Developing the high risk group predictive model for student direct loan default using data mining

Abstract Objective: To establish a predictive model of carotid vulnerable plaque through systematic screening of high-risk population for stroke.Patients and methods: All community residents who participated in the screening of stroke high-risk population by the China National Stroke Screening and Prevention Project (CNSSPP). A total of 19 risk factors were analyzed. Individuals were randomly divided into Derivation Set group and Validation Set group. According to carotid ultrasonography, the derivation set group patients were divided into instability plaque group and non-instability plaque group. Univariate and multivariable logistic regression were taken for risk factors. A predictive model scoring system were established by the coefficient. The AUC value of both derivation and validation set group were used to verify the effectiveness of the model.Results: A total of 2841 high-risk stroke patients were enrolled in this study, 266 (9.4%) patients were found instability plaque. According to the results of Doppler ultrasound, Derivation Set group were divided into instability plaque group (174 cases) and non-instability plaque group (1720 cases). The independent risk factors for carotid instability plaque were: male (OR 1.966, 95%CI 1.406-2.749)，older age (50-59, OR 6.012, 95%CI 1.410-25.629; 60-69, OR 13.915, 95%CI 3.381-57.267;≥70, OR 31.267, 95%CI 7.472-130.83) , married(OR 1.780, 95%CI 1.186-2.672)，LDL-c(OR 2.015, 95%CI 1.443-2.814), and HDL-C(OR 2.130, 95%CI 1.360-3.338). A predictive scoring system was created, range 0-10. The cut-off value of prediction model score is 6.5. The AUC value of derivation and validation set group were 0.738 and 0.737.Conclusion：For a high risk group of stroke individual, We provide a model that could distinguishing those who have a high probability of having carotid instability plaque. When resident’s predictive model score exceeds 6.5, the incidence of carotid instability plaque is high, carotid artery Doppler ultrasound would be checked immediately. This model can be helpful in the primary prevention of stroke.

Download Full-text

Determinants of Preventive Behaviors for COVID-19 in Japan

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18199979 ◽

2021 ◽

Vol 18 (19) ◽

pp. 9979

Author(s):

Motoko Kosugi

Keyword(s):

Regression Analysis ◽

High Risk ◽

Risk Group ◽

Age Groups ◽

High Risk Group ◽

Perceived Effectiveness ◽

Preventive Behaviors ◽

Risk Of Mortality ◽

Main Factors ◽

Using Data

As of June 2021, there have been more than 13,000 deaths in Japan due to the COVID-19 pandemic. Data from the Ministry of Health, Labor, and Welfare show that the mortality rate of COVID-19 greatly varies by age. In this study, using data from a questionnaire survey, an investigation was carried out to find differences in anxiety and risk perception, attitudes toward risk, and the frequency of implementation of countermeasures to infection among age groups that are prone to a greater risk of mortality, as well as the main factors that determine the frequency of implementation. Older people, who form a high-risk group, have a stronger tendency for anxiety and cautious attitudes toward COVID-19, and they more frequently implement preventive behaviors. The results of multiple regression analysis showed that the frequency of implementation of behaviors is determined not only by anxiety, cautious attitude, risk of aggravation to oneself, and perceived effectiveness of behaviors but also by regret, altruism, and conformity. In addition, almost no age-based gap was found between the determinants, suggesting that the motivation to take infection preventive behaviors is the same regardless of age.

Download Full-text

Prediction of Primary Treatment Outcome Using Gene Expression Profiling of Pre-Treatment Biopsies Obtained from Childhood and Adolescent Hodgkin Lymphoma Patients

Blood ◽

10.1182/blood.v126.23.175.175 ◽

2015 ◽

Vol 126 (23) ◽

pp. 175-175 ◽

Cited By ~ 6

Author(s):

Anja Mottok ◽

Rebecca Lea Johnston ◽

Fong Chun Chan ◽

David W Scott ◽

Debra L. Friedman ◽

...

Keyword(s):

Gene Expression ◽

Treatment Outcome ◽

High Risk ◽

Risk Stratification ◽

Predictive Model ◽

Expression Profiling ◽

Cox Regression ◽

Risk Group ◽

High Risk Group ◽

Pre Treatment

Abstract Introduction: Hodgkin lymphoma (HL) is a common malignancy of children and adolescents and is highly curable with a 5-year overall survival (OS) rate of > 97%, yet dose-intensified chemotherapy regimens in combination with radiation therapy come with a high cost in form of long-term toxicity and morbidity (Castellino et al., Blood 2011). This major clinical challenge has resulted in the evaluation of risk-adapted treatment regimens in clinical trials aiming to achieve the optimal equilibrium between high survival rates and prevention of treatment-related toxicity. However, risk stratification is currently limited to the use of clinical factors as there are no validated integral biomarkers that can be employed to either improve risk stratification or as surrogate markers of treatment outcome in pediatric HL. The aim of our study was to perform gene expression profiling (GEP) to uncover disease biology underlying treatment response and develop a prognostic model to tailor first-line therapy in pediatric HL. Methods: We selected 203 formalin-fixed, paraffin-embedded tissue (FFPET) specimens from patients enrolled in a randomized phase 3 clinical trial (AHOD0031) of the Children's Oncology Group (COG) based on the availability of archived FFPET blocks. That trial was designed to assess the value of early chemotherapy response for tailoring subsequent therapy in intermediate-risk pediatric HL. We performed GEP on RNA extracted from pre-treatment FFPET biopsies using NanoString technology and a customized codeset encompassing probes for 784 genes. These genes were either previously reported to be associated with prognosis and outcome in HL or represent the cellular diversity of the tumor microenvironment. Event free survival (EFS) and OS were estimated using the Kaplan-Meier method. Gene expression data were used to develop a predictive model for EFS using penalized Cox regression with parameters trained using leave-one-out cross-validation. Results: Of the 203 tissue samples obtained from the Biopathology Center at the Cooperative Human Tissue Network, 182 (89.7%) passed quality assurance testing, similar to the pass rate achieved for adult HL samples obtained from the Eastern Cooperative Oncology Group trial E2496 (Scott et al., JCO 2013). We applied our previously published 23-gene predictor for OS (Scott et al., JCO 2013), developed using biopsies from adult HL patients to our pediatric cohort. After calibrating the new codeset, 53 patients were classified as "high-risk" and 129 as "low-risk". Importantly, the model failed to predict inferior outcomes in the "high-risk" group (5-year OS 100% vs 95%, log-rank P = 0.125; 5-year EFS 82% vs 70%, log-rank P = 0.159), with patients in the "high risk" group trending to have superior outcomes than the "low risk" patients. Moreover, only 2 genes from this model, IFNG and CXCL11, were significantly associated with EFS in univariate Cox regression analysis (P = 0.003 and 0.048, respectively) but with inverse hazard ratios in the pediatric group compared to adult patients. Therefore, we sought to develop a novel EFS predictive model for pediatric patients treated in the AHOD0031 trial. Using univariate Cox regression we identified 79 genes significantly associated with EFS (raw P < 0.05). Using the expression of these 79 genes as the input to penalized Cox regression, we developed a 16-gene model to predict EFS in our training cohort. Using an optimized cut-off for the model score, 31% of patients were designated high-risk and had significantly inferior post-treatment outcome (5-year EFS 38% vs 89%, log-rank P < 0.0001). When multivariate analyses were performed including our EFS-model score, disease stage and initial treatment response as variables, only the model score was significantly associated with EFS (P < 0.0001, HR 11.3 (95% CI 5.5-23.4)). Conclusions: Failure of the GEP-based model developed in adult HL suggests distinct biology underlies treatment failure in the pediatric age group. We describe the development of a novel predictive model for EFS in intermediate-risk pediatric HL patients that will be validated in an independent cohort of patients treated in the AHOD0031 trial. Successful validation of the model may provide a clinically relevant biomarker for pediatric and adolescent HL patients allowing refinement of risk stratification and the combination of molecular and clinical risk factors at diagnosis. Disclosures Scott: Celgene: Consultancy, Honoraria; NanoString: Patents & Royalties: Inventor on a patent that NanoString has licensed.

Download Full-text

A model for predicting carotid instability plaque in high risk group of stroke individuals

10.21203/rs.2.13605/v2 ◽

2019 ◽

Author(s):

Junxiong Yin ◽

Chuanyong Yu ◽

Hongxing Liu ◽

Mingyang Du ◽

Feng Sun ◽

...

Keyword(s):

Risk Factors ◽

High Risk ◽

Predictive Model ◽

Doppler Ultrasound ◽

Scoring System ◽

Risk Group ◽

High Risk Group ◽

High Risk Population ◽

Auc Value ◽

Validation Set

Abstract Background: Atherosclerosis is the main risk factor of cerebral vascular disease. Previous studies published several predictive models of asymptomatic carotid stenosis , yet they were ignored that people with lower levels of stenosis (＜50% or carotid instability plaque) who may benefit from early risk reducing medications, such as statins, antiplatelet drugs. Thus, this study determined to establish a predictive model of carotid vulnerable plaque through systematic screening of high-risk population for stroke. Methods: All community residents who participated in the screening of stroke high-risk population by the China National Stroke Screening and Prevention Project(CNSSPP). A total of 19 risk factors were analyzed. Individuals were randomly divided into Derivation-Set group and Validation-Set group. According to carotid ultrasonography, the derivation set group patients were divided into instability plaque group and non-instability plaque group. Univariate and multivariable logistic regression were taken for risk factors. A predictive model scoring system were established by the coefficient. The Area under curve (AUC) value of both derivation and validation set group were used to verify the effectiveness of the model. Results: A total of 2841 high risk stroke patients were enrolled in this study, 266(9.4%) patients were found instability plaque. According to the results of Doppler ultrasound, Derivation Set group were divided into instability plaque group (174 cases) and non-instability plaque group (1720 cases). The independent risk factors for carotid instability plaque were: male (OR 1.966, 95%CI 1.406-2.749)，older age (50-59, OR 6.012, 95%CI 1.410-25.629; 60-69, OR 13.915, 95%CI 3.381-57.267;≥70, OR 31.267, 95%CI 7.472-130.83) , married(OR 1.780, 95%CI 1.186-2.672)，LDL-c(OR 2.015, 95%CI 1.443-2.814), and HDL-C(OR 2.130, 95%CI 1.360-3.338). A predictive scoring system was created, range 0-10. The cut-off value of prediction model score is 6.5. The AUC value of derivation and validation set group were 0.738 and 0.737. Conclusions:For a high risk group of stroke individual, We provide a model that could distinguishing those who have a high probability of having carotid instability plaque. When resident’s predictive model score exceeds 6.5, the incidence of carotid instability plaque is high, carotid artery Doppler ultrasound would be checked immediately. This model can be helpful in the primary prevention of stroke.

Download Full-text

Acromegaly and Obstructive Sleep Apnea: Identifying the High-Risk Group

10.1055/s-0039-1679596 ◽

2019 ◽

Author(s):

Xiaojun Zhan ◽

Chandala Chitguppi ◽

Ethan Berman ◽

Gurston Nyquist ◽

Tomas Garzon-Muvdi ◽

...

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

High Risk ◽

Risk Group ◽

High Risk Group ◽

Obstructive Sleep

Download Full-text

Recommendations from male students help shape mental health support for this high-risk group

10.3310/alert_42077 ◽

2020 ◽

Keyword(s):

Mental Health ◽

High Risk ◽

Risk Group ◽

High Risk Group ◽

Male Students ◽

Mental Health Support ◽

Health Support

Download Full-text

Anamnestic factors that shape reproductive health of women with repeated unsuccessful popygamy in vitro fertilization

HEALTH OF WOMAN ◽

10.15574/hw.2016.114.140 ◽

2016 ◽

pp. 140-143

Author(s):

N.V. Cotsabin ◽

◽

O.M. Makarchuk ◽

Keyword(s):

High Risk ◽

Risk Group ◽

Polycystic Ovary ◽

High Risk Group ◽

Stress Factors ◽

Control Group ◽

Fertilization In Vitro ◽

Infertile Women ◽

Group I

The proportion of patients with multiple unsuccessful attempts of assisted reproductive technology (ART) is about 30% of all patients treated with the use of ART. Women with history of unsuccessful ART attempts - a special category of patients who require emergency attention and a thorough examination at the stage of preparation for superovulation stimulation,the selection of embryos and endometrium preparation for embryo transfer. The objective: to distinguish high-risk group of unsuccessful attempts based on a detailed analysis of anamnestic and clinical data of infertile women with repeated unsuccessful ART attempts that requires more in-depth study of hormonal features, ovarian reserve and condition of the endometrium. Materials and methods. For better understanding of the problem of repeated unsuccessful ART attempts and сreation of efficient infertility treatment algorithms for these couples we conducted a thorough analysis of anamnestic data of three groups of infertile women (105 patients), which were distributed by age: group I – younger than 35, the II group – from 35 to 40, the III group - over 40 years. These groups of patients were compared with each other and with the control group of healthy women (30 persons). Results. Leading stress factors in the percentage three times prevailed in the group of infertile women and had a direct connection with the fact of procedure «fertilization in vitro» and chronic stressors caused by prolonged infertility. Primary infertility was observed significantly more frequent in patients younger than 35 years (p <0.05), secondary infertility - mostly in the second and third experimental groups (p <0.05). Noteworthy significant percentage of wellknown causes of infertility and idiopathic factor in all groups, and the prevalence of tubal-peritoneal factor in the second and third experimental groups, and endocrine dysfunction in the I experimental group. The most common disorder among this category of woman was polycystic ovary syndrome. Frequency of usual miscarriage among patients of I ana II groups was two times higher than in the third group (p <0.05). Among the experimental groups the leading place belongs urinary tract infection, respiratory tract diseases, pathologies of the cardiovascular system. Data of the stratified analysis show an increase likelihood of repeated unsuccessful ART attempts under the influence of constant chronic stress (odds ratio OR=2.06; 95% CI: 0.95–3.17; p<0.05). Conclusions. Among infertile patients with repeated unsuccessful ART attempts must be separated a high risk group of failures. The identity depends on the duration of infertility, female age and leading combination of factors. Key words: repeated unsuccessful ART attempts, anamnesis, infertility, high risk.

Download Full-text