1.A machine learning-based model for predicting the risk of diabetic kidney disease in type 2 diabetes mellitus
Tingting LI ; Peng SU ; Jinbo CHEN ; Xiaoyan HE ; Yi CAO ; Xin ZHANG ; Qingling TANG ; Xubin MIAO ; Xiaohua LIANG ; Dong MA
Chinese Journal of Diabetes 2025;33(4):241-247
Objective To compare and find an optimal model for predicting the risk of DKD occurrence in patients with type 2 diabetes mellitus(T2DM).Methods A total of 2005 patients with T2DM were enrolled in this study from The Second Hospital of Shijiazhuang City during December 2017 to December 2022.All the subjects were divided into a training set(n=1403)and a validation set(n=602)according to the ratio of 3∶1 by simple random sampling.With the occurrence of DKD as the outcome variablein the training set,important feature variables were screened by LASSO regression.Six different machine learning models were established according to the feature variables,thenthe optimal model was determined by comparison,and anonlinerisk predictor for DKD occurrence was constructed in patients with T2DM.Results Taking the occurrence of DKD as the outcome variable in the training set,the results of LASSO regression analysis showed that the optimal value of the model was 10-fold cross validation lambda.1se=0.01662473,and 15 characteristic variables with nonzero coefficient were screened out to be related to the occurrence of DKD.The data included sex,age,family history of DM,DM duration,LDL-C,HbA1c,WBC,PDW,Scr,urine α1-microglobulin,urine β2-microglobulin,urine microalbumin,hypertension,hypokalemia,and DR.In the training set and validation set,the prediction performance of XGBoost model was better than that of other models(AUC=0.872,0.893,95%CI 0.853~0.891,0.865~0.921),the sensitivity was 0.779,0.863,and the specificity was 0.721,0.758,respectively.The F1 scores were 0.774 and 0.787.DCA analysis showed that the XGBoost model had a greater net benefit and threshold probability.According to the XGBoost model,the online predictor of DKD risk in T2DM patients was laid out,and two patients were selected for application,the results showed that the predictive value of the model was 0.185 in non-DKD patients,and the predictive value was 0.510 in DKD patients.Conclusions The XGBoost model is the best model for predicting the occurrence of DKD in T2DM patients,and an online predictor was successfully built.
2.A machine learning-based model for predicting the risk of diabetic kidney disease in type 2 diabetes mellitus
Tingting LI ; Peng SU ; Jinbo CHEN ; Xiaoyan HE ; Yi CAO ; Xin ZHANG ; Qingling TANG ; Xubin MIAO ; Xiaohua LIANG ; Dong MA
Chinese Journal of Diabetes 2025;33(4):241-247
Objective To compare and find an optimal model for predicting the risk of DKD occurrence in patients with type 2 diabetes mellitus(T2DM).Methods A total of 2005 patients with T2DM were enrolled in this study from The Second Hospital of Shijiazhuang City during December 2017 to December 2022.All the subjects were divided into a training set(n=1403)and a validation set(n=602)according to the ratio of 3∶1 by simple random sampling.With the occurrence of DKD as the outcome variablein the training set,important feature variables were screened by LASSO regression.Six different machine learning models were established according to the feature variables,thenthe optimal model was determined by comparison,and anonlinerisk predictor for DKD occurrence was constructed in patients with T2DM.Results Taking the occurrence of DKD as the outcome variable in the training set,the results of LASSO regression analysis showed that the optimal value of the model was 10-fold cross validation lambda.1se=0.01662473,and 15 characteristic variables with nonzero coefficient were screened out to be related to the occurrence of DKD.The data included sex,age,family history of DM,DM duration,LDL-C,HbA1c,WBC,PDW,Scr,urine α1-microglobulin,urine β2-microglobulin,urine microalbumin,hypertension,hypokalemia,and DR.In the training set and validation set,the prediction performance of XGBoost model was better than that of other models(AUC=0.872,0.893,95%CI 0.853~0.891,0.865~0.921),the sensitivity was 0.779,0.863,and the specificity was 0.721,0.758,respectively.The F1 scores were 0.774 and 0.787.DCA analysis showed that the XGBoost model had a greater net benefit and threshold probability.According to the XGBoost model,the online predictor of DKD risk in T2DM patients was laid out,and two patients were selected for application,the results showed that the predictive value of the model was 0.185 in non-DKD patients,and the predictive value was 0.510 in DKD patients.Conclusions The XGBoost model is the best model for predicting the occurrence of DKD in T2DM patients,and an online predictor was successfully built.
3.A case of mental retardation-56 caused by the CLTC gene mutation and literature review
Bingbin MAI ; Wenhui MO ; Yi LI ; Qiaowen TU ; Minghao HUANG ; Haojie LIU ; Yun CAO ; Xin XIAO
Chinese Journal of Applied Clinical Pediatrics 2025;40(2):133-137
The clinical data and genetic characteristics of one child with mental retardation-56 (MRD56) diagnosed at the Department of Neonatology, Foshan Fosun Chancheng Hospital in October 2021 were retrospectively analyzed.The patient was admitted to the hospital with " 34 + 2 weeks of preterm birth, shortness of breath, and dyspnea for 0.5 hours". In the neonatal period, the patient had special facial features, hypotonia, weaning and feeding difficulties, laryngeal stridor.In infancy, the patient showed global psychomotor development delay, intellectual disability, epilepsy, etc.Magnetic resonance imaging of the brain showed delayed myelination and dysplasia of the cerebellum and corpus callosum.Whole-exome sequencing showed that the CLTC gene had a new missense mutation c.3334T>C (p.Trp1112Arg), and MRD56 was confirmed.A total of 32 cases of MRD56 were reported worldwide, with special facial features, intellectual disability, and psychomotor retardation as the main clinical manifestations.The cause is a mutation in the CLTC gene, which leads to abnormality in the structure of the clathrin encoded, thus affecting neurotransmitter transmission.This is the first report of MRD56 caused by the CLTC gene mutation in China, and a new clinical phenotype has been discovered.The finding enriches the phenotypic spectrum of the disease and provides a basis for clinicians to understand and study the disease.
4.Analysis of the current status and related factors of antiviral treatment for chronic hepatitis B virus infection in rural communities of Zhangqiu District, Jinan City
Xiaomeng ZHANG ; Bingyu YAN ; Jingjing LYU ; Yi FENG ; Xin MENG ; Chuanzhao CAO ; Li ZHANG
Chinese Journal of Preventive Medicine 2025;59(3):286-291
Objective:To investigate the current status and related factors of antiviral treatment for chronic hepatitis B virus (HBV) infection in rural communities in China.Methods:In 2023, 866 chronic HBV-infected individuals from rural communities in Zhangqiu District, Jinan City, were included in the study. Basic information, disease status and antiviral treatment conditions of the infected individuals were collected through questionnaires, specimen collection and laboratory tests. Univariate and multivariate logistic regression were used to analyze the related factors of the antiviral treatment rate of those who met the indications for hepatitis B antiviral treatment.Results:The median age ( Q1, Q3) of subjects was 56 (48, 66) years old, among which 436 (50.4%) were males. There were 712 (82.2%) individuals who met the indications for hepatitis B antiviral treatment, and 110 individuals received antiviral treatment with a rate of 15.5%. Multivariate logistic regression analysis showed that compared with males, families with an average monthly income per capita of <1 000 yuan, no alcohol consumption, no smoking, and a family history of HBV infection, females ( OR=4.66, 95% CI: 2.88-7.53), families with an average monthly income per capita of 1 000-1 999 yuan ( OR=1.64, 95% CI: 1.00-2.68) and ≥2 000 yuan ( OR=2.78, 95% CI: 1.54-5.03), alcohol consumption ( OR=6.42, 95% CI: 2.80-14.7), smoking ( OR=1.98, 95% CI: 1.04-3.77), and no family history of HBV infection ( OR=1.90, 95% CI: 1.16-3.09) had a lower antiviral treatment rate for chronic HBV infection. Conclusion:The antiviral treatment rate of chronic HBV-infected individuals in rural communities of Zhangqiu District, Jinan City is low, and the related factors are female, high monthly income per capita, alcohol consumption, smoking, and no family history of HBV infection.
5.Analysis of the current status and related factors of antiviral treatment for chronic hepatitis B virus infection in rural communities of Zhangqiu District, Jinan City
Xiaomeng ZHANG ; Bingyu YAN ; Jingjing LYU ; Yi FENG ; Xin MENG ; Chuanzhao CAO ; Li ZHANG
Chinese Journal of Preventive Medicine 2025;59(3):286-291
Objective:To investigate the current status and related factors of antiviral treatment for chronic hepatitis B virus (HBV) infection in rural communities in China.Methods:In 2023, 866 chronic HBV-infected individuals from rural communities in Zhangqiu District, Jinan City, were included in the study. Basic information, disease status and antiviral treatment conditions of the infected individuals were collected through questionnaires, specimen collection and laboratory tests. Univariate and multivariate logistic regression were used to analyze the related factors of the antiviral treatment rate of those who met the indications for hepatitis B antiviral treatment.Results:The median age ( Q1, Q3) of subjects was 56 (48, 66) years old, among which 436 (50.4%) were males. There were 712 (82.2%) individuals who met the indications for hepatitis B antiviral treatment, and 110 individuals received antiviral treatment with a rate of 15.5%. Multivariate logistic regression analysis showed that compared with males, families with an average monthly income per capita of <1 000 yuan, no alcohol consumption, no smoking, and a family history of HBV infection, females ( OR=4.66, 95% CI: 2.88-7.53), families with an average monthly income per capita of 1 000-1 999 yuan ( OR=1.64, 95% CI: 1.00-2.68) and ≥2 000 yuan ( OR=2.78, 95% CI: 1.54-5.03), alcohol consumption ( OR=6.42, 95% CI: 2.80-14.7), smoking ( OR=1.98, 95% CI: 1.04-3.77), and no family history of HBV infection ( OR=1.90, 95% CI: 1.16-3.09) had a lower antiviral treatment rate for chronic HBV infection. Conclusion:The antiviral treatment rate of chronic HBV-infected individuals in rural communities of Zhangqiu District, Jinan City is low, and the related factors are female, high monthly income per capita, alcohol consumption, smoking, and no family history of HBV infection.
6.Potentials of artificial intelligence in revolutionizing clinical laboratory
Chinese Journal of Laboratory Medicine 2025;48(2):172-178
Artificial Intelligence (AI) is rapidly revolutionizing clinical laboratory testing and diagnostics. Through technologies like machine learning and natural language processing, AI enhances diagnostic efficiency and accuracy while providing personalized medical services. In laboratory quality management, AI enables real-time process monitoring and error detection, significantly improving testing reliability. New models that integrate traditional statistical methods with AI technologies, such as patient-based real-time quality control has shown high effectiveness in identifying both systematic and non-systematic errors. AI-driven clinical decision support systems demonstrate great potential in managing acute kidney injury, sepsis, liver fibrosis, and cardiovascular diseases by improving disease risk prediction and patient management. However, the application of AI in this field still faces challenges like data standardization, privacy security, and technical implementation costs. With the establishment of global AI regulatory frameworks, AI technologies will be gradually integrated into laboratory information management systems, becoming a key force in advancing laboratory medicine.
7.Expert consensus on early orthodontic treatment of class III malocclusion.
Xin ZHOU ; Si CHEN ; Chenchen ZHOU ; Zuolin JIN ; Hong HE ; Yuxing BAI ; Weiran LI ; Jun WANG ; Min HU ; Yang CAO ; Yuehua LIU ; Bin YAN ; Jiejun SHI ; Jie GUO ; Zhihua LI ; Wensheng MA ; Yi LIU ; Huang LI ; Yanqin LU ; Liling REN ; Rui ZOU ; Linyu XU ; Jiangtian HU ; Xiuping WU ; Shuxia CUI ; Lulu XU ; Xudong WANG ; Songsong ZHU ; Li HU ; Qingming TANG ; Jinlin SONG ; Bing FANG ; Lili CHEN
International Journal of Oral Science 2025;17(1):20-20
The prevalence of Class III malocclusion varies among different countries and regions. The populations from Southeast Asian countries (Chinese and Malaysian) showed the highest prevalence rate of 15.8%, which can seriously affect oral function, facial appearance, and mental health. As anterior crossbite tends to worsen with growth, early orthodontic treatment can harness growth potential to normalize maxillofacial development or reduce skeletal malformation severity, thereby reducing the difficulty and shortening the treatment cycle of later-stage treatment. This is beneficial for the physical and mental growth of children. Therefore, early orthodontic treatment for Class III malocclusion is particularly important. Determining the optimal timing for early orthodontic treatment requires a comprehensive assessment of clinical manifestations, dental age, and skeletal age, and can lead to better results with less effort. Currently, standardized treatment guidelines for early orthodontic treatment of Class III malocclusion are lacking. This review provides a comprehensive summary of the etiology, clinical manifestations, classification, and early orthodontic techniques for Class III malocclusion, along with systematic discussions on selecting early treatment plans. The purpose of this expert consensus is to standardize clinical practices and improve the treatment outcomes of Class III malocclusion through early orthodontic treatment.
Humans
;
Malocclusion, Angle Class III/classification*
;
Orthodontics, Corrective/methods*
;
Consensus
;
Child
8.Medication rules of Astragali Radix in ancient Chinese medical books based on "disease-medicine-dose" pattern.
Jia-Lei CAO ; Lü-Yuan LIANG ; Yi-Hang LIU ; Zi-Ming XU ; Xuan WANG ; Wen-Xi WEI ; He-Jia WAN ; Xing-Hang LYU ; Wei-Xiao LI ; Yu-Xin ZHANG ; Bing-Qi WEI ; Xian-Qing REN
China Journal of Chinese Materia Medica 2025;50(3):798-811
This study employed the "disease-medicine-dose" pattern to mine the medication rules of traditional Chinese medicine(TCM) prescriptions containing Astragali Radix in ancient Chinese medical books, aiming to provide a scientific basis for the clinical application of Astragali Radix and the development of new medicines. The TCM prescriptions containing Astragali Radix were retrieved from databases such as Chinese Medical Dictionary and imported into Excel 2020 to construct the prescription library. Statical analysis were performed for the prescriptions regarding the indications, syndromes, medicine use frequency, herb effects, nature and taste, meridian tropism, dosage forms, and dose. SPSS statistics 26.0 and IBM SPSS Modeler 18.0 were used for association rules analysis and cluster analysis. A total of 2 297 prescriptions containing Astragali Radix were collected, involving 233 indications, among which sore and ulcer, consumptive disease, sweating disorder, and apoplexy had high frequency(>25), and their syndromes were mainly Qi and blood deficiency, Qi and blood deficiency, Yin and Yang deficiency, and Qi deficiency and collateral obstruction, respectively. In the prescriptions, 98 medicines were used with the frequency >25 and they mainly included Qi-tonifying medicines and blood-tonifying medicines. Glycyrrhizae Radix et Rhizoma, Angelicae Sinensis Radix, Ginseng Radix et Rhizoma, Atractylodis Macrocephalae Rhizoma, and Citri Reticulatae Pericarpium were frequently used. The medicines with high frequency mainly have warm or cold nature, and sweet, pungent, or bitter taste, with tropism to spleen, lung, heart, liver, and kidney meridians. In the treatment of sore and ulcer, Astragali Radix was mainly used with the dose of 3.73 g and combined with Glycyrrhizae Radix et Rhizoma to promote granulation and heal up sores. In the treatment of consumptive disease, Astragali Radix was mainly used with the dose of 37.30 g and combined with Ginseng Radix et Rhizoma to tonify deficiency and replenish Qi. In the treatment of sweating disorder, Astragali Radix was mainly used with the dose of 3.73 g and combined with Glycyrrhizae Radix et Rhizoma to consolidate exterior and stop sweating. In the treatment of apoplexy, Astragali Radix was mainly used with the dose of 7.46 g and combined with Glycyrrhizae Radix et Rhizoma to dispell wind and stop convulsions. Astragali Radix can be used in the treatment of multiple system diseases, with the effects of tonifying Qi and ascending Yang, consolidating exterior and stopping sweating, and expressing toxin and promoting granulation. According to the manifestations of different diseases, when combined with other medicines, Astragali Radix was endowed with the effects of promoting granulation and healing up sores, tonifying deficiency and Qi, consolidating exterior and stopping sweating, and dispelling wind and replenishing Qi. The findings provide a theoretical reference and a scientific basis for the clinical application of Astragali Radix and the development of new medicines.
Drugs, Chinese Herbal/history*
;
Humans
;
Medicine, Chinese Traditional/history*
;
History, Ancient
;
Astragalus Plant/chemistry*
;
China
;
Astragalus propinquus
9.Saltwater stir-fried Plantaginis Semen alleviates renal fibrosis by regulating epithelial-mesenchymal transition in renal tubular cells.
Xin-Lei SHEN ; Qing-Ru ZHU ; Wen-Kai YU ; Li ZHOU ; Qi-Yuan SHAN ; Yi-Hang ZHANG ; Yi-Ni BAO ; Gang CAO
China Journal of Chinese Materia Medica 2025;50(5):1195-1208
This study aimed to investigate the effect of saltwater stir-fried Plantaginis Semen(SPS) on renal fibrosis in rats and decipher the underlying mechanism. Thirty-six Sprague-Dawley rats were randomly assigned into control, model, losartan potassium, and low-, medium-, and high-dose(15, 30, and 60 g·kg~(-1), respectively) SPS groups. Rats in other groups except the control group were subjected to unilateral ureteral obstruction(UUO) to induce renal fibrosis, and the modeling and gavage lasted for 14 days. After 14 consecutive days of treatment, the levels of serum creatinine(Scr) and blood urea nitrogen(BUN) in rats of each group were determined by an automatic biochemical analyzer. Hematoxylin-eosin(HE) and Masson staining were used to evaluate pathological changes in the renal tissue. Western blot and immunofluorescence assay were conducted to determine the protein levels of fibronectin(FN), collagen Ⅰ, vimentin, and α-smooth muscle actin(α-SMA) in the renal tissue. The mRNA levels of epithelial-mesenchymal transition(EMT)-associated transcription factors including twist family bHLH transcription factor 1(TWIST1), snail family transcriptional repressor 1(SNAI1), and zinc finger E-box binding homeobox 1(ZEB1), as well as inflammatory cytokines such as interleukin-1β(IL-1β), interleukin-6(IL-6), and tumor necrosis factor-α(TNF-α), were determined by RT-qPCR. Human renal proximal tubular epithelial(HK2) cells exposed to transforming growth factor-β(TGF-β) for the modeling of renal fibrosis were used to investigate the inhibitory effect of SPS on EMT. Network pharmacology and Western blot were employed to explore the molecular mechanism of SPS in alleviating renal fibrosis. The results showed that SPS significantly reduced Scr and BUN levels and alleviated renal injury and collagen deposition in UUO rats. Moreover, SPS notably down-regulated the protein levels of FN, collagen Ⅰ, vimentin, and α-SMA as well as the mRNA levels of SNAI1, ZEB1, TWIST1, IL-1β, IL-6, and TNF-α in the kidneys of UUO rats and TGF-β-treated HK-2 cells. In addition, compared with Plantaginis Semen without stir-frying with saltwater, SPS showed increased content of specific compounds, which were mainly enriched in the mitogen-activated protein kinase(MAPK) signaling pathway. SPS significantly inhibited the phosphorylation of extracellular signal-regulated kinase(ERK) and p38 MAPK in the kidneys of UUO rats and TGF-β-treated HK2 cells. In conclusion, SPS can alleviate renal fibrosis by attenuating EMT through inhibition of the MAPK signaling pathway.
Animals
;
Epithelial-Mesenchymal Transition/drug effects*
;
Rats, Sprague-Dawley
;
Male
;
Rats
;
Fibrosis/genetics*
;
Drugs, Chinese Herbal/administration & dosage*
;
Kidney Diseases/pathology*
;
Kidney Tubules/pathology*
;
Humans
10.Effect and mechanism of Bufei Decoction on improving Klebsiella pneumoniae pneumonia in rats by regulating IL-17 signaling pathway.
Li-Na HUANG ; Zheng-Ying QIU ; Xiang-Yi PAN ; Chen LIU ; Si-Fan LI ; Shao-Guang GE ; Xiong-Wei SHI ; Hao CAO ; Rui-Hua XIN ; Fang-di HU
China Journal of Chinese Materia Medica 2025;50(11):3097-3107
Based on the interleukin-17(IL-17) signaling pathway, this study explores the effect and mechanism of Bufei Decoction on Klebsiella pneumoniae pneumonia in rats. SD rats were randomly divided into the control group, model group, Bufei Decoction low-dose group(6.68 g·kg~(-1)·d~(-1)), Bufei Decoction high-dose group(13.36 g·kg~(-1)·d~(-1)), and dexamethasone group(1.04 mg·kg~(-1)·d~(-1)), with 10 rats in each group. A pneumonia model was established by tracheal drip injection of K. pneumoniae. After successful model establishment, the improvement in lung tissue damage was observed following drug administration. Core targets and signaling pathways were screened using transcriptomics techniques. Real-time fluorescence quantitative polymerase chain reaction was used to detect the mRNA expression of core targets interleukin-6(IL-6), interleukin-1β(IL-1β), tumor necrosis factor-α(TNF-α), and chemokine CXC ligand 6(CXCL6). Western blot was used to assess key proteins in the IL-17 signaling pathway, including interleukin-17A(IL-17A), nuclear transcription factor-κB activator 1(Act1), tumor necrosis factor receptor-associated factor 6(TRAF6), and downstream phosphorylated p38 mitogen-activated protein kinase(p-p38 MAPK), and phosphorylated nuclear factor-κB p65(p-NF-κB p65). Apoptosis of lung tissue cells was detected by terminal deoxynucleotidyl transferase-mediated dUTP-biotin nick end labeling(TUNEL). The results showed that, compared with the control group, the model group exhibited significant pathological damage in lung tissue. The mRNA expression of IL-6, IL-1β, TNF-α, and CXCL6, as well as the protein levels of IL-17A, Act1, TRAF6, p-p38 MAPK/p38 MAPK, and p-NF-κB p65/NF-κB p65, were significantly increased, and the number of apoptotic cells was notably higher, indicating successful model establishment. Compared with the model group, both low-and high-dose groups of Bufei Decoction showed reduced pathological damage in lung tissue. The mRNA expression levels of IL-6, IL-1β, TNF-α, and CXCL6, and the protein levels of IL-17A, Act1, TRAF6, p-p38 MAPK/p38 MAPK, and p-NF-κB p65/NF-κB p65, were significantly decreased, with a significant reduction in apoptotic cells in the high-dose group. In conclusion, Bufei Decoction can effectively improve lung tissue damage and reduce inflammation in rats with K. pneumoniae. The mechanism may involve the regulation of the IL-17 signaling pathway and the reduction of apoptosis.
Animals
;
Interleukin-17/metabolism*
;
Drugs, Chinese Herbal/administration & dosage*
;
Rats, Sprague-Dawley
;
Signal Transduction/drug effects*
;
Rats
;
Male
;
Klebsiella pneumoniae/physiology*
;
Klebsiella Infections/immunology*
;
Humans
;
Lung/drug effects*

Result Analysis
Print
Save
E-mail