1.Phlorizin Ameliorates Glucose and Lipid Metabolism Disorders in T2DM Rats by Modulating IRS-1/PI3K/Akt Signaling Pathway
Nuer AILI ; Qingyu CAO ; Huan LIU ; Junwei HE ; Weihong ZHONG ; Lan CAO
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):139-148
ObjectiveTo observe the pharmacodynamic efficacy of phlorizin in improving hepatic glycolipid metabolism disorders in type 2 diabetic mellitus (T2DM) rats and to explore its mechanism of action based on the insulin receptor substrate-1 (IRS-1)/phosphatidylinositol 3-kinase (PI3K)/protein kinase B (Akt) signaling pathway. MethodsA high-fat diet and streptozotocin (STZ) were used to establish T2DM rat models. The rats were randomly assigned into six groups: the blank control group, model group, metformin group (300 mg·kg-1), and phlorizin high-dose (100 mg·kg-1) and low-dose groups (25 mg·kg-1). The rats were given intragastric administration for 6 weeks. The changes in body weight and fasting blood glucose (FBG) were observed, and the oral glucose tolerance test (OGTT) was carried out. The levels of total cholesterol (TC), triglyceride (TG), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), glycated serum protein (GSP), aspartate aminotransferase (AST), and alanine aminotransferase (ALT) in serum were detected by an automatic biochemical analyzer. The levels of fasting insulin (FINS), interleukin (IL)-1β, IL-6, and tumour necrosis factor (TNF)-α were detected by enzyme-linked immunosorbent assay (ELISA). The levels of superoxide dismutase (SOD) and malondialdehyde (MDA) were detected by the biochemical assays. The pancreas index, liver index, and insulin resistance index were calculated. Hematoxylin-eosin (HE) staining was used to evaluate the pathological changes in liver and pancreatic tissues. The immunofluorescence method was used to detect the changes in insulin and glucagon in pancreatic tissue. Western blot was used to detect the expression of related proteins in the IRS-1/PI3K/Akt pathway of liver tissue and its downstream glycogen synthase kinase-3β (GSK-3β) and forkhead box transcription factor O1 (FoxO1) proteins. ResultsCompared with the blank control group, the body weight of rats in the model group continued to decrease, while the FBG level increased significantly. The area under the OGTT blood glucose curve (AUC), GSP, TC, TG, LDL-C, IL-1β, IL-6, TNF-α, MDA, pancreatic index and liver index increased significantly, while the levels of HDL-C, SOD, and FINS decreased significantly (P0.05, P0.01). Histological results showed that the pancreatic islets of rats in the model group exhibited atrophy and severe structural abnormalities. The insulin-positive β-cells decreased significantly (P0.01), while the glucagon-positive α-cells increased significantly (P0.01). Inflammatory cell infiltration and partial necrosis were observed in the liver tissues of the model group rats. The expressions of p-IRS-1/IRS-1, p-GSK-3β/GSK-3β, and p-FoxO1/FoxO1 proteins in the liver of the model group increased significantly (P0.01), while the expressions of p-PI3K/PI3K and p-Akt/Akt proteins decreased significantly (P0.01). Compared with the model group, the diabetic symptoms of rats in all administration groups were improved. The changes in body weight and FBG were close to those of the blank control group. The levels of OGTT-AUC, GSP, TC, TG, LDL-C, MDA, IL-1β, IL-6, TNF-α and the pancreatic index, liver index were obviously reduced (P0.05, P0.01), while the levels of HDL-C, SOD, and FINS obviously increased (P0.05, P0.01). The pathological changes of the pancreas and liver in rats in all treatment groups were effectively improved. The insulin-positive β-cells in the pancreas increased significantly (P0.01), while the glucagon-positive α-cells decreased significantly (P0.01). The protein expressions of p-IRS-1/IRS-1, p-GSK-3β/GSK-3β, and p-FoxO1/FoxO1 in the liver were significantly reduced (P0.01), while the protein expressions of p-PI3K/PI3K and p-Akt/Akt significantly increased (P0.01). ConclusionPhlorizin reversed the weight loss and abnormal increase of FBG in T2DM rats, improved blood lipid profiles, oxidative stress, and inflammatory levels, alleviated insulin resistance, and had certain protective effects on the liver and pancreas. The hypoglycemic mechanism may involve regulating the IRS-1/PI3K/Akt signaling pathway to inhibit the activities of GSK-3β and FoxO1, thereby promoting liver glycogen synthesis and suppressing hepatic gluconeogenesis, ultimately improving glycolipid metabolism disorders.
2.Phlorizin Ameliorates Glucose and Lipid Metabolism Disorders in T2DM Rats by Modulating IRS-1/PI3K/Akt Signaling Pathway
Nuer AILI ; Qingyu CAO ; Huan LIU ; Junwei HE ; Weihong ZHONG ; Lan CAO
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):139-148
ObjectiveTo observe the pharmacodynamic efficacy of phlorizin in improving hepatic glycolipid metabolism disorders in type 2 diabetic mellitus (T2DM) rats and to explore its mechanism of action based on the insulin receptor substrate-1 (IRS-1)/phosphatidylinositol 3-kinase (PI3K)/protein kinase B (Akt) signaling pathway. MethodsA high-fat diet and streptozotocin (STZ) were used to establish T2DM rat models. The rats were randomly assigned into six groups: the blank control group, model group, metformin group (300 mg·kg-1), and phlorizin high-dose (100 mg·kg-1) and low-dose groups (25 mg·kg-1). The rats were given intragastric administration for 6 weeks. The changes in body weight and fasting blood glucose (FBG) were observed, and the oral glucose tolerance test (OGTT) was carried out. The levels of total cholesterol (TC), triglyceride (TG), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), glycated serum protein (GSP), aspartate aminotransferase (AST), and alanine aminotransferase (ALT) in serum were detected by an automatic biochemical analyzer. The levels of fasting insulin (FINS), interleukin (IL)-1β, IL-6, and tumour necrosis factor (TNF)-α were detected by enzyme-linked immunosorbent assay (ELISA). The levels of superoxide dismutase (SOD) and malondialdehyde (MDA) were detected by the biochemical assays. The pancreas index, liver index, and insulin resistance index were calculated. Hematoxylin-eosin (HE) staining was used to evaluate the pathological changes in liver and pancreatic tissues. The immunofluorescence method was used to detect the changes in insulin and glucagon in pancreatic tissue. Western blot was used to detect the expression of related proteins in the IRS-1/PI3K/Akt pathway of liver tissue and its downstream glycogen synthase kinase-3β (GSK-3β) and forkhead box transcription factor O1 (FoxO1) proteins. ResultsCompared with the blank control group, the body weight of rats in the model group continued to decrease, while the FBG level increased significantly. The area under the OGTT blood glucose curve (AUC), GSP, TC, TG, LDL-C, IL-1β, IL-6, TNF-α, MDA, pancreatic index and liver index increased significantly, while the levels of HDL-C, SOD, and FINS decreased significantly (P0.05, P0.01). Histological results showed that the pancreatic islets of rats in the model group exhibited atrophy and severe structural abnormalities. The insulin-positive β-cells decreased significantly (P0.01), while the glucagon-positive α-cells increased significantly (P0.01). Inflammatory cell infiltration and partial necrosis were observed in the liver tissues of the model group rats. The expressions of p-IRS-1/IRS-1, p-GSK-3β/GSK-3β, and p-FoxO1/FoxO1 proteins in the liver of the model group increased significantly (P0.01), while the expressions of p-PI3K/PI3K and p-Akt/Akt proteins decreased significantly (P0.01). Compared with the model group, the diabetic symptoms of rats in all administration groups were improved. The changes in body weight and FBG were close to those of the blank control group. The levels of OGTT-AUC, GSP, TC, TG, LDL-C, MDA, IL-1β, IL-6, TNF-α and the pancreatic index, liver index were obviously reduced (P0.05, P0.01), while the levels of HDL-C, SOD, and FINS obviously increased (P0.05, P0.01). The pathological changes of the pancreas and liver in rats in all treatment groups were effectively improved. The insulin-positive β-cells in the pancreas increased significantly (P0.01), while the glucagon-positive α-cells decreased significantly (P0.01). The protein expressions of p-IRS-1/IRS-1, p-GSK-3β/GSK-3β, and p-FoxO1/FoxO1 in the liver were significantly reduced (P0.01), while the protein expressions of p-PI3K/PI3K and p-Akt/Akt significantly increased (P0.01). ConclusionPhlorizin reversed the weight loss and abnormal increase of FBG in T2DM rats, improved blood lipid profiles, oxidative stress, and inflammatory levels, alleviated insulin resistance, and had certain protective effects on the liver and pancreas. The hypoglycemic mechanism may involve regulating the IRS-1/PI3K/Akt signaling pathway to inhibit the activities of GSK-3β and FoxO1, thereby promoting liver glycogen synthesis and suppressing hepatic gluconeogenesis, ultimately improving glycolipid metabolism disorders.
3.LC-MS Analysis on Material Basis of Famous Classical Formula Xuefu Zhuyutang
Shujing ZHONG ; Zhaoyue LIU ; Mengge WANG ; Lan MIAO ; Changying REN ; Mingqian SUN ; Li LIN
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(6):188-196
ObjectiveTo systematically identify the chemical constituents of Xuefu Zhuyutang(XFZY) and quantitatively determine its main components, aiming to elucidate its pharmacodynamic material basis and provide a scientific foundation for improving its quality control standards. MethodsUltra-performance liquid chromatography-quadrupole-time-of-flight mass spectrometry(UPLC-Q-TOF-MS/MS) was employed for qualitative analysis of XFZY, and the identification of compounds was accomplished by comparing their retention times, secondary MS fragment ion information, 52 reference standards and relevant databases, followed by attribution of their herbal sources. A total of 22 representative compounds were screened out, and UPLC-quadrupole-linear ion trap mass spectrometry(UPLC-Q-TRAP-MS/MS) was applied for quantitative analysis of the compounds in the formula. ResultsA total of 77 compounds were identified in XFZY, including 31 flavonoids mainly derived from Aurantii Fructus, Glycyrrhizae Radix et Rhizoma, Persicae Semen, Carthami Flos, Bupleuri Radix, Paeoniae Radix Rubra and Achyranthis Bidentatae Radix, 24 terpenoids mainly derived from Platycodonis Radix, Glycyrrhizae Radix et Rhizoma, Paeoniae Radix Rubra and Rehmanniae Radix, 9 phenylpropanoids and their derivatives mainly derived from Chuanxiong Rhizoma, Angelicae Sinensis Radix and Rehmanniae Radix, 4 phenolic acids mainly derived from Chuanxiong Rhizoma, Angelicae Sinensis Radix and Paeoniae Radix Rubra, 3 saccharides mainly derived from Rehmanniae Radix and Achyranthis Bidentatae Radix, and 6 other compounds mainly derived from Persicae Semen, Rehmanniae Radix and Angelicae Sinensis Radix. The results of quantitative analysis showed that the contents of protocatechuic acid, hydroxypaeoniflorin, amygdalin, vanillic acid, paeoniflorin, liquiritin apioside, liquiritin, isoquercitrin, naringin, cosmosiin, hesperidin, neohesperidin, isoliquiritin, liquiritigenin, naringenin, benzoylpaeoniflorin, hesperetin, isoliquiritigenin, formononetin, glycyrrhizic acid, nobiletin and ligustilide in XFZY were determined to be 0.12, 1.57, 54.53, 0.29, 36.17, 4.29, 4.84, 0.09, 46.67, 0.04, 3.44, 31.95, 0.82, 0.10, 0.11, 0.43, 0.07, 0.03, 0.01, 8.24, 0.13, 1.81 mg·g-1. ConclusionThe qualitative method established in this study enables rapid and sensitive analysis of the chemical constituents in XFZY. Among the identified compounds, 52 are confirmed by reference standards, ensuring the accuracy of identification. The quantitative analysis of 22 key components provides a reliable experimental basis for the pharmacodynamic material basis research and quality control standard improvement of XFZY.
4.Research progress on multidimensional impacts of climate change on nursing practice and adaptation strategies
Zerun ZHAO ; Yumeng LAN ; Juanping ZHONG ; Xinglei WANG ; Xinman DOU
Journal of Environmental and Occupational Medicine 2026;43(2):247-252
Climate change has evolved from an environmental issue into a global public health crisis, posing severe challenges to healthcare systems. Issues such as shifts in patient disease patterns, increased care demands for vulnerable populations, and insufficient resilience in nursing systems are becoming increasingly prominent. As the frontline of healthcare delivery, nursing practice directly confronts multiple health risks triggered by climate change. Under the Healthy China 2030 strategy, the role of nursing in addressing climate change cannot be overlooked. Therefore, this paper systematically reviewed the impacts of climate change on nursing practice and corresponding domestic and international strategies, and proposed recommendations for localized development pathways. First, strengthen climate health literacy in nursing education by integrating the climate change system into curricula and clinical practice. Second, promote nursing policy participation in global health governance to establish a climate-adaptive nursing policy system with Chinese characteristics. Finally, establish a multidisciplinary nursing research framework to foster integration among nursing science, climate science, public health, traditional Chinese medicine, and other relevant fields. This paper aims to provide theoretical foundations for constructing a climate-adaptive nursing system with Chinese characteristics, thereby advancing the coordinated development of Healthy China initiative and climate governance.
5.Roles of plant-derived natural compounds in the prevention and treatment of osteoporosis
Ziyi DUAN ; Wenhao ZHOU ; Yingjie CAI ; Min ZHONG ; Jian MAO ; Lan JIANG
Science of Traditional Chinese Medicine 2026;4(1):33-39
Osteoporosis is a systemic disease, and epidemiological projections indicate that by 2050, approximately 23.43% of the Chinese population over 50 years of age will be affected. Given the poor prognosis associated with osteoporosis, the exploration of safe and effective natural products is of considerable significance. Studies investigating the chemical constituents of traditional Chinese medicine in cellular and/or animal models have demonstrated bone-protective effects. Although most of these compounds lack clinical data, they hold considerable potential as lead candidates for drug development. In-depth study of the structure-activity relationship of these natural products not only contributes to elucidating the mechanisms of action but also provides a theoretical basis for the development of novel antiosteoporosis therapies. This review summarizes natural products with potential antiosteoporotic effects reported between 2020 and 2024. Overall, plant-derived natural compounds exhibit antiosteoporotic effects by regulating bone remodeling, inflammation, and oxidative stress, highlighting their promise as multitarget therapeutic candidates.
6.Dissecting antibody-mediated natural killer cell effects reveals a cytotoxic CX3CR1+KLRC2–CD16hi subset linked to hepatitis B virus outcomes
Libo TANG ; Yuhao WANG ; Zihan JIN ; Yurong GU ; Zhaofeng ZENG ; Linnan SONG ; Xuan YI ; Lingtao ZHANG ; Yujing ZHANG ; Weiying HE ; Liping WANG ; Weixin HE ; Jianru SUN ; Xiaoqin LAN ; Xiangyong LI ; Shihong ZHONG ; Yongyin LI
Clinical and Molecular Hepatology 2026;32(2):683-705
Background/Aims:
Natural killer (NK) cell function is generally considered dampened in chronic hepatitis B virus (HBV) infection; however, the NK cell pool exhibits phenotypic and functional heterogeneity, and the antibody--mediated effect of NK cells remains less characterized. This study evaluated the dynamic changes in antibody-mediated NK cell responses and the involvement of distinct NK subsets across disease stages and during antiviral treatment.
Methods:
A T-cell receptor-like antibody specific for the HBV core 18–27 peptide (cTCRL-Ab) was used to determine the antibody-mediated effect of NK cells, and an array of NK cell surface markers were analyzed in cross-sectional and longitudinal cohorts of patients with chronic HBV infection. Single-cell RNA sequencing (scRNA-seq) was performed to identify the heterogeneity of NK subsets.
Results:
The cTCRL-Ab enabled the detection of NK cell cytolytic activity and IFNγ production. Notably, cTCRL-Ab-mediated NK cell responses were compromised in chronically HBV-infected patients, particularly in those receiving pegylated interferon-α (Peg-IFNα), which was associated with the downregulation of CD16 expression. Correspondingly, Peg-IFNα inhibited cTCRL-Ab-mediated NK cell function by reducing CD16 expression in vitro. scRNA-seq revealed that CD16 downregulation occurred mainly within a dysfunctional CD16hi NK subset exhibiting exhaustion properties. In contrast, an activated CD16hiNK subpopulation (CX3CR1⁺KLRC2–CD16hi) with high cytotoxicity was enriched in patients who experienced favorable treatment responses. Furthermore, the intrahepatic CX3CR1+KLRC2–CD16hi subset tended to exhibit functional restoration in HBsAg-loss individuals.
Conclusions
Our data contribute to the understanding of antibody-mediated responses of NK cells in chronic HBV infection, and highlight a previously unappreciated functional CX3CR1+KLRC2–CD16hiNK subset as a potential therapeutic target.
7.Study the effect of rhGM-CSF combined with bifidobacterium treating on stomatitis after chemotherapy
Qinghua LAN ; Qingfang ZENG ; Wei XIAO ; Tao ZHAN ; Jianming ZHONG ; Liujin QIU
China Modern Doctor 2025;63(23):50-53
Objective To investigate the clinical efficacy of recombinant human granulocyte-macrophage colony-stimulating factor(rhGM-CSF)combined with bifidobacterium in the treatment of oral mucositis after chemotherapy.Methods A total of 60 post-chemotherapy patients with oral mucositis admitted to Ganzhou Cancer Hospital of Jiangxi Province from January 2023 to December 2024 were selected as subjects,the patients were divided into observation group(n=30)and control group(n=30)by using a randomized digital table method.The control group received rhGM-CSF mouthwash treatment,while the observation group was additionally administered bifidobacterium-lactobacillus triple live capsules orally.Clinical efficacy,symptom scores,inflammatory factor levels,oral microbiota indicators,and treatment safety were evaluated after 2 weeks of treatment.Results After treatment,the total effective rate in observation group was significantly higher than that in control group(P<0.05).Post-treatment evaluations showed that patients in observation group exhibited lower scores for edema,congestion,and ulceration,along with reduced pain visual analog scores and decreased levels of inflammatory markers including Toll-like receptor 4,lectin-3,and interleukin-8,the difference were statistically significant(P<0.05).After treatment,the oral microecological flora of patients in observation group,including lactic acid bacteria and bifidobacterium,were higher than that of control group,while porphyromonas gingivalis and fusetella were lower than that of control group,the difference were statistically significant(P<0.05).Conclusion The clinical effect of rhGM-CSF combined with bifidobacterium in the treatment of oral mucositis after chemotherapy was significant,which could reduce various symptoms of patients,inhibit inflammatory factors,improve oral microecology,and have good safety.
8.The prognostic value of TNM stage and L3-skeletal muscle mass index combined score in elderly patients with colorectal cancer
Wenbin LI ; Wanling CHEN ; Qinfen LAN ; Wei ZHONG ; Zhipeng QUE ; Dongbo XU
Chinese Journal of Geriatrics 2025;44(3):324-329
Objective:We study the prognostic value of TNM stage and L3-skeletal muscle mass index in overall survival(OS)in elderly patients with colorectal cancer after surgery.Furthermore, investigate the prognostic value of combined scoring system(TNM-SMI score)in patients with colorectal cancer.Methods:From January 1, 2018 to January 31, 2019, the clinical data of elderly patients who were diagnosed with colorectal cancer for the first time in Longyan First Hospital, Fujian Medical University were retrospectively analyzed.The baseline data were compared in patients with different TNM stage and L3SMI.The relevant factors that might affect the prognosis of the patients were analyzed to determine the independent risk factors in cox regression analyses.Survival curves were plotted by using the Kaplan-Meier method, and Log-rank test was used to compare Overall Survival.Predictive efficacy was compared by plotting (ROC)curve and calculating the area under the curve(AUC).Results:A total of 128 eligible patients aged 65-88(73.96±6.20)years were enrolled.Among them, 82 were male.Univariate and multifactorial cox regression analyses showed that TNM stage( HR=3.944, 95% CI: 1.519-10.237, P<0.05)and L3SMI( HR=3.194, 95% CI: 1.222-8.349, P<0.05)were the independent risk factors for OS in elderly colorectal cancer patients; Survival curves plotted by Kaplan-Meier method showed that the 5-year survival rate(OS rate)of patients in TNM(Ⅲ and Ⅳ)group was lower than in TNM(Ⅰ and Ⅱ)group(58.8% vs.88.9%, P<0.001), and the 5-year survival rate(OS rate)of patients in low L3SMI group was lower than in high L3SMI group(51.0% vs.88.3%, P<0.001); Elderly colorectal patients were risk stratified by TNM-SMI score, the patients with higher score had worse 5-year OS rate; The AUC of L3SMI, TNM stage, and TNM-SMI score are 0.729, 0.695, and 0.800. Conclusions:The TNM stage and L3SMI are independent risk factors of OS after colorectal cancer surgery; TNM-SMI score, which combines TNM stage and L3SMI, can predict prognosis more efficiency compare to single-factor.The higher TNM-SMI score had the worse prognosis; TNM stage in combination with L3SMI improves the efficiency prediction of OS after colorectal cancer surgery.
9.Latent profile analysis of psychosocial adaptation among young and middle-aged stroke patients and its relationship with quality of life
Jiaxuan LI ; Xi PAN ; Lan XU ; Zhi WANG ; Weiying ZHONG ; Yi ZHANG ; Lei CHEN ; Lin YAO
Chinese Journal of Nursing 2025;60(15):1843-1849
Objective To explore the different potential subtypes of psychosocial adaptation among young and middle-aged stroke patients,and analyze the relationship between different potential subtypes and quality of life,so as to provide references for the subsequent development of targeted interventions.Methods A total of 406 young and middle-aged stroke patients in 4 tertiary hospitals in Suzhou from June 2023 to June 2024 were recruited by convenience sampling.The General Information Questionnaire,the Self-Report Psychosocial Adjustment to Illness Scale and the EuroQol five-dimensional questionnaire were conducted for investigation.Latent profile analysis was used to explore the potential subtypes of psychosocial adaptation among young and middle-aged stroke patients.Generalized linear regression analysis was conducted with quality of life as dependent variables.Results A total of 380 young and middle-aged stroke patients were included.The psychosocial adaptation of patients could be classified into 3 potential subtypes:high adaptation level type(23.90%),medium adaptation level with health concerns type(46.40%),and low adaptation level with psychological barriers type(29.70%).The results of generalized linear regression analysis showed that potential subtypes of psychosocial adaptation were the influencing factors for quality of life in young and middle-aged stroke patients(P<0.05).Conclusion There was group heterogeneity in psychosocial adaptation among young and middle-aged stroke patients,and the potential subtype of psychosocial adaption was an important factor affecting the quality of life of patients.It is suggested that medical staff should focus on patients with low adaptation level with psychological barriers type,and take targeted interventions according to characteristics of different subtypes of patients,so as to improve their quality of life.
10.Explainable machine learning model for predicting septic shock in critically sepsis patients based on coagulation indexes: A multicenter cohort study.
Qing-Bo ZENG ; En-Lan PENG ; Ye ZHOU ; Qing-Wei LIN ; Lin-Cui ZHONG ; Long-Ping HE ; Nian-Qing ZHANG ; Jing-Chun SONG
Chinese Journal of Traumatology 2025;28(6):404-411
PURPOSE:
Septic shock is associated with high mortality and poor outcomes among sepsis patients with coagulopathy. Although traditional statistical methods or machine learning (ML) algorithms have been proposed to predict septic shock, these potential approaches have never been systematically compared. The present work aimed to develop and compare models to predict septic shock among patients with sepsis.
METHODS:
It is a retrospective cohort study based on 484 patients with sepsis who were admitted to our intensive care units between May 2018 and November 2022. Patients from the 908th Hospital of Chinese PLA Logistical Support Force and Nanchang Hongdu Hospital of Traditional Chinese Medicine were respectively allocated to training (n=311) and validation (n=173) sets. All clinical and laboratory data of sepsis patients characterized by comprehensive coagulation indexes were collected. We developed 5 models based on ML algorithms and 1 model based on a traditional statistical method to predict septic shock in the training cohort. The performance of all models was assessed using the area under the receiver operating characteristic curve and calibration plots. Decision curve analysis was used to evaluate the net benefit of the models. The validation set was applied to verify the predictive accuracy of the models. This study also used Shapley additive explanations method to assess variable importance and explain the prediction made by a ML algorithm.
RESULTS:
Among all patients, 37.2% experienced septic shock. The characteristic curves of the 6 models ranged from 0.833 to 0.962 and 0.630 to 0.744 in the training and validation sets, respectively. The model with the best prediction performance was based on the support vector machine (SVM) algorithm, which was constructed by age, tissue plasminogen activator-inhibitor complex, prothrombin time, international normalized ratio, white blood cells, and platelet counts. The SVM model showed good calibration and discrimination and a greater net benefit in decision curve analysis.
CONCLUSION
The SVM algorithm may be superior to other ML and traditional statistical algorithms for predicting septic shock. Physicians can better understand the reliability of the predictive model by Shapley additive explanations value analysis.
Humans
;
Shock, Septic/blood*
;
Machine Learning
;
Male
;
Female
;
Retrospective Studies
;
Middle Aged
;
Aged
;
Sepsis/complications*
;
ROC Curve
;
Cohort Studies
;
Adult
;
Intensive Care Units
;
Algorithms
;
Blood Coagulation
;
Critical Illness

Result Analysis
Print
Save
E-mail