Use Machine Learning Methods to Explore the Associated Risk Factors of Osteoporosis or Bone Loss in Chinese People with Type 2 Diabetes a Clinical Prediction Model

2020 ◽  
Author(s):  
Yaqian Mao ◽  
Ting Xue ◽  
Jixing Liang ◽  
Wei Lin ◽  
Junping Wen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Type 2 Diabetes ◽  
Bone Loss ◽  
Chinese People ◽  
Clinical Prediction ◽  
Clinical Prediction Model ◽  
Machine Learning Methods ◽  
Associated Risk Factors

scholarly journals Use Machine Learning Methods to Explore the Associated Risk Factors of Osteoporosis or Bone Loss in Chinese People With Type 2 Diabetes: A Clinical Prediction Model

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. A250-A251
Author(s):  
Yaqian Mao ◽  
Jixing Liang ◽  
Wei Lin ◽  
Junping Wen ◽  
Gang Chen
Keyword(s):  
Risk Factors ◽  
Bone Loss ◽  
Prediction Models ◽  
Clinical Prediction ◽  
Clinical Prediction Models ◽  
Prediction Ability ◽  
Related Risk ◽  
Associated Risk Factors ◽  
Index Value

Abstract Objective: This study aimed to use machine learning (ML) methods to explore the risk factors associated with OP and bone loss in the Chinese T2DM population, so as to construct useful clinical prediction models. Methods: This was a two-center, retrospective study. The data came from a chronic disease epidemiological investigation database conducted in Ningde City and Wuyishan City, Fujian Province, China from March 2011 to December 2014. Finally, 798 T2DM patients who met the enrollment criteria were included in the final analysis. In order to control gender as a confounding factor that affects the results, we constructed two clinical prediction models based on different genders. We used the least absolute shrinkage and selection operator (LASSO) algorithm to filter relevant feature variables. The selected characteristic variables were modeled by logistic regression (LR), and clinical nomograms were used for more intuitive expression. The stability, clinical applicability and recognition of the model were evaluated by C-index, receiver operating characteristic (ROC) curve, calibration chart and decision curve analysis (DCA). Internal verification was achieved through bootstrapping validation. Results: In exploring the related risk factors of OP or bone loss in female T2DM patients. There were a total of 9 related predictors, namely age, marital status, glutamyl transpeptidase, fracture, coronary heart disease, fruit-flavored drinks, moderate-intensity exercise, menopause and nap time were determined by LASSO analysis from a total of 69 variables. The model we constructed using these 9 related predictors showed medium prediction ability (C-index value: 0.738, 95%CI[0.692, 0.784]), the C-index in bootstrapping validation was 0.714, and the area under the ROC curve (AUC) was 0.738. The DCA showed that if the risk threshold was between 4% and 100%, the nomogram could be used clinically. In exploring the related risk factors of OP and bone loss in male T2DM patients. A total of 12 related predictors were identified from 65 variables through LASSO analysis, including age, marital status, fasting serum insulin, alanine aminotransferase, coronary heart disease, respiratory diseases, diabetic retinopathy, seafood, desserts, fruit-flavored beverages, coffee, high-intensity exercise. The model we constructed using these 12 related predictors showed medium prediction ability (C-index value: 0.751, 95%CI[0.694–0.808]), the C-index in bootstrapping validation was 0.704, and the AUC value was 0.751. The DCA showed that if the risk threshold was between 3% and 68%, the nomogram could be used clinically. Conclusion: We explored the associated risk factors of osteoporosis or bone Loss in Chinese people with type 2 diabetes, and developed a risk nomogram with moderate predictive power. The nomogram can help clinicians and patients make joint decisions before treatment.

Type 2 diabetes in Bangladesh and associated risk factors

2015 ◽  
Vol 36 (2) ◽  
pp. 174-178 ◽  
Author(s):  
S. M. Ferdous Hossain ◽  
Jahida Gulshan ◽  
Parvin Akter Khanam
Keyword(s):  
Risk Factors ◽  
Type 2 Diabetes ◽  
Associated Risk Factors

scholarly journals Prevalence and Risk Factors of Depression in Chinese Patients With Type 2 Diabetes Mellitus: a Protocol of Systematic Review and Meta-analysis

2020 ◽  
Author(s):  
Xiaobo LIU ◽  
Chao Dong ◽  
Hong Jiang ◽  
Dongling Zhong ◽  
Yuxi Li ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Systematic Review ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Early Detection ◽  
Meta Analysis ◽  
Prevalence Of Depression ◽  
Associated Risk Factors

Abstract Background: The prevalence of type 2 diabetes mellitus (T2DM) is growing in China. Both physical and psychological complications occur along with the development of T2DM. The patients with depression account for a significant proportion of T2DM. Depressive symptoms interfere with blood glucose management, leading to poorer treatment outcome and even relate to the occurrence of other serious complications of T2DM population. Among these T2DM patients with depression, early detection and treatment is essential and effective. Knowledge of the current prevalence of depression in T2DM patients as well as associated risk factors may be meaningful for healthcare planning. Therefore, we plan to conduct a systematic review and meta-analysis to evaluate the Chinese prevalence of depression in T2DM and explore associated risk factors.Methods: We will search literatures recorded in MEDLINE/PubMed, EMBASE, the Cochrane Library, Chinese Biomedical Literature Database (CBM), China National Knowledge Infrastructure (CNKI), Chinese Science and Technology Periodical Database (VIP), and Wanfang database (Wanfang Data). The grey literatures and reference list will be manually searched. We will include population-based, cross-sectional surveys that investigated the Chinese prevalence of depression in T2DM or/and researched the possible risk factors. Two reviewers will screen studies, extract data and evaluate quality independently. We will assess inter-rater agreement between reviewers for study inclusion, data extraction, and study quality assessment using Kappa statistics. The primary outcome will be the pooled Chinese prevalence of depression in T2DM patients. The secondary outcome will contain the potential risk factors for depression in patients with T2DM. R software (version 3.6.1) and STATA software (version 12) will be used for data analysis.Discussion: This systematic review will provide comprehensive evidence of the Chinese prevalence and risk factors of depression in patients with T2DM. we expect to provide evidence basis for healthcare practitioners and policy makers to pay attention to the mental health of T2DM. Our data will highlight the need and importance of early detection and intervention for depression in patients with T2DM. Systematic review registration: PROSPERO CRD42020182979.

scholarly journals Evaluation of Metabolic Syndrome and Its Associated Risk Factors in Type 2 Diabetes: A Descriptive Cross-Sectional Study at the Komfo Anokye Teaching Hospital, Kumasi, Ghana

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Francis Agyemang-Yeboah ◽  
Benjamin Ackon Jnr. Eghan ◽  
Max Efui Annani-Akollor ◽  
Eliezer Togbe ◽  
Sampson Donkor ◽  
...  
Keyword(s):  
Risk Factors ◽  
Type 2 Diabetes ◽  
Metabolic Syndrome ◽  
Waist Circumference ◽  
Teaching Hospital ◽  
The Body ◽  
Diabetic Patients ◽  
Study Population ◽  
Associated Risk Factors

Background. Metabolic syndrome (MS) is a collection of cardiovascular risk factors comprising insulin resistance, dyslipidemia, obesity, and hypertension, which may cause further complications in diabetes. Although metabolic syndrome (MS) is increasing in incidence in diabetics and leading to significant cardiovascular diseases and mortality, there is dearth of data in Ghana. This study investigated metabolic syndrome, its prevalence, and its associated risk factors in type 2 diabetes at the Komfo Anokye Teaching Hospital, Kumasi, Ghana. Methods. The study involved 405 diabetic patients attending the Diabetic Clinic of the Komfo Anokye Teaching Hospital (KATH) Kumasi, in the Ashanti Region of Ghana. A well-structured questionnaire was used to obtain demographic background such as their age and gender. Anthropometric measurements were obtained using the Body Composition Monitor (Omron ® 500, Germany) which generated digital results on a screen and also by manual methods. Fasting venous blood was collected for the measurement of biochemical parameters comprising fasting plasma glucose (FPG), glycated haemoglobin (HbA1c), high density lipoprotein cholesterol (HDL-c), and triglyceride (TG). Metabolic syndrome was defined according to the National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III). Results. Out of the total of 405 participants, 81 were males and 324 were females, and the estimated mean age was 58.5 ± 9.9 years. The female patients exhibited higher mean waist circumference (WC) and mean hip circumference (HC) as well as an approximately higher body mass index than males (28.3 ± 5.1, 26.5 ± 4.2 for the female and male respectively). Overall, the prevalence of metabolic syndrome observed among the study population was 90.6%. Conclusions. The prevalence of metabolic syndrome observed among the study population was 90.6%, with a higher percentage in females than males. High triglyceride levels and high waist circumference were the main risk factors for MS in the diabetic population.

scholarly journals The comparison of machine learning methods for prediction study of type 2 diabetes mellitus’s drug design

2020 ◽  
Author(s):  
Nadya Asanul Husna ◽  
Alhadi Bustamam ◽  
Arry Yanuar ◽  
Devvi Sarwinda ◽  
Oky Hermansyah
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Drug Design ◽  
Learning Methods ◽  
Machine Learning Methods

scholarly journals Prevalence of Type 2 Diabetes and Associated Risk Factors Among Saharawi Refugees (P10-071-19)

2019 ◽  
Vol 3 (Supplement_1) ◽  
Author(s):  
Sigrun Henjum ◽  
Victoria Telle Hjellset ◽  
Marte Karoline Raberg Kjollesdal ◽  
Merethe Flaaten ◽  
Eivind Andersen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Type 2 Diabetes ◽  
Waist Circumference ◽  
Overweight And Obesity ◽  
Refugee Camps ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Increased Risk ◽  
Associated Risk Factors

Abstract Objectives Economic development, globalization and urbanization has resulted in a shift in dietary consumption and energy expenditure in low- and middle-income countries, called the Nutrition Transition. At the same time, the prevalence of type 2 diabetes (T2D) and associated co-morbidities are rising worldwide. The Saharawi refugees have been living in refugee camps in the Algerian desert since 1975 and are totally dependent on food aid. High prevalence of overweight and obesity has been reported among Saharawi women. Limited knowledge about the prevalence of T2D and associated risk factors exists in this population; therefore, the aim with this study was to address this gap in the literature. Methods A cross-sectional survey was carried out in five Saharawi refugee camps, in Algeria and 180 women and 175 men were randomly selected. Participants’ blood glucose levels was assessed by HbA1c measurements and diagnosed with diabetes if HbA1c ≥48 mmol/mol and prediabetes if HbA1c was between 42–47 mmol/mol. The Finnish Diabetes Risk Score (FINDRISK) was used to assess various risk factors for T2D. Results Mean HbA1c among the Saharawi refugees was 38 mmol/mol. Seven and 15% were diagnosed with T2D and prediabetes, respectively, and 26% and 19% were overweight and obese, respectively. According to FINDRISK, 9% of the participants had high risk of developing diabetes, 10% had moderate risk, 37% had some risk and 44% had low risk. In multiple logistic regression models, after controlling for age, gender, number of children, BMI and education, the strongest predictor for diabetes was waist circumference, OR (95% CI): 1.1 (1.0, 1.1). The strongest predictor for prediabetes was age and waist circumference OR (95% CI): 1.0 (1.0, 1.1) and OR (95% CI): 1.1 (1.0, 1.1), respectively. Conclusions We found moderate prevalence of diabetes among the Saharawi refugees; however a high proportion had prediabetes and were suffering from overweight and obesity. In light of this, the rates of T2D are likely to increase dramatically in the near future. The Saharawi health authorities should pay attention to the increased risk of diabetes in this in this vulnerable population. Funding Sources Oslo Metropolitan University.

Sign in / Sign up

Export Citation Format

Share Document