroll 6431 medical radiologists who ordered occupational health checkups from January 2022 to December 2023, and basic information such as demographic characteristics, occupational characteristics, lifestyles, and dietary habits was collected through questionnaires. Physical examinations were conducted using a standardized protocol. Individual dose equivalents of occupational external exposure were monitored by dosimeters worn by medical radiologists. Logistic regression model was used for identifying influencing factors of MetS and sensitivity analysis, and restricted cubic spline model was used to explore the dose-response relationship between cumulative effective dose and MetS. Two-stage linear regression was used to evaluate threshold effect of association between cumulative effective dose and MetS. Results The positive rate of MetS was 13.6% (877/6431) among the enrolled 6431 study participants. The logistic regression showed that gender, age, monthly income, body mass index (BMI), cumulative effective dose, and smoking were influencing factors for MetS. The risk of MetS was higher in males (OR=1.511, 95%CI: 1.209, 1.888); using the < 30 years old group as reference, the risk of MetS was higher in the 30-39 years old (OR=1.509, 95%CI: 1.095, 2.079), 40-49 years old (OR=2.214, 95%CI: 1.551, 3.161), and ≥50 years old (OR=3.480, 95%CI: 2.338, 5.181) groups; using the <10000 yuan group as reference, the risk of MetS was lower in the group with a monthly income of 10000-14999 yuan (OR=0.715, 95%CI: 0.582, 0.878); the risk of MetS was higher in the BMI ≥ 24 kg·m⁻² group (OR=7.548, 95%CI: 6.223, 9.156); using the < 0.76 mSv group as reference, the risk of MetS was higher in the cumulative effective dose of 0.76-2.73 mSv group (OR=1.270, 95%CI: 1.017, 1.586); the risk of MetS was higher in the smoking group (OR=1.734, 95%CI: 1.428, 2.107). The results of restricted cubic spline showed that the cumulative effective dose was nonlinearly correlated with MetS (P _{non-linearity}=0.028), with an inflection point of 1.25 mSv. The risk of developing MetS increased by 34.1% for each unit increase in cumulative effective dose up to 1.25 mSv, whereas above 1.25 mSv, the statistical association was not significant. The sensitivity analysis results showed that after excluding the self-reported hypertensive and diabetic patients, the cumulative effective dose 0.76-2.73 mSv group still had an increased risk of developing MetS compared with the < 0.76 mSv group (P < 0.05), and the results were robust. Conclusion Among medical radiologists, male, age, BMI, and smoking are positively correlated with MetS, and monthly income is negatively correlated with MetS; cumulative effective dose is non-linearly correlated with MetS among medical radiologists.

OBJECTIVES: To investigate the clinical sub-phenotype (SP) of pediatric acute kidney injury (AKI) and their association with clinical outcomes. METHODS: General status and initial values of laboratory markers within 24 hours after admission to the pediatric intensive care unit (PICU) were recorded for children with AKI in the derivation cohort (n=650) and the validation cohort (n=177). In the derivation cohort, a least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify death-related indicators, and a two-step cluster analysis was employed to obtain the clinical SP of AKI. A logistic regression analysis was used to develop a parsimonious classifier model with simplified metrics, and the area under the curve (AUC) was used to assess the value of this model. This model was then applied to the validation cohort and the combined derivation and validation cohort. The association between SPs and clinical outcomes was analyzed with all children with AKI as subjects. RESULTS: In the derivation cohort, two clinical SPs of AKI (SP1 and SP2) were identified by the two-step cluster analysis using the 20 variables screened by LASSO regression, namely SP_d1 group (n=536) and SP_d2 group (n=114). The simplified classifier model containing eight variables (P<0.05) had an AUC of 0.965 in identifying the two clinical SPs of AKI (P<0.001). The validation cohort was clustered into SP_v1 group (n=156) and SP_v2 group (n=21), and the combined derivation and validation cohort was clustered into SP1 group (n=694) and SP2 group (n=133). After adjustment for confounding factors, compared with the SP1 group, the SP2 group had significantly higher incidence rates of multiple organ dysfunction syndrome and death during the PICU stay (P<0.001), and SP2 was significantly associated with the risk of death within 28 days after admission to the PICU (P<0.001). CONCLUSIONS This study establishes a parsimonious classifier model and identifies two clinical SPs of AKI with different clinical features and outcomes.The SP2 group has more severe disease and worse clinical prognosis.
Humans ; Acute Kidney Injury/diagnosis* ; Prognosis ; Male ; Female ; Child ; Child, Preschool ; Phenotype ; Infant ; Logistic Models ; Adolescent