Predicting the Behavioral Health Needs of Asian Americans in Public Mental Health Treatment: A Classification Tree Approach.

Given the fact that experiencing pandemic-related hardship and racial discrimination worsen Asian Americans' mental health, this study aimed to identify unique characteristics of behavioral health needs among Asian Americans (N = 544) compared to White Americans (N = 78,704) and Black Americans (N = 11,252) who received publicly funded behavioral health services in Indiana before and during the COVID-19 pandemic. We used 2019-2020 Adults Needs and Strengths Assessment (ANSA) data for adults eligible for Medicaid or funding from the state behavioral health agency. Chi-squared automatic interaction detection (CHAID) was used to detect race-specific differences among demographic variables, the pandemic status, and ANSA items. Results indicated that, regardless of age, gender, or pandemic status, Asian Americans who received behavioral health services, struggled more with cultural-related factors compared to White and Black individuals. Within this context, intersections among behavioral/emotional needs (psychosis), life functioning needs (involvement in recovery, residential stability, decision making, medical/physical health), and strengths (job history, interpersonal, and spiritual) further differentiated the mental health functioning of Asian from White and Black Americans. Classification tree algorithms offer a promising approach to detecting complex behavioral health challenges and strengths of populations based on race, ethnicity, or other characteristics.

Relationship between dietary patterns and sleep disorders among health screening population in Changsha. / é•¿æ²™åœ°åŒºéƒ¨åˆ†å¥åº·ä½“æ£€äººç¾¤é¥®é£Ÿæ¨¡å¼ä¸Žç¡çœ éšœç¢çš„å ³ç³».

OBJECTIVES: Sleep disorders directly affect health-related quality of life, so it is of great significance to investigate the risk factors of sleep disorders and to actively intervene. This study aims to investigate the relationship between dietary patterns and associated factors and sleep disorders among the health screening populations in Changsha. METHODS: A cross-sectional study was carried out in 86 073 subjects aged 18-70 years old who underwent the health screening. The association between dietary patterns and sleep disorders was analyzed. The associated factors for sleep disorders were identified via by principal component analysis and classification tree model. RESULTS: The overall prevalence of reporting sleep disorders was 18.64%. Four major dietary patterns (healthy, snacks, whole-grain, and fried food patterns) were identified. In logistic regression, snacks and fried food patterns had higher risk of sleep disorders. The whole-grain pattern was a protective factor for sleep disorders. Nine associated factors including age, susceptibility to anxiety, snacking parterns, feelings of depression, chronic pain, physical activity, educational level, gender, and weight, and 9 groups at high risk for sleep disorders were identified by classification tree model. CONCLUSIONS: Sleep disorders are prevalent in the health screening population of Changsha. There is a close association between snacks dietary patterns and sleep disorders. It is necessary to promote healthy and reasonable diet, and keep good lifestyle for the prevention and control of sleep disorders. Health management after physical examination should take different health interventions for high-risk groups with different characteristics of sleep disorders.

Risk factors for diabetic nephropathy complications in community patients with type 2 diabetes mellitus in Shanghai: Logistic regression and classification tree model analysis.

BACKGROUND: The prevalence of type 2 diabetes mellitus (T2DM) in China was 11.6% in 2010. Chronic complications are the main diabetes-related cause of death and disability, accounting for more than 80% of the cost of diabetes treatment. Diabetic nephropathy (DN) is a common microvascular complication and is the second leading cause of end-stage renal failure in China. OBJECTIVE: We aimed to analyse the DN status among community-based T2DM patients and to explore risk factors for T2DM with DN. METHODS: This study was conducted in six communities of Shanghai. We administered a questionnaire, physical examination, and biochemical tests to 5078 patients with T2DM. Logistic regression and the classification tree model were used to analyse risk factors for T2DM with DN. RESULTS: In total, 1937 patients were diagnosed with DN (prevalence 38.4%). The logistic regression model indicated that course of disease more than 15 years, body mass index (BMI) greater than 24 kg/m2 , haemoglobin A1c (HbA1c) greater than 7.5%, fasting blood glucose (FBG) greater than 11.0 mmol/L, total cholesterol (TC), and high-density lipoprotein (HDL)-C control failure, hypertension, and diabetic retinopathy were risk factors for T2DM with DN (P < .05). The classification tree model identified seven risk factors (HbA1c, FBG, hypertension, postprandial blood glucose, BMI, triacylglycerol, and HDL), of which, HbA1c (cut-off point 7.45%), hypertension, and FBG showed the strongest association. CONCLUSION: This suggests that screening for DN based on HbA1c, FBG, and hypertension should be more extensively promoted by the government on a community level, more attention should be focused on patients' health management, and that patients should be educated on self-management.

[Analysis of HIV infection status and the related factors among male students who have sex with men from voluntary counseling and testing clinics by classification tree model in Changzhou City, Jiangsu Province].

Objective: To analysis the status of HIV infection and the related factors among students of men who have sex with men (MSM) from voluntary counseling and testing (VCT) clinics in Changzhoucity Jiangsu province. Methods: A total of 236 subjects with previous male sexual history, 16-25 years of age and less than 3 months of confirmation time of HIV positive infection were recruited in Changzhou from January 2014 to December 2017. Questionnaires were conducted and plasma samples were collected for selenium and HIV antibody testing. The relevant factors of HIV infection among MSM were screened by classification tree model. The model was evaluated using cross validation and receiver operating characteristic (ROC) curve. Results: The age of subjects was (20.76±1.97) years old. The age of the first sex with men was (19.14±1.85) years old and the plasma selenium content was (82.59±11.99) ng/ml. Of the 236 subjects, 74.58% (176 cases) were college students or undergraduates; 8.90% (21 cases) were diagnosed with venereal diseases in the last year; 80.93% (191 cases) received health services in the last year, and the positive rate of HIV antibody was 25.00% (59 cases). Four relevant factors were screened by the classification tree model, including the diagnosis of sexual transmitted diseases (STDs) in the last year, health services in the last year, plasma selenium level and education level. The most important factor was whether STDs were diagnosed in the last year. The estimate of re-substitution and cross-validation of the classification tree model was 0.186 and 0.195, and the standard error was 0.025 and 0.026, respectively. The area under the ROC was 0.706 (P<0.001). Conclusion: The MSM HIV antibody positive rate of VCT students in Changzhou City, Jiangsu Province was 25.0%. The diagnosis of STDs in the last year, receiving health services in the last year, plasma selenium level and education level were relevant factors of HIV infection.

Can Religious Beliefs be a Protective Factor for Suicidal Behavior? A Decision Tree Analysis in a Mid-Sized City in Iran, 2013.

This study aimed to assess using tree-based models the impact of different dimensions of religion and other risk factors on suicide attempts in the Islamic Republic of Iran. Three hundred patients who attempted suicide and 300 age- and sex-matched patient attendants with other types of disease who referred to Kerman Afzalipour Hospital were recruited for this study following a convenience sampling. Religiosity was assessed by the Duke University Religion Index. A tree-based model was constructed using the Gini Index as the homogeneity criterion. A complementary discrimination analysis was also applied. Variables contributing to the construction of the tree were stressful life events, mental disorder, family support, and religious belief. Strong religious belief was a protective factor for those with a low number of stressful life events and those with a high mental disorder score; 72 % of those who formed these two groups had not attempted suicide. Moreover, 63 % of those with a high number of stressful life events, strong family support, strong problem-solving skills, and a low mental disorder score were less likely to attempt suicide. The significance of four other variables, GHQ, problem-coping skills, friend support, and neuroticism, was revealed in the discrimination analysis. Religious beliefs seem to be an independent factor that can predict risk for suicidal behavior. Based on the decision tree, religious beliefs among people with a high number of stressful life events might not be a dissuading factor. Such subjects need more family support and problem-solving skills.

Potential Predictive Value of miR-125b-5p, miR-155-5p and Their Target Genes in the Course of COVID-19.

Purpose: This study aimed to provide new biomarkers for predicting the disease course of COVID-19 by analyzing the dynamic changes of microRNA (miRNA) and its target gene expression in the serum of COVID-19 patients at different stages. Methods: Serum samples were collected from all COVID-19 patients at three time points: the acute stage, the turn-negative stage, and the recovery stage. The expression level of miRNA and the target mRNA was measured by Quantitative Real-Time Polymerase Chain Reaction (RT-qPCR). The classification tree model was established to predict the disease course, and the prediction efficiency of independent variables in the model was analyzed using the receiver operating characteristic (ROC) curve. Results: The expression of miR-125b-5p and miR-155-5p was significantly up-regulated in the acute stage and gradually decreased in the turn-negative and recovery stages. The expression of the target genes CDH5, STAT3, and TRIM32 gradually down-regulated in the acute, turn-negative, and recovery stages. MiR-125b-5p, miR-155-5p, STAT3, and TRIM32 constituted a classification tree model with 100% accuracy of prediction and AUC >0.7 for identification and prediction in all stages. Conclusion: MiR-125b-5p, miR-155-5p, STAT3, and TRIM32 could be useful biomarkers to predict the time nodes of the acute, turn-negative, and recovery stages of COVID-19.

A contrast-enhanced-CT-based classification tree model for classifying malignancy of solid lung tumors in a Chinese clinical population.

BACKGROUND: To develop and validate a contrast-enhanced CT based classification tree model for classifying solid lung tumors in clinical patients into malignant or benign. METHODS: Between January 2015 and October 2017, 827 pathologically confirmed solid lung tumors (487 malignant, 340 benign; median size, 27.0 mm, IQR 18.0-39.0 mm) from 827 patients from a dedicated Chinese cancer hospital were identified. Nodules were divided randomly into two groups, a training group (575 cases) and a testing group (252 cases). CT characteristics were collected by two radiologists, and analyzed using a classification and regression tree (CART) model. For validation, we used the decision analysis threshold to evaluate the classification performance of the CART model and radiologist's diagnosis (benign; malignant) in the testing group. RESULTS: Three out of 19 characteristics [margin (smooth; slightly lobulated/lobulated/spiculated), and shape (round/oval; irregular), subjective enhancement (no/uniform enhancement; heterogeneous enhancement)] were automatically generated by the CART model for classifying solid lung tumors. The sensitivity, specificity, PPV, NPV, and diagnostic accuracy of the CART model is 98.5%, 58.1%, 80.6%, 98.6%, 79.8%, and 90.4%, 54.7%, 82.4% 98.5%, 74.2% for the radiologist's diagnosis by using three-threshold decision analysis. CONCLUSIONS: Tumor margin and shape, and subjective tumor enhancement were the most important CT characteristics in the CART model for classifying solid lung tumors as malignant. The CART model had higher discriminatory power than radiologist's diagnosis. The CART model could help radiologists making recommendations regarding follow-up or surgery in clinical patients with a solid lung tumor.

Establishing Classification Tree Models in Rheumatoid Arthritis Using Combination of Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry and Magnetic Beads.

Background: There is no simple method for early diagnosis and evaluation of rheumatoid arthritis (RA). This study aimed to determine potential biomarkers and establish diagnostic patterns for RA using proteomic fingerprint technology combined with magnetic beads. Methods: The serum protein profiles of 97 RA patients and 76 healthy controls (HCs) were analyzed by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) with weak cationic exchange (WCX) magnetic beads. Samples were randomly divided into training (83 RA patients and 56 HCs) and test sets (14 RA patients and 20 HCs). Patients were classified according to their Disease Activity Score: in remission, n = 28; with low disease activity, n = 17; with moderate disease activity, n = 21; with high disease activity, n = 31. There are 44 RA patients alone, 22 RA patients with interstitial lung disease (RA-ILD), 18 RA patients with secondary Sjögren's syndrome (RA-sSS), 6 RA patients with osteonecrosis of the femoral head (RA-ONFH), and 7 RA patients with other complications. Eleven patients were treated with etanercept only for half a year, after which their serum protein profiles were detected. The proteomic pattern was identified by Biomarker Patterns Software, and the potential biomarkers for RA diagnosis were further identified and quantified by enzyme-linked immunosorbent assay. Results: The diagnostic pattern with four potential protein biomarkers, mass-to-charge (m/z) 3,448.85, 4,716.71, 8,214.29, and 10,645.10, could accurately recognize RA patients from HCs (specificity, 91.57%; sensitivity, 92.86%). The test set were correctly classified by this model (sensitivity, 95%; specificity, 100%). The components containing the four biomarkers were preliminarily retrieved through the ExPasy database, including the C-C motif chemokine 24 (CCL24), putative metallothionein (MT1DP), sarcolipin (SLN), and C-X-C motif chemokine 11 (CCXL11). Only the CCL24 level was detected to have a significant decrease in the serum of RA patients as compared with HCs (p < 0.05). No significant difference was found in others, but a decreasing trend consistent with the down-regulation of the four biomarkers detected by MALDI-TOF-MS was observed. The diagnostic models could effectively discriminate between RA alone and RA with complications (RA-ILD: m/z 10,645.10 and 12,595.86; RA-sSS: m/z 6,635.62 and 33,897.72; RA-ONFH: m/z 2,071.689). The classification model, including m/z 1,130.776, 1,501.065, 2,091.198, and 11,381.87, could distinguish between RA patients with disease activity and those in remission. RA with low disease activity could be efficiently discriminated from other disease activity patients by specific protein biomarkers (m/z 2,032.31, 2,506.214, and Z9286.495). Two biomarkers (m/z 2,032.31 and 4,716.71) were applied to build the classification model for RA patients with moderate and high disease activities. Biological markers for etanercept (m/z 2,671.604064, 5,801.840579, 8,130.195641, and 9,286.49499) were observed between the responder (n = 7) and non-responder groups (n = 4) (p < 0.05). Conclusion: We successfully established a series of diagnostic models involving RA and RA with complications as well as assessed disease activity. Furthermore, we found that CCL24 may be a valuable auxiliary diagnostic indicator for RA. These results provide reference values for clinical practice in the future.

Identification of the important environmental factors influencing natural vegetation succession following cropland abandonment on the Loess Plateau, China.

Identification of typical vegetation succession types and their important influencing factors is an important prerequisite to implement differential vegetation and soil management after land abandonment on the Loess Plateau, China. However, there is no reported study specifically on the identification of vegetation types and their important factors as well as the thresholds of the important factors for classification of the vegetation types, based on the medium- to long-term succession of natural vegetation after cropland abandonment. We collected vegetation and soil data on the natural vegetation with the longest 60-year-old forest communities that developed after cropland abandonment and analyzed the data using two-way indicator species analysis, detrended correspondence analysis, direct canonical correspondence analysis and classification tree model. The vegetation communities were classified into five distinct vegetation types, including Artemisia scoparia, Lespedeza davurica and Stipa bungeana, Artemisia giraldii pamp, Sophora viciifolia, Quercus liaotungensis and Biota orientalis. The years after cropland abandonment and soil C/N were further identified as important factors determining the types of vegetation. Likewise, it was observed that most of the investigated soil nutrient variables and soil texture-related variables improved with the vegetation succession while soil water in the surface layers showed a decreasing trend. These findings may provide an ecological basis for site-specific management of vegetation types after cropland abandonment in the medium-long term on the Loess Plateau. Our results encourage further exploration of vegetation succession and their important factors based on longer periods of vegetation succession after cropland abandonment under more soil and climatic conditions on the mountainous areas as the Loess Plateau.

Analysis of influencing factors of dental fluorosis in children based on logistic regression and classification tree model / 中华地方病学杂志

Objective:To analyze the influencing factors of dental fluorosis of children in the drinking-water-borne endemic fluorosis (referred to as drinking-water-borne fluorosis) areas with qualified drinking water.Methods:In 2020 and 2021, the cluster sampling method was used to select the children aged 8 to 12 years old from the drinking-water-borne fluorisis areas with qualified drinking water in Tianjin City for water and urine fluoride detection, dental fluorosis examination and questionnaire survey, and logistic regression and classification tree model were used to analyze the influencing factors of dental fluorosis in children.Results:A total of 3 795 cases children aged 8 to 12 years old were investigated, and 1 001 cases of dental fluorosis were detected, and the detection rate of dental fluorosis was 26.38% (1 001/3 795). The results of logistic analysis showed that age [odds ratio ( OR) = 1.193, 95% confidence interval ( CI): 1.115 - 1.277], high urinary fluoride (1.84 - 19.40 mg/L, OR = 1.510, 95% CI: 1.169 - 1.952) and the number of permanent residents at home ≥6 ( OR = 1.377, 95% CI: 1.090 - 1.739) were risk factors of dental fluorosis in children; and the mother's with higher education level (college degree or above, OR = 0.664, 95% CI: 0.441 - 0.999), the years of water improvement ≥5 years (5 - < 10 years, OR = 0.193, 95% CI: 0.157 - 0.238; ≥10 years, OR = 0.254, 95% CI: 0.193 - 0.333) were protective factors of dental fluorosis in children. The results of classification tree model analysis showed that the years of water improvement contributed the most to the prevalence of dental fluorosis among children in the drinking-water-borne fluorisis areas with qualified drinking water, followed by age, number of permanent residents at home and urinary fluoride. The area under the receiver operating characteristic curve (AUC) of logistic regression model and classification tree model were 0.730 (95% CI: 0.711 - 0.748) and 0.721 (95% CI: 0.702 - 0.739), respectively, with good fitting effect. Conclusion:The detection rate of children's dental fluorosis in the drinking-water-borne fluorosis areas with qualified drinking water is mainly related to the years of water improvement, age, the number of permanent residents at home and urinary fluoride.

Prognostic factors analysis in EGFR mutation-positive non-small cell lung cancer with brain metastases treated with whole brain-radiotherapy and EGFR-tyrosine kinase inhibitors.

The survival time of non-small cell lung cancer (NSCLC) patients with brain metastases has been previously reported to be 6.5-10.0 months, even with systematic treatment. Patients that possess a certain epidermal growth factor receptor (EGFR) mutation alongside NSCLC with brain metastases also have a short survival rate, and a reliable prognostic model for these patients demonstrates a strong correlation between the outcome and treatment recommendations. The Cox proportional hazards regression and classification tree models were used to explore the prognostic factors in EGFR mutation-positive NSCLC patients with brain metastases following whole-brain radiation therapy (WBRT) and EGFR-tyrosine kinase inhibitor (EGFR-TKI) treatment. A total of 66 EGFR mutation-positive NSCLC patients with brain metastases were retrospectively reviewed. Univariate and multivariate analyses by Cox proportional hazards regression were then performed. The classification tree model was applied in order to identify prognostic groups of the patients. In the survival analysis, age, carcinoembryonic antigen (CEA) and status of the primary tumor were prognostic factors for progression free survival (P=0.006, 0.014 and 0.005, respectively) and overall survival (P=0.009, 0.013 and 0.009, respectively). The classification tree model was subsequently applied, which revealed 3 patient groups with significantly different survival times: Group I, age <65 years and CEA ≤10 µg/ml; Group II, age <65 years and CEA >10 µg/ml or age ≥65 years and CEA ≤10 µg/ml; and Group III, age ≥65 years and CEA >10 µg/ml. The major prognostic predictors for EGFR mutation-positive NSCLC patients with brain metastases following WBRT and EGFR-TKI were age and CEA. In addition, primary tumor control may be important for predicting survival.

Relationship between dietary patterns and sleep disorders among health screening population in Changsha / 中南大学学报(医学版)

OBJECTIVES@#Sleep disorders directly affect health-related quality of life, so it is of great significance to investigate the risk factors of sleep disorders and to actively intervene. This study aims to investigate the relationship between dietary patterns and associated factors and sleep disorders among the health screening populations in Changsha.@*METHODS@#A cross-sectional study was carried out in 86 073 subjects aged 18-70 years old who underwent the health screening. The association between dietary patterns and sleep disorders was analyzed. The associated factors for sleep disorders were identified via by principal component analysis and classification tree model.@*RESULTS@#The overall prevalence of reporting sleep disorders was 18.64%. Four major dietary patterns (healthy, snacks, whole-grain, and fried food patterns) were identified. In logistic regression, snacks and fried food patterns had higher risk of sleep disorders. The whole-grain pattern was a protective factor for sleep disorders. Nine associated factors including age, susceptibility to anxiety, snacking parterns, feelings of depression, chronic pain, physical activity, educational level, gender, and weight, and 9 groups at high risk for sleep disorders were identified by classification tree model.@*CONCLUSIONS@#Sleep disorders are prevalent in the health screening population of Changsha. There is a close association between snacks dietary patterns and sleep disorders. It is necessary to promote healthy and reasonable diet, and keep good lifestyle for the prevention and control of sleep disorders. Health management after physical examination should take different health interventions for high-risk groups with different characteristics of sleep disorders.

Classification Tree Model Analysis on Risk Factors of Diabetic Kidney Disease to Progress to ESRD for CKD3-4 Stages Patients / 中山大学学报(医学科学版)

@#【Objective】To analyze the risk factors of progression to end-stage renal disease（ESRD）in patients with diabetic kidney disease（DKD），and screen the high-risk population for early prevention.【Methods】The clinical data of 231 patients with diabetic nephropathy in our hospital were collected and followed up for 3 years. According to whether ESRD occurred，they were divided into non-progressing ESRD group（133 cases）and ESRD group（98 cases）. Classification tree model was used to analyze the risk factors related to ESRD，and the high-risk population was screened by node gain analysis.【Results】Four important explanatory variables were screened out by the classification tree model from the candi⁃ date variables related to early renal damage，including apolipoprotein B（ApoB），gender，diabetic retinopathy，systemic blood pressure（SBP）. ApoB level was an important factor for DKD progression. For DKD patients with the chronic kidney disease （CKD）3~4 stageswith ApoB> 1.14 mmol/L，theprobabilityofprogression toESRDfor 3 yearswas 75.0 %，and ifat the same time with diabetic retinopathy，the probability was 79.7 %.【Conclusion】The classification tree model can analyze the risk factors of progression to ESRD in DKD patients effectively，to identify the characteristics of high-risk populations.

Analysis of HIV infection status and the related factors among male students who have sex with men from voluntary counseling and testing clinics by classification tree model in Changzhou City, Jiangsu Province / 中华预防医学杂志

Objective@#To analysis the status of HIV infection and the related factors among students of men who have sex with men (MSM) from voluntary counseling and testing (VCT) clinics in Changzhoucity Jiangsu province.@*Methods@#A total of 236 subjects with previous male sexual history, 16-25 years of age and less than 3 months of confirmation time of HIV positive infection were recruited in Changzhou from January 2014 to December 2017. Questionnaires were conducted and plasma samples were collected for selenium and HIV antibody testing. The relevant factors of HIV infection among MSM were screened by classification tree model. The model was evaluated using cross validation and receiver operating characteristic (ROC) curve.@*Results@#The age of subjects was (20.76±1.97) years old. The age of the first sex with men was (19.14±1.85) years old and the plasma selenium content was (82.59±11.99) ng/ml. Of the 236 subjects, 74.58% (176 cases) were college students or undergraduates; 8.90% (21 cases) were diagnosed with venereal diseases in the last year; 80.93% (191 cases) received health services in the last year, and the positive rate of HIV antibody was 25.00% (59 cases). Four relevant factors were screened by the classification tree model, including the diagnosis of sexual transmitted diseases (STDs) in the last year, health services in the last year, plasma selenium level and education level. The most important factor was whether STDs were diagnosed in the last year. The estimate of re-substitution and cross-validation of the classification tree model was 0.186 and 0.195, and the standard error was 0.025 and 0.026, respectively. The area under the ROC was 0.706 (P<0.001).@*Conclusion@#The MSM HIV antibody positive rate of VCT students in Changzhou City, Jiangsu Province was 25.0%. The diagnosis of STDs in the last year, receiving health services in the last year, plasma selenium level and education level were relevant factors of HIV infection.

Classification tree model analysis on related factors of different stages of kidney in type 1 diabetic patients / 中华肾脏病杂志

Objective To analyze the related factors of micro-albuminuria and macroalbuminuria in type 1 diabetes mellitus (DM) in the classification tree model,and to screen the high risk population of diabetic kidney disease.Methods 394 patients with type 1 diabetes were enrolled in the hospital from 2008 to 2015.According to glomerular filtration rates and urine albumin quantification,the patients were divided into type 1 diabetes group (299 cases),micro-albuminuria group (73 cases) and macro-albuminuria group (22 cases).The classification tree model was utilized to analyze related factors of the different stages of proteinuria,and the high-risk population was screened by node gain analysis.Results Four important explanatory variables were screened out by the classification tree model from the 27 candidate variables related to primary renal damage,including retinopathy,fibrinogen,waist-hip ratio (WHR),red blood cell distribution width (RDW).Retinopathy was an major factor of DKD.The probability of macro-albuminuria in retinopathy and WHR ＞ 0.82 group was 43.8％,and if at the same time RDW ＞ 0.14,the probability of macro-albuminuria was 88.9％.Conclusions The classification tree model can analyze factors of the separate stages of proteinuria in type 1 diabetic patients effectively.Retinopathy is the major influential factors of type 1 diabetic patients with proteinuria.

Classification tree model analysis on related factors of different stages of kidney in type 1 diabetic patients / 中华肾脏病杂志

Objective To analyze the related factors of micro-albuminuria and macroalbuminuria in type 1 diabetes mellitus (DM) in the classification tree model,and to screen the high risk population of diabetic kidney disease.Methods 394 patients with type 1 diabetes were enrolled in the hospital from 2008 to 2015.According to glomerular filtration rates and urine albumin quantification,the patients were divided into type 1 diabetes group (299 cases),micro-albuminuria group (73 cases) and macro-albuminuria group (22 cases).The classification tree model was utilized to analyze related factors of the different stages of proteinuria,and the high-risk population was screened by node gain analysis.Results Four important explanatory variables were screened out by the classification tree model from the 27 candidate variables related to primary renal damage,including retinopathy,fibrinogen,waist-hip ratio (WHR),red blood cell distribution width (RDW).Retinopathy was an major factor of DKD.The probability of macro-albuminuria in retinopathy and WHR ＞ 0.82 group was 43.8％,and if at the same time RDW ＞ 0.14,the probability of macro-albuminuria was 88.9％.Conclusions The classification tree model can analyze factors of the separate stages of proteinuria in type 1 diabetic patients effectively.Retinopathy is the major influential factors of type 1 diabetic patients with proteinuria.

Classification tree model analysis of influencing factors for hepatocyte steatosis in patients with chronic hepatitis B / 临床肝胆病杂志

ObjectiveTo investigate the influencing factors for hepatocyte steatosis in patients with chronic hepatitis B (CHB) and the high-risk population by classification tree model analysis, and to establish a simple method to assess the risk of hepatocyte steatosis in CHB patients. MethodsThe clinical data and pathological results of the CHB patients who underwent liver biopsy in Department of Infectious Diseases, The First People's Hospital of Shunde, from January 2006 and December 2014 were collected. The classification tree model was applied to analyze the influencing factors for hepatocyte steatosis, and index value curve, misclassification matrix, and error of estimation were applied for overall evaluation of classification results of the classification tree model. ResultsThe influencing factors for hepatocyte steatosis in CHB patients were body mass index (BMI), total cholesterol, and low-density lipoprotein, and the most important factor was BMI. This classification tree model had a sensitivity of 84.3%, a specificity of 81.5%, an accuracy of 82.9%, and an error of estimation of 0.171, suggesting that this model was well fitted. ConclusionClassification tree model analysis shows that the pathogenesis of hepatocyte steatosis in CHB patients is closely related to the influencing factors BMI, total cholesterol, and low-density lipoprotein. A simple classification method is established based on these factors to evaluate the risk of hepatocyte steatosis in CHB patients. It is necessary to conduct further clinical studies to investigate the clinical value of this method.

Classification tree model analysis on related factors of early renal damage in type 2 diabetic patients / 中华肾脏病杂志

Objective To analyze the impact factors for early renal damage in type 2 diabetic patients by the classification tree model.Methods A total of 601 patients with type 2 diabetes were enrolled.According to glomerular filtration rates and urine albumin quantification,the patients were divided into type 2 diabetes group (418 cases) and early diabetic renal damage group (183 cases).The clinical data of the patients were recorded to analyze the main influential factors for the microalbuminuria of type 2 diabetic patients using the Exhaustive CHAID classification tree algorithm.Results Six important explanatory variables were screened out by the classification tree model from the 34 candidate variables related to early renal damage,including fibrinogen,history of hypertension,retinopathy,Cys C levels,SBP and peripheral neuropathy.Elevated fibrinogen was the main factor.Conclusion The classification tree model can analyze the major influential factors of early renal damage in type 2 diabetic patients effectively,and it can help develop the prevention and treatment methods.