To develop and validate a model for predicting intensive care unit (ICU) mortality risk in patients with malignant tumors complicated by acute respiratory failure (ARF) based on an explainable machine learning framework.

Based on the theory of "disease of both blood and water" in Essentials from the Golden Cabinet （《金匮要略》）， and in combination with the dynamic syndrome evolution of heart failure with preserved ejection fraction （HFpEF）， this paper systematically clarifies the pathomechanism of HFpEF， characterized by yang deficiency as the root， blood stasis as the pivotal factor and water retention as the manifestation. Accordingly， the therapeutic principles have been proposed， which are warming yang and banking up original qi to consolidate the root， activating blood and unblocking collaterals to smooth the mechanism， and promoting urination and regulating pivot to remove the branch. On this basis， a compound formula structure of "one monarch， one minister and one assistant" is established， forming an integrated intervention strategy that synergistically combines the three methods of warming yang， activating blood， and promoting urination through combined classical formulas. Zhenwu Decoction （真武汤）， which warms yang and dissolves rheum， is used to consolidate the root and directly target the source of yang deficiency， serving as the monarch； Guizhi Fuling Pills （桂枝茯苓丸）， which activates blood， promotes urination and unblocks the pivot， assists in interrupting the binding of blood stasis and water retention， serving as the minister； Tingli Dazao Xiefei Decoction （葶苈大枣泻肺汤）， which regulates qi， disperses retained fluids， and eliminates the manifestation， alleviates acute water-retention symptoms， serving as the assistant. This compound formula is warming without being drying， diuretic without being drastic， and dispels stasis without consuming blood， thereby achieving the therapeutic effects of warming yang， activating blood， and promoting urination.

Objective: To analyze the independent and interaction effects of daytime outdoor light exposure and moderate to vigorous physical activity (MVPA) duration on sleep quality of primary school students, so as to provide scientific evidence for interventions on children s sleep health. Methods: From April to June 2024, a total of 444 students from grades 3 and 4 in 2 primary schools in Jiading District, Shanghai were selected using stratified random cluster sampling method for continuous 7 day monitoring. Wearable devices "Clouclip" were used to monitor daytime outdoor activity time (represented by time with light intensity ≥ 1 000 lx ), and accelerometers were used to monitor MVPA time and sleep quality related indicators. Multiple linear regression was used to analyze the associations of daytime outdoor activity and MVPA with sleep quality. Results: Both daytime outdoor light exposure and MVPA duration(longer actual sleep duration per night,longer time in bed,fewer awakening and shorter post sleep awakening shic) were independently associated with multiple sleep indicators( β =0.52, 0.46, -0.83, -2.19, all P <0.05), with no significant interaction between the associations ( P >0.05). After controlling for MVPA, more daytime outdoor light exposure was significantly and independently associated with longer actual sleep time ( β =0.50, 95% CI =0.21-0.79, P <0.05). After controlling for light exposure, longer MVPA duration was independently associated with shorter post-sleep awakening duration ( β=-4.15, 95% CI = -6.33 to -1.96, P <0.05). Conclusion Increased daytime outdoor activity and MVPA are both associated with better sleep quality in primary school students.

OBJECTIVE To evaluate the cost-effectiveness of culmerciclib combined with fulvestrant as second-line treatment for patients with hormone receptor-positive（HR+）/human epidermal growth factor receptor 2-negative （HER2–） locally advanced or metastatic breast cancer， within the context of the Chinese healthcare system. METHODS A partitioned survival model was established based on the CULMATE-1 study， with a simulation time horizon set at 15 years and a cycle length of 28 days. The incremental cost-effectiveness ratio （ICER） of culmerciclib combined with fulvestrant versus fulvestrant monotherapy as second-line treatment for HR+/HER2– breast cancer was calculated. One-way sensitivity analysis and probabilistic sensitivity analysis were performed to assess the robustness of the model. Meanwhile， scenario analysis of culmerciclib price reduction was conducted； the required price reduction and price to reach the willingness-to-pay （WTP） threshold in this study were calculated. RESULTS The results of the base-case analysis indicated that， compared with the fulvestrant monotherapy regimen， culmerciclib combined with fulvestrant yielded an additional 0.823 quality-adjusted life year （QALY）， with a corresponding ICER of 371 696.26 yuan/QALY， which exceeded the WTP threshold （199 330 yuan/QALY）. The results of the univariate sensitivity analysis indicated that the cost of culmerciclib， the discount rate， the utility values for progression disease and progression free survival status were significant factors influencing the ICER； both the univariate sensitivity analysis and the probabilistic sensitivity analysis validated the robustness of the model results. Scenario analysis indicated that when the price of culmerciclib was reduced by 30%， 55% and 85% respectively， the corresponding ICER values fell below 3， 2， and 1 times China’s per capita GDP in 2025， with the probability of cost-effectiveness being 3.00%， 94.90%， 100%. When the cost of culmerciclib （60 mg） was reduced by 52.6% to 50.96 yuan， the ICER value met the WTP threshold established in this study. CONCLUSIONS When the WTP threshold is set at twice China’s per capita GDP in 2025， second-line treatment with culmerciclib combined with fulvestrant for HR+/HER2– locally advanced or metastatic breast cancer does not exhibit cost-effectiveness advantage over fulvestrant monotherapy. Therefore， a reasonable price reduction is required to alleviate the financial burden on patients.

ObjectiveTo observe the protective effect of Erchentang （ECT） on SiO₂-induced lung injury in rats and to explore its underlying mechanism. MethodsA rat model of lung injury was established by a single intratracheal instillation of 50 mg·mL^-1 SiO₂ suspension. Thirty male Sprague-Dawley （SD） rats were randomly assigned to five groups： control， model， low and high-dose （4.5 g·kg^-1·d^-1 and 9 g·kg^-1·d^-1， respectively） ECT， and dexamethasone （0.2 mg·kg^-1·d^-1）. All the groups were treated for 4 consecutive weeks. Histopathological alterations in the lung tissue were examined by hematoxylin and eosin （HE） staining. The levels of malondialdehyde （MDA）， superoxide dismutase （SOD）， and glutathione peroxidase （GSH-Px） in the lung tissue were measured through biochemical assays. The expression of key molecules in the nuclear factor erythroid 2-related factor 2 （Nrf2）/heme oxygenase-1 （HO-1） pathway was determined by Real-time fluorescence quantitative polymerase chain reaction （Real-time PCR）， Western blot， and immunofluorescence assay. The primary active components of ECT were identified by ultra-performance liquid chromatography-tandem mass spectrometry （UPLC-MS/MS）， and their binding affinity to Nrf2/HO-1 was assessed by molecular docking. Untargeted metabolomics of the lung tissue was performed based on UPLC-quadrupole time-of-flight mass spectrometry （UPLC-Q-TOF-MS）， and correlation analysis was performed to identify differential metabolites and parameters closely associated with the Nrf2/HO-1 pathway. ResultsCompared with the control group， the model group exhibited a reduction in body weight gain， an increase in lung index， increased MDA content， weakened SOD and GSH-Px activities in the lung tissue， down-regulated mRNA and protein levels of Nrf2 and protein levels of HO-1 and GPX4， and an up-regulated protein level of Keap1 （P<0.05， P<0.01）. Treatment with ECT attenuated the SiO₂-induced decline in body weight （P<0.05）， alleviated inflammatory cell infiltration and silicotic nodule formation in alveoli， and reduced the MDA content and enhanced the SOD and GSH-Px activities in the lung tissue （P<0.05， P<0.01）. UPLC-MS/MS and molecular docking revealed that core components of ECT， such as hesperidin and glycyrrhizic acid， displayed strong binding affinity to Nrf2/HO-1. Molecular biological experiments demonstrated that ECT promoted nuclear translocation of Nrf2， up-regulated the mRNA and protein levels of HO-1 and GPX4， and down-regulated Keap1 expression （P<0.05， P<0.01）. Metabolomic analysis indicated that ECT reversed the SiO₂-induced aberrant expression of metabolites， including linoleic acid and glutamine （P<0.05， P<0.01）. Correlation analysis showed that Nrf2 and HO-1 were positively correlated with SOD and GSH-Px （P<0.05， P<0.01）， but negatively correlated with glutamine and serine （P<0.05， P<0.01）. ConclusionECT may activate the Nrf2/HO-1 pathway through its core active components， thereby regulating oxidative stress and metabolic disorders to ameliorate SiO₂-induced lung injury in rats. This study provides experimental evidence for ECT in the prevention and treatment of occupational lung injury.

Triatoma rubrofasciata is currently the most widely distributed species of Triatoma worldwide, and it is also widespread in southern China. T. rubrofasciata has been proven to transmit Trypanosoma cruzi, and is one of vectors transmitting Chagas disease, which poses a potential risk for transmission of imported Chagas disease in China. Findings from latest studies have shown that T. rubrofasciata naturally infects T. lewisi, T. conorhini, and T. rangeli, which undoubtedly increases significant risks of and challenges to trypanosomiasis control in China. This article briefly describes the species of T. rubrofasciata-transmitted trypanosomes, and summarizes the epidemiological characteristics of trypanosomiasis, so as to provide insights into T. rubrofasciata-transmitted trypanosomiasis surveillance and control, and prevention of trypanosomiasis development and transmission in China.

ObjectiveThis paper aims to investigate the differential mechanisms underlying the staged therapeutic effects of Qijia Rougan formula on liver fibrosis using proteomic technology. MethodsThe staged rat model of liver fibrosis was established by subcutaneous injection of carbon tetrachloride （CCl₄） and olive oil. One hundred and four SD rats were randomized into thirteen groups：a normal group，a two-week model group，a four-week model group，a six-week model group，an eight-week model group，a two-week Qijia Rougan formula group，a four-week Qijia Rougan formula group，a six-week Qijia Rougan formula group，an eight-week Qijia Rougan formula group，a two-week compound Biejia Ruangan tablet group，a four-week Compound Biejia Ruangan Tablet group，a six-week Compound Biejia Ruangan Tablet group，and an eight-week compound Biejia Ruangan tablet group. After two weeks of drug intervention，liver tissue and abdominal aortic blood samples were collected from the rats for testing. Hematoxylin-eosin （HE） staining，Masson staining，and Picro Sirius red staining were used to observe pathological damage and collagen fiber deposition in liver tissues. Immunohistochemistry （IHC） was employed to detect the contents of fibrosis markers in liver tissues. The contents of liver function indicators in the serum were measured using a fully automated biochemical analyzer，and the levels of liver fibrosis indicators in the serum were assessed by enzyme-linked immunosorbent assay （ELISA）. Liver tissues from the normal group，each model group，and each Qijia Rougan formula group were subjected to label-free quantitative proteomic analysis to identify differential proteins among the groups，with key proteins validated by Western blot. Finally，bioinformatics analysis was performed on the differential proteins. Results（1） The staged rat model of liver fibrosis constructed with CCl₄ and olive oil showed pathological results at the 2^nd，4^th，6^th，and 8^th weeks of modeling that were consistent with the Metavir standards for the F1，F2，F3，and F4 stages. Compared with those in the normal control group，the protein expressions of α-smooth muscle actin （α-SMA） and Collagen Ⅰ were significantly increased in each stage （P<0.05）. The levels of liver function indicators in the serum，including alanine aminotransferase （ALT），aspartate aminotransferase （AST），alkaline phosphatase （ALP），direct bilirubin （DBIL），and total bilirubin （TBil） in each model group，were significantly elevated in each stage （P<0.01）. The levels of liver fibrosis indicators in the serum，including procollagen Ⅲ peptide （PⅢP），type Ⅳ collagen（Ⅳ-C），hyaluronic acid （HA），and laminin （LN） in each model group，were significantly increased in each stage （P<0.05，P<0.01）. This study successfully established a staged rat model of liver fibrosis. （2） Compared with the model groups at each stage，the administration groups showed a reduction in hepatocyte ballooning degeneration，a more orderly arrangement of hepatocytes，and a decrease of inflammatory cell infiltration. The blue-stained collagen fibers became significantly thinner and finer，with reduced and narrowed fibrous septa. The areas of collagen fibers and Picro Sirius red staining were reduced （P<0.05）. The positive areas of α-SMA and Collagen Ⅰ expression were significantly decreased （P<0.05）. The levels of ALT，AST，ALP，DBIL，and TBil in the rats of the model groups at each stage were significantly reduced （P<0.05，P<0.01）. The levels of PⅢP，Ⅳ-C，HA，and LN in the rats of the model groups at each stage were significantly decreased （P<0.05）. Among these，the improvements in all indicators were most significant in the F3 stage （P<0.01）.（3） The proteomic results show that a total of 165 differential proteins exhibit a callback trend when comparing the model groups at four stages with the normal group，and when comparing the Qijia Rougan formula group with the model group. Western blot analysis reveals that the levels of NAD（P）H：quinone oxidoreductase 1 （NQO1），mitogen-activated protein kinase 1 （MAPK1），arginase 1 （Arg1），and glutathione S-transferase α1 （GSTA1） were consistent with the proteomic results. Bioinformatics results reveal that 165 differentially expressed proteins are enriched in multiple signaling pathways. Notably，signaling pathways such as drug metabolism-cytochrome P450，arginine biosynthesis，and the peroxisome proliferator-activated receptor （PPAR） signaling pathway were found to be closely associated with liver fibrosis，suggesting that the Qijia Rougan formula may exert its staged regulatory effects on liver fibrosis by regulating these pathways. ConclusionThe Qijia Rougan formula may achieve staged regulation of liver fibrosis by regulating drug metabolism-cytochrome P450，arginine biosynthesis，and the PPAR signaling pathway.

Objective: To address the lack of fine-grained clinical recognition for specific Yang deficiency syndrome subtypes and the limitations of conventional object detection models in extracting irregular, low-contrast tongue phenotypes. This study aims to develop an objective subtype recognition framework based on an improved You Only Look Once nano (YOLO11n) architecture, using a standardized visual phenotype matrix to translate macroscopic traditional Chinese medicine (TCM) descriptions into quantifiable clinical targets. Methods: This cross-sectional diagnostic study consecutively enrolled adult inpatients admitted to the Department of Thyroid and Breast Surgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital), between September 1, 2024 and June 1, 2025, who were suspected of having Yang deficiency constitution based on initial TCM consultation. Clinical tongue image data were collected for analysis. Based on an Expert Visual Phenotype Annotation Matrix, a five-category recognition system was established, including the following TCM syndrome subtypes: spleen-dampness exuberance syndrome, mild kidney Yang deficiency syndrome, upper heat and lower cold syndrome, simultaneous Yin-Yang deficiency syndrome, and Yin deficiency and fluid depletion syndrome (negative control). The proposed Yang deficiency YOLO (YD-YOLO) model, built upon the YOLO11n baseline, integrates the Cross Stage Partial with kernel size 2 (C3k2)-GhostBottleneck-Dynamic Convolution (GBDC) module into the backbone to adaptively extract low-contrast features, and embeds the multipath aggregation coordinate attention (MACA) mechanism into the neck to suppress background interference through multi-scale spatial coordination. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize feature attribution and evaluate the biological plausibility of the model’s focus. Model performance was evaluated through ablation and comparative experiments using mean average precision (mAP), precision, recall, F1 score, inference speed (frames per second, FPS), overall accuracy, Cohen’s kappa, and the area under the receiver operating characteristic (ROC) curve (AUC). Results: Based on the final inclusion of 1 186 clinical cases, the YD-YOLO model had an overall accuracy of 91.5%, a Cohen’s kappa of 0.912, and an mAP@50 of 0.731 [higher than the YOLO11n baseline (0.681)], with AUC ranging from 0.91 to 0.97 across all TCM syndrome subtypes. Among the TCM syndrome subtypes, the mild kidney Yang deficiency syndrome had the highest mAP@50 (0.900), and the inference speed reached 89.00 FPS. Grad-CAM analysis showed that the model localized activation to key TCM pathological features, such as marginal tooth marks and focal root coatings, while suppressing non-diagnostic oral background noise. Conclusion The YD-YOLO model demonstrates the feasibility of deep learning for the fine-grained classification of TCM Yang deficiency subtypes. By integrating visual phenotype quantification with model interpretability, the proposed framework provides an objective basis for syndrome differentiation, supporting the development of standardized digital diagnostic systems and the provision of clinical decision support in TCM practice.

The rupture of carotid vulnerable plaques is the core pathological basis for major cardiovascular and cerebrovascular events. However， the insufficient alignment between existing animal models and the clinical disease and syndrome characteristics of traditional Chinese and western medicine has limited research progress. In this study， biomedical databases in China and abroad were systematically searched， and the modeling mechanisms and evaluation systems of carotid vulnerable plaque animal models were systematically assessed based on diagnostic criteria of both traditional Chinese and western medicine. Analysis of the clinical correspondence indicated that existing animal models can be categorized into four types： simple high-fat diet， surgical induction combined with high-fat feeding， genetic engineering combined with high-fat feeding， and drug induction combined with high-fat feeding. Among these， the compound strategy of surgical induction combined with high-fat feeding has become the current mainstream approach， showing good concordance with western medicine. The study found that the double balloon injury rabbit model and the ApoE^-/- mouse carotid artery tandem constriction combined with high-fat feeding model demonstrated a high degree of clinical correspondence with both traditional Chinese and western medicine in terms of vulnerable plaque imaging and pathological features. Nevertheless， existing models still face significant technical limitations in faithfully simulating plaque pathology and in translating findings to clinical applications. To address these challenges， integrating complex comorbidity mechanism construction， multimodal dynamic mechanism monitoring， and collaborative evaluation systems of traditional Chinese and western medicine could enable the development of highly concordant carotid vulnerable plaque disease-syndrome combination animal models. Such models would provide a reproducible experimental platform for targeted drug development to regulate plaque stability and for individualized precision treatment， as well as a theoretical basis for innovation in clinical diagnostic and therapeutic strategies.

OBJECTIVE: To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. METHODS: Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. RESULTS: The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. CONCLUSION The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.
Humans ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Adult ; Male ; Female