ObjectiveTo investigate whether Huanglian Jiedutang can inhibit neutrophil infiltration in the brains of middle cerebral artery occlusion （MCAO） mice by regulating the expression of neutrophil-related chemokines in exosomes， thereby achieving therapeutic effects. MethodsA total of 130 male specific pathogen-free （SPF） C57BL/6J mice were randomly divided into four groups： Sham-operated group， MCAO model group， Huanglian Jiedutang group （6 g·kg^-1）， and Ginaton group （21.6 mg·kg^-1）， with 10 mice in the Ginaton group and 40 mice in each of the remaining three groups. Mice in the Huanglian Jiedutang group and the Ginaton group were administered the corresponding drugs by oral gavage once daily at a volume of 0.15 mL·（10 g）^-1 for 7 consecutive days， while the sham-operated and model groups received an equal volume of saline via the same route. After 7 days， MCAO surgery was performed. The distal and proximal ends of the right common carotid artery （CCA） were ligated， a small incision was made between the two ligatures， and a silicone rubber-coated monofilament with a rounded tip was inserted into the lumen to occlude the CCA. The filament was left in place for 1 h to establish a focal cerebral ischemia model. At 24 h after modeling， mice were evaluated. Neurological function was assessed using the Longa score. Cerebral infarct volume was measured by 2，3，5-triphenyltetrazolium chloride （TTC） staining. Cerebral blood flow was observed by laser speckle imaging. Hematoxylin and eosin （HE） staining and Nissl staining were used to observe pathological changes in brain tissues. Exosomes were isolated from mouse plasma and brain tissues by ultracentrifugation and molecular size exclusion and identified by electron microscopy， particle size analysis， and protein blotting. Long-chain RNA libraries of exosomes were constructed and sequenced. Real-time quantitative reverse transcription polymerase chain reaction （Real-time PCR） was used to detect the mRNA expression of inflammatory factors and neutrophil-related chemokines in exosomes from plasma and brain tissues of each group. Enzyme-linked immunosorbent assay （ELISA） was used to detect the protein expression of inflammatory factors and neutrophil-related chemokines in exosomes from brain tissues of each group. Immunohistochemistry was used to detect the expression of the neutrophil-specific protein myeloperoxidase （MPO） in the brains of mice in each group. ResultsCompared with the sham-operated group， the model group showed decreased neurological function scores （P<0.01）， obvious cerebral infarction （P<0.01）， reduced cerebral blood flow （P<0.01）， neuronal necrosis in the brain， and decreased numbers of Nissl bodies （P<0.01）. The mRNA expression levels of IL-1β， MPO， CXCL1， CXCL2， CXCL3， CXCL10， CCL2， and CCL3 in exosomes from plasma and brain tissues were significantly increased （P<0.05， P<0.01）. The protein expression levels of IL-1β， MPO， CXCL2， and CXCL10 in exosomes from brain tissues were increased （P<0.05， P<0.01）， and MPO-positive rates and mean optical density values in brain tissues were elevated （P<0.01）. Compared with the model group， the Huanglian Jiedutang group and the Ginaton group showed increased neurological function scores （P<0.05）， reduced cerebral infarct volume （P<0.01）， restored cerebral blood flow （P<0.01）， reduced necrotic cells in the brain， and increased numbers of Nissl bodies （P<0.01）. In the Huanglian Jiedutang group， the mRNA expression levels of IL-1β， MPO， CXCL1， CXCL2， CXCL3， CXCL10， CCL2， and CCL3 in exosomes from plasma and brain tissues were decreased （P<0.05， P<0.01）. The protein expression levels of IL-1β， MPO， CXCL2， and CXCL10 in exosomes from brain tissues were reduced （P<0.05， P<0.01）， and MPO-positive rates and mean optical density values in brain tissues were decreased （P<0.01）. ConclusionHuanglian Jiedutang can effectively regulate the expression of neutrophil-related chemokines in exosomes from plasma and brain tissues of MCAO mice， thereby reducing neutrophil infiltration in the brain and achieving therapeutic effects.

ObjectiveTo investigate whether Huanglian Jiedutang can inhibit neutrophil infiltration in the brains of middle cerebral artery occlusion （MCAO） mice by regulating the expression of neutrophil-related chemokines in exosomes， thereby achieving therapeutic effects. MethodsA total of 130 male specific pathogen-free （SPF） C57BL/6J mice were randomly divided into four groups： Sham-operated group， MCAO model group， Huanglian Jiedutang group （6 g·kg^-1）， and Ginaton group （21.6 mg·kg^-1）， with 10 mice in the Ginaton group and 40 mice in each of the remaining three groups. Mice in the Huanglian Jiedutang group and the Ginaton group were administered the corresponding drugs by oral gavage once daily at a volume of 0.15 mL·（10 g）^-1 for 7 consecutive days， while the sham-operated and model groups received an equal volume of saline via the same route. After 7 days， MCAO surgery was performed. The distal and proximal ends of the right common carotid artery （CCA） were ligated， a small incision was made between the two ligatures， and a silicone rubber-coated monofilament with a rounded tip was inserted into the lumen to occlude the CCA. The filament was left in place for 1 h to establish a focal cerebral ischemia model. At 24 h after modeling， mice were evaluated. Neurological function was assessed using the Longa score. Cerebral infarct volume was measured by 2，3，5-triphenyltetrazolium chloride （TTC） staining. Cerebral blood flow was observed by laser speckle imaging. Hematoxylin and eosin （HE） staining and Nissl staining were used to observe pathological changes in brain tissues. Exosomes were isolated from mouse plasma and brain tissues by ultracentrifugation and molecular size exclusion and identified by electron microscopy， particle size analysis， and protein blotting. Long-chain RNA libraries of exosomes were constructed and sequenced. Real-time quantitative reverse transcription polymerase chain reaction （Real-time PCR） was used to detect the mRNA expression of inflammatory factors and neutrophil-related chemokines in exosomes from plasma and brain tissues of each group. Enzyme-linked immunosorbent assay （ELISA） was used to detect the protein expression of inflammatory factors and neutrophil-related chemokines in exosomes from brain tissues of each group. Immunohistochemistry was used to detect the expression of the neutrophil-specific protein myeloperoxidase （MPO） in the brains of mice in each group. ResultsCompared with the sham-operated group， the model group showed decreased neurological function scores （P<0.01）， obvious cerebral infarction （P<0.01）， reduced cerebral blood flow （P<0.01）， neuronal necrosis in the brain， and decreased numbers of Nissl bodies （P<0.01）. The mRNA expression levels of IL-1β， MPO， CXCL1， CXCL2， CXCL3， CXCL10， CCL2， and CCL3 in exosomes from plasma and brain tissues were significantly increased （P<0.05， P<0.01）. The protein expression levels of IL-1β， MPO， CXCL2， and CXCL10 in exosomes from brain tissues were increased （P<0.05， P<0.01）， and MPO-positive rates and mean optical density values in brain tissues were elevated （P<0.01）. Compared with the model group， the Huanglian Jiedutang group and the Ginaton group showed increased neurological function scores （P<0.05）， reduced cerebral infarct volume （P<0.01）， restored cerebral blood flow （P<0.01）， reduced necrotic cells in the brain， and increased numbers of Nissl bodies （P<0.01）. In the Huanglian Jiedutang group， the mRNA expression levels of IL-1β， MPO， CXCL1， CXCL2， CXCL3， CXCL10， CCL2， and CCL3 in exosomes from plasma and brain tissues were decreased （P<0.05， P<0.01）. The protein expression levels of IL-1β， MPO， CXCL2， and CXCL10 in exosomes from brain tissues were reduced （P<0.05， P<0.01）， and MPO-positive rates and mean optical density values in brain tissues were decreased （P<0.01）. ConclusionHuanglian Jiedutang can effectively regulate the expression of neutrophil-related chemokines in exosomes from plasma and brain tissues of MCAO mice， thereby reducing neutrophil infiltration in the brain and achieving therapeutic effects.

ObjectiveTo investigate whether Huanglian Jiedutang （HLJD） and its major active constituents （geniposide， baicalin， and berberine） can inhibit the inflammatory response of BV2 cells under lipopolysaccharide （LPS） stimulation via the high-mobility group protein B1 （HMGB1）/Toll-like receptor 4 （TLR4）/nuclear factor-κB （NF-κB） signaling pathway， and to explore differences in therapeutic efficacy among the three monomers， their combined formula， and HLJD under equal content ratios. MethodsBV2 microglial cells were used as the primary experimental model. Cell viability was assessed using the cell counting kit-8 （CCK-8） method to examine the effects of different concentrations of dimethyl sulfoxide （DMSO， 0.8%， 0.4%， 0.2%， 0.1%， and 0.05%） on cell viability. IncuCyte was employed to monitor the growth of cells under different concentrations of HLJD （200， 100， 50， 25， 12.5， 6.25 mg·L^-1）. Nitric oxide （NO） assay was used to screen the optimal HLJD concentration. High-performance liquid chromatography （HPLC） determined the content of geniposide， baicalin， and berberine in HLJD， and experimental groups were subsequently established according to the relative proportions of these constituents. CCK-8 assay evaluated cell viability under different treatments. Enzyme-linked immunosorbent assay （ELISA） measured levels of inflammatory factors （TNF-α， IL-1β， IL-6， IL-10） in the supernatant. Flow cytometry assessed the effects of treatments on M1-type polarization of BV2 cells. Western blot determined the expression levels of HMGB1， TLR4， and NF-κB-related proteins. ResultsCompared with the blank group， DMSO at concentrations ≤0.2% did not affect cell viability within 48 h. BV2 cell growth plateaued at 24 h after treatment with 200 mg·L^-1 HLJD. Under stimulation with 2 mg·L^-1 LPS， this concentration of HLJD effectively reduced NO release， and 6 h pre-treatment had a stronger inhibitory effect on NO than direct administration. HPLC results showed that 1 mg of HLJD freeze-dried powder contained approximately 24 μg of geniposide， 15 μg of baicalin， and 30 μg of berberine. Based on these ratios， experimental groups were blank， LPS （2 mg·L^-1）， HLJD （200 mg·L^-1）， monomer combination， geniposide （4.8 mg·L^-1）， baicalin （3 mg·L^-1）， and berberine （6 mg·L^-1）. The monomer combination group consisted of all three active constituents dissolved together. LPS and HLJD or its active constituents did not affect cell viability compared with the blank group. LPS significantly increased TNF-α， IL-1β， IL-6， and IL-10 in the supernatant （P<0.01）. HLJD and its active constituents significantly reduced pro-inflammatory factors TNF-α， IL-1β， and IL-6 （P<0.05， P<0.01） while upregulating anti-inflammatory IL-10 （P<0.01）， with the monomer combination showing the strongest effect （P<0.05， P<0.01）. Compared with the blank group， LPS significantly increased the proportion of CD80⁺CD86⁺ （M1-type） BV2 cells （P<0.01）. HLJD and its constituents partially inhibited M1 polarization （P<0.05， P<0.01）， with the monomer combination exhibiting the most pronounced effect （P<0.05， P<0.01）. Compared with the blank group， LPS upregulated HMGB1， TLR4， and NF-κB-related proteins （P<0.01）， whereas HLJD and its active constituents significantly reduced their expression （P<0.05， P<0.01）， with the monomer combination having the strongest regulatory effect （P<0.05， P<0.01）. ConclusionHLJD and its major active constituents （geniposide， baicalin， berberine） can inhibit LPS-induced inflammatory responses in BV2 cells. The combination of the three active constituents demonstrates the most potent anti-inflammatory effect， significantly attenuating M1-type polarization of BV2 cells via the HMGB1/TLR4/NF-κB signaling pathway.

Huanglian Jiedutang （HLJDT）， as a classical formula for clearing heat and removing toxins， has been widely applied in the treatment of various clinical diseases in recent years， particularly during the fire-heat stage of stroke， where it has attracted considerable attention. Based on previous studies， this paper systematically elaborates on the research progress on the active components of HLJDT， its clinical application in ischemic stroke， and advances in studies on its mechanisms of action. Modern pharmacological studies have demonstrated that HLJDT contains multiple active components， including baicalin， geniposide， and berberine. In the treatment of ischemic stroke， these components exert therapeutic effects through multi-target， multi-pathway， and multi-level mechanisms. Clinical studies have shown that HLJDT can increase cerebral blood flow， reduce cerebral infarct volume， and improve post-stroke physical dysfunction in patients with ischemic stroke. Experimental studies have indicated that HLJDT can improve neurological function scores and increase cerebral perfusion in experimental stroke models. In addition， the mechanisms underlying the anti-ischemic stroke effects of HLJDT may be related to anti-inflammatory and antioxidant activities， promotion of angiogenesis， and regulation of amino acid and energy metabolism. Although existing studies have confirmed that HLJDT exhibits multi-target and multi-pathway synergistic therapeutic characteristics， further large-sample randomized controlled trials are still needed to verify its long-term efficacy and to further elucidate the dynamic interaction network among components， targets， and pathways. Combined with network pharmacology and molecular docking analyses， this study further clarifies the synergistic targets of the core components （berberine， baicalin， and geniposide）， providing a theoretical basis for in-depth research and clinical translation of HLJDT in the treatment of ischemic stroke.

The crystalline lens of the eye is recognized as one of the most radiosensitive tissues in the human body. While the International Commission on Radiological Protection (ICRP) has classified ionizing radiation (IR)-induced cataracts as a tissue reaction (deterministic effect) and subsequently reduced the occupational equivalent dose limit for the lens, significant uncertainties remain regarding the precise dose threshold and the complex biological pathways driving lens opacification. This review provides a comprehensive synthesis of current knowledge concerning radiation-induced lens damage, integrating epidemiological exposure characteristics with dose-response modeling and mechanistic molecular insights. First, we analyze exposure characteristics through four epidemiological dimensions: dose, time, space, and population. Clinical evidence suggests that radiation cataracts—particularly posterior subcapsular opacities—exhibit a distinct latency period that is inversely correlated with dose. We highlight that risk is not confined to acute high-dose scenarios (such as in atomic bomb survivors) but is increasingly relevant in chronic low-dose occupational settings (e.g., interventional radiology) and medical diagnostics (e.g., CT scans). Crucially, individual susceptibility is modified by genetic background, age, and environmental co-factors, complicating risk assessment. Second, we critically examine the dose-effect relationship. Although the ICRP suggests a threshold of 0.5 Gy, emerging data challenge the traditional threshold model, with some studies advocating for a linear non-threshold (LNT) relationship. We further discuss the critical roles of radiation quality and dose rate. High linear energy transfer (LET) radiation demonstrates a significantly higher relative biological effectiveness (RBE) for cataractogenesis compared to low-LET radiation. Paradoxically, and unlike many other tissues, the lens may exhibit an “inverse dose-rate effect,” where fractionated or protracted exposures potentially enhance biological damage—a finding that challenges classical radiobiological paradigms. Third, drawing upon the “cataractogenic load” hypothesis and the unique physiological constraints of the lens, this review elucidates the multidimensional molecular mechanisms driving radiation-induced opacification. Key mechanisms include four aspects. (1) DNA damage and repair: IR induces DNA double-strand breaks (DSBs) that, due to the lens’ limited repair capacity (modulated by genes such as ATM, Ptch1, and Ercc2), lead to the accumulation of damage. (2) Antioxidant defense system: dysfunction of the Nrf2/HO-1 antioxidant axis results in redox imbalances, triggering NF-κB-mediated inflammation and protein aggregation. (3) Cell proliferation and senescence: IR disrupts cell cycle regulation, causing a dichotomy of effects—driving premature senescence in some cell populations (evidenced by ATM nuclear foci) while inducing aberrant proliferation via growth factor upregulation (FGF2, TGFβ) in others. (4) Cell migration and adhesion: activation of the Wnt/β‑catenin pathway and alterations in the E-cadherin complex promote the abnormal migration of epithelial cells to the posterior capsule, a hallmark of radiation-induced cataracts. In conclusion, radiation-induced cataractogenesis is a multifactorial process in which genetic susceptibility and environmental stressors converge to overwhelm the lens’ homeostatic thresholds. Future research must prioritize longitudinal cohort studies to refine dose thresholds and employ multi-omics approaches to map the crosstalk between DNA damage responses and matrix remodeling. Establishing a robust mechanistic model is essential for developing targeted radioprotective strategies and optimizing radiation protection standards for occupational and medical safety.

OBJECTIVE: To investigate the association between ABO blood types and gestational diabetes mellitus (GDM) risk. METHODS: A prospective birth cohort study was conducted. ABO blood types were determined using the slide method. GDM diagnosis was based on a 75-g, 2-h oral glucose tolerance test (OGTT) according to the criteria of the International Association of Diabetes and Pregnancy Study Groups. Logistic regression was applied to calculate the odds ratios ( ORs) and 95% confidence intervals ( CIs) between ABO blood types and GDM risk. RESULTS: A total of 30,740 pregnant women with a mean age of 31.81 years were enrolled in this study. The ABO blood types distribution was: type O (30.99%), type A (26.58%), type B (32.20%), and type AB (10.23%). GDM was identified in 14.44% of participants. Using blood type O as a reference, GDM risk was not significantly higher for types A ( OR = 1.05) or B ( OR = 1.04). However, women with type AB had a 19% increased risk of GDM ( OR = 1.19, 95% CI = 1.05-1.34; P < 0.05), even after adjusting for various factors. This increased risk for type AB was consistent across subgroup and sensitivity analyses. CONCLUSION The ABO blood types may influence GDM risk, with type AB associated with a higher risk. Incorporating it-either as a single risk factor or in combination with other known factors-could help identify individuals at risk for GDM before or during early pregnancy.
Humans ; Female ; Pregnancy ; Diabetes, Gestational/etiology* ; ABO Blood-Group System ; Adult ; Prospective Studies ; Risk Factors ; Young Adult

Objective:To investigate the role of mechanosensor Yes-associated protein 1 (YAP1) in urothelial cells in inducing bladder dysfunction in a partial bladder outlet obstruction (pBOO) model.Methods:Ten female C57BL/6 mice were included in this study and randomly divided into pBOO and sham groups based on body weight using a stratified pairing method, with 5 mice in each group. The pBOO group underwent proximal urethral ligation surgery, while the sham group underwent a sham operation. Two weeks after surgery, the urinary pattern was analyzed using the urine spot test. The significant increase in urine spot numbers indicated the successful establishment of the pBOO model. The mice were then sacrificed, and bladder tissues were weighed and stained with hematoxylin and eosin (HE) to observe morphological changes. The bladder urothelial layer was further isolated, and total cell proteins were extracted to detect the expression levels of YAP1 protein using Western blotting. Mouse immortalized bladder urothelial cells were divided into three experimental groups: the negative control (NC) group, which was treated with YAP1-NC lentivirus; the overexpression (OE) group, which was treated with YAP1-OE lentivirus to induce YAP1 protein overexpression; and the verteporfin treatment (VP) group, which was treated with verteporfin on the basis of the OE group. Real-time quantitative PCR and Western blotting were used to verify the transcription and expression levels of YAP1 protein, the co-transcriptional activator TEAD4 protein, and the phosphorylated protein DRP1-616 (at serine 616) of dynamin-related protein 1 (DRP1). An ATP detection kit was used to measure the ATP release concentration in the NC, OE, and VP groups. The interaction between YAP1 and TEAD4 was investigated using co-immunoprecipitation, and the expression of the mitochondrial marker translocase of the outer mitochondrial membrane 20 (Tom20) was observed using immunofluorescence staining.Results:The results of the urine spot test showed that the number of urine spots on the filter paper in the pBOO group was higher than that in the sham group within 6 hours [(283.0±9.1) spots vs. (3.7±0.3) spots, P<0.01], and the urine spots were scattered. The bladder wet weight in the pBOO group was significantly higher than that in the sham group [(105.70±6.84) mg vs. (22.33±1.20) mg, P<0.01]. Histological observations revealed reduced bladder mucosal folds and increased detrusor muscle thickness in the pBOO group. The expression of YAP1 protein in the bladder urothelial cells of the pBOO group was significantly upregulated compared to the sham group [(1.26±0.08) vs. (0.50±0.04), P<0.01]. In vitro experiments showed that compared to the NC group, the OE group had significantly increased expression of DRP1-616 [(0.94±0.05) vs. (0.33±0.01), P<0.01] and higher ATP release concentration [(24.45±0.16) μmol/mg vs. (19.67±0.42) μmol/mg, P<0.01]. In contrast, the VP group had significantly decreased expression of DRP1-616 [(0.29±0.04) vs. (0.94±0.05), P<0.01] and lower ATP release concentration [(10.55±0.01) μmol/mg vs. (24.45±0.16) μmol/mg, P<0.01] compared to the OE group. Co-immunoprecipitation experiments using YAP1 and TEAD4 antibodies showed that YAP1 and TEAD4 proteins could interact and form a transcriptional complex to regulate ATP release. Immunofluorescence staining revealed increased expression of Tom20 in the OE group compared to the NC group [(104.20±3.28) vs. (74.51±3.87), P<0.01]. Conclusions:In the pBOO-induced bladder dysfunction model, YAP1 is highly expressed in urothelial cells. YAP1 forms a transcriptional complex with TEAD4 to regulate ATP release by promoting mitochondrial fission via DRP1-616 expression, which is a key mechanism underlying pBOO-induced bladder dysfunction.

Objective:To identify risk factors associated with endoscopic atrophic progression of gastric mucosa after Helicobacter pylori ( HP) eradication and to develop a risk scoring system for establishing an individualized endoscopic follow-up strategy for patients with chronic gastritis. Methods:This retrospective cohort study included chronic gastritis patients with successful HP eradication at the Department of Gastroenterology, Beijing Friendship Hospital between January 2018 and October 2021. Demographic characteristics, endoscopic findings, and other clinical data were analyzed. Endoscopic outcomes of gastric mucosal atrophy before and after follow-up were compared to classify patients into progression and non-progression groups. Univariate and multivariate analyses were performed to identify independent risk factors for endoscopic atrophic progression. A risk scoring system was then constructed based on these factors. Results:A total of 218 patients with chronic gastritis were included, including 153 in the non-progression group and 65 in the progression group. Multivariate logistic regression analysis showed that gastric ulcer ( P=0.008, OR=4.24, 95% CI: 1.46-12.25), history of proton pump inhibitor use ( P=0.007, OR=4.06, 95% CI: 1.46-11.27), alcohol consumption ( P=0.002, OR=3.77, 95% CI: 1.64-8.67), high-salt diet ( P=0.008, OR=2.90, 95% CI: 1.32-6.41), and high red meat intake ( P=0.025, OR=2.33, 95% CI: 1.11-6.31) were independent risk factors for endoscopic atrophic progression after HP eradication. The predictive model based on these 5 factors demonstrated strong discriminative capacity, with an area under the receiver operating characteristic curve of 0.813 (95% CI: 0.755-0.876, P<0.001). The optimal cut-off value was 1.5 points, stratifying patients into low-risk (0-2 points) and high-risk (3-5 points) groups. Conclusion:Patients with chronic gastritis remain susceptible to progression even after successful HP eradication. Individualized endoscopic follow-up strategies should be considered based on patients' medical history, medication use, lifestyle, and dietary habits.

Objective To explore the roles of the mechanoreceptor Yes-associated protein 1(YAP1)and piezo type mechanosensitive ion channel component 2(PIEZO2)in mechanotransduction in mouse bladder urothelial cells.Methods Mouse bladder urothelial cells were subjected to mechanical stretching using the FX-6000T cell stretching system and treated with the YAP1-specific inhibitor verteporfin(VP).The expressions of PIEZO2,YAP1 and connective tissue growth factor(CTGF)at the mRNA and protein levels,as well as changes in cellular adenosine triphosphatase(ATP)concentration,were detected using reverse transcription quantitative PCR(RT-qPCR)and Western blotting(WB).Results After stretching stimulation,under the fluorescence microscope,it was observed that the diameter length of the stretched cells were longer than that before stretching,and the difference was statistically significant(P＜0.05).The expressions of YAP1,PIEZO2 and CTGF at the mRNA and protein levels were increased in the stretched group compared to those of the non-stretched group(P＜0.05).VP effectively reduced the expressions of YAP1,PIEZO2 and CTGF at the mRNA and protein levels after stretching stimulation(P＜0.05).Stretching stimulation significantly increased the intracellular ATP concentration,while VP was able to inhibit the increase in ATP concentration,with a statistically significant difference(P＜0.000 1).Conclusion Stretching stimulation increased the expressions of YAP1 and PIEZO2 in bladder urothelial cells and promoted the release of ATP;verteporfin inhibited the increase in YAP1 activity and the overexpression of PIEZO2 caused by stretching,thereby reducing the release of ATP.It is suggested that mouse bladder urothelial cells may primarily sense mechanical signals through the YAP1-PIEZO2-ATP pathway.

Objective To propose a novel identification algorithm based on ensemble learning for assessing the severity of acute respiratory distress syndrome(ARDS)to achieve continuous monitoring of the disease severity.Methods Firstly,leve-raging the open-source MIMIC-Ⅳ database,a variety of non-invasive physiological parameters of patients were extracted and subjected to preliminary preprocessing.A multivariate feature selection algorithm was employed to rank these parameters and calculate feature importance scores through weighted computation.Secondly,based on the feature importance scores,a subset search algorithm was utilized to identify the subset of features that could yield optimal performance across four machine learning algorithms:neural networks,logistic regression,AdaBoost and XGBoost.Finally,a soft voting ensemble method was designed using a generalized linear regression model to integrate the results of each single machine learning algorithm,and a multivariate ensemble learning algorithm was proposed by combining the optimal feature subsets.The algorithm proposed when used to identify the severity of ADRS was evaluated with MIMIC-Ⅳ database,and compared with the traditional algorithms.Results The sensitivity,specificity,accuracy and AUC of the algorithm were 87.15％,89.23％,88.34％and 0.923 4,respectively,all of which outperformed those of the traditional algorithms.Conclusion The ARDS severity identification algorithm based on ensemble learning is capable of achieving continuous and real-time monitoring of the severity of ARDS,thereby offering robust support for the early identification and warning of ARDS in patients.[Chinese Medical Equipment Journal,2025,46(2):1-9]