scholarly journals An explainable XGBoost–based approach towards assessing the risk of cardiovascular disease in patients with Type 2 Diabetes Mellitus

2020 ◽  
Author(s):  
Maria Athanasiou ◽  
Konstantina Sfrintzeri ◽  
Konstantia Zarkogianni ◽  
Anastasia Thanopoulou ◽  
Konstantina S. Nikita
Keyword(s):  
Diabetes Mellitus ◽  
Cardiovascular Disease ◽  
Risk Prediction ◽  
Prediction Models ◽  
Therapeutic Interventions ◽  
Gradient Boosting ◽  
Cvd Risk ◽  
Medical Visits ◽  
Extreme Gradient Boosting

<div> <div> <div> <p>Cardiovascular Disease (CVD) is an important cause of disability and death among individuals with Diabetes Mellitus (DM). International clinical guidelines for the management of Type 2 DM (T2DM) are founded on primary and secondary prevention and favor the evaluation of CVD related risk factors towards appropriate treatment initiation. CVD risk prediction models can provide valuable tools for optimizing the frequency of medical visits and performing timely preventive and therapeutic interventions against CVD events. The integration of explainability modalities in these models can enhance human understanding on the reasoning process, maximize transparency and embellish trust towards the models’ adoption in clinical practice. The aim of the present study is to develop and evaluate an explainable personalized risk prediction model for the fatal or non-fatal CVD incidence in T2DM individuals. An explainable approach based on the eXtreme Gradient Boosting (XGBoost) and the Tree SHAP (SHapley Additive exPlanations) method is deployed for the calculation of the 5-year CVD risk and the generation of individual explanations on the model’s decisions. Data from the 5- year follow up of 560 patients with T2DM are used for development and evaluation purposes. The obtained results (AUC=71.13%) indicate the potential of the proposed approach to handle the unbalanced nature of the used dataset, while providing clinically meaningful insights about the ensemble model’s decision process. </p> </div> </div> </div>

scholarly journals An explainable XGBoost–based approach towards assessing the risk of cardiovascular disease in patients with Type 2 Diabetes Mellitus

2020 ◽  
Author(s):  
Maria Athanasiou ◽  
Konstantina Sfrintzeri ◽  
Konstantia Zarkogianni ◽  
Anastasia Thanopoulou ◽  
Konstantina S. Nikita
Keyword(s):  
Diabetes Mellitus ◽  
Cardiovascular Disease ◽  
Risk Prediction ◽  
Prediction Models ◽  
Therapeutic Interventions ◽  
Gradient Boosting ◽  
Cvd Risk ◽  
Medical Visits ◽  
Extreme Gradient Boosting

<div> <div> <div> <p>Cardiovascular Disease (CVD) is an important cause of disability and death among individuals with Diabetes Mellitus (DM). International clinical guidelines for the management of Type 2 DM (T2DM) are founded on primary and secondary prevention and favor the evaluation of CVD related risk factors towards appropriate treatment initiation. CVD risk prediction models can provide valuable tools for optimizing the frequency of medical visits and performing timely preventive and therapeutic interventions against CVD events. The integration of explainability modalities in these models can enhance human understanding on the reasoning process, maximize transparency and embellish trust towards the models’ adoption in clinical practice. The aim of the present study is to develop and evaluate an explainable personalized risk prediction model for the fatal or non-fatal CVD incidence in T2DM individuals. An explainable approach based on the eXtreme Gradient Boosting (XGBoost) and the Tree SHAP (SHapley Additive exPlanations) method is deployed for the calculation of the 5-year CVD risk and the generation of individual explanations on the model’s decisions. Data from the 5- year follow up of 560 patients with T2DM are used for development and evaluation purposes. The obtained results (AUC=71.13%) indicate the potential of the proposed approach to handle the unbalanced nature of the used dataset, while providing clinically meaningful insights about the ensemble model’s decision process. </p> </div> </div> </div>

Determining the Cardiovascular Disease Risk Factor Knowledge and Related Factors Among Adults With Type 2 Diabetes Mellitus

2021 ◽  
pp. 105477382110464
Author(s):  
Emine Karaman ◽  
Aslı Kalkım ◽  
Banu Pınar Şarer Yürekli
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Cvd Risk Factors ◽  
Cvd Risk ◽  
Related Factors

In this study was to determine knowledge of cardiovascular disease (CVD) risk factors and to explore related factors among adults with type 2 diabetes mellitus (DM) who have not been diagnosed with CVD. This descriptive study was conducted with 175 adults. Data were collected individual identification form and Cardiovascular Disease Risk Factors Knowledge Level (CARRF-KL) scale. A negative correlation was found between age and CARRF-KL score. A significant difference was found between educational status and CARRF-KL score. The individuals described their health status as good, managed their condition with diet and exercise, received information from nurses, adults with DM in their family and those with no DM complications had significantly higher scores in CARRF-KL. The knowledge of an individual with DM about CVD risk factors should be assessed, CVD risks should be identified at an early stage, and individuals at risk should be subjected to screening.

Assessing 10-Year Cardiovascular Disease Risk in Malaysians With Type 2 Diabetes Mellitus: Framingham Cardiovascular Versus United Kingdom Prospective Diabetes Study Equations

2019 ◽  
Vol 31 (7) ◽  
pp. 622-632
Author(s):  
Sheng Qian Yew ◽  
Yook Chin Chia ◽  
Michael Theodorakis
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Type 2 Diabetes Mellitus ◽  
United Kingdom ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Cvd Risk ◽  
Fatal Stroke

In this study, we evaluated the performance of the Framingham cardiovascular disease (CVD) and the United Kingdom Prospective Diabetes Study (UKPDS) risk equations to predict the 10-year CVD risk among type 2 diabetes mellitus (T2DM) patients in Malaysia. T2DM patients (n = 660) were randomly selected, and their 10-year CVD risk was calculated using both the Framingham CVD and UKPDS risk equations. The performance of both equations was analyzed using discrimination and calibration analyses. The Framingham CVD, UKPDS coronary heart disease (CHD), UKPDS Fatal CHD, and UKPDS Stroke equations have moderate discrimination (area under the receiver operating characteristic [aROC] curve = 0.594-0.709). The UKPDS Fatal Stroke demonstrated a good discrimination (aROC curve = 0.841). The Framingham CVD, UKPDS Stroke, and UKPDS Fatal Stroke equations showed good calibration ( P = .129 to .710), while the UKPDS CHD and UKPDS Fatal CHD are poorly calibrated ( P = .035; P = .036). The UKPDS is a better prediction equation of the 10-year CVD risk among T2DM patients compared with the Framingham CVD equation.

scholarly journals Knowledge and Perceptions towards Cardiovascular Disease Prevention among Patients with Type 2 Diabetes Mellitus: A Review of Current Assessments and Recommendations

2020 ◽  
Vol 16 ◽  
Author(s):  
Mohamed Hassan Elnaem ◽  
Mahmoud E Elrggal ◽  
Nabeel Syed ◽  
Atta Abbas Naqvi ◽  
Muhammad Abdul Hadi
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Type 2 Diabetes Mellitus ◽  
Original Research ◽  
Knowledge Gaps ◽  
Cvd Risk ◽  
Cvd Prevention

Introduction: Patients with type 2 diabetes mellitus (T2DM) are at significantly higher risk of developing cardiovascular disease (CVD). There is scarcity of literature reviews that describes and summarises T2DM patients' knowledge and perception about CVD prevention. Objectives: To describe and summarise the assessment of knowledge and perceptions about CVD risk and preventive approaches among patients with T2DM. Methods: A scoping review methodology was adopted, and three scientific databases, Google Scholar, Science Direct and PubMed were searched using predefined search terms. A multistage screening process that considered relevancy, publication year (2009-2019), English language, and article type (original research) was followed. We formulated research questions focused on the assessment of levels of knowledge and perceptions of the illness relevant to CVD prevention and the identification of associated patients' characteristics. Results: A total of 16 studies were included. Patients were not confident to identify CVD risk and other clinical consequences that may occur in the prognostic pathway of T2DM. Furthermore, patients were less likely to identify all CV risk factors indicating a lack of understanding of the multi-factorial contribution of CVD risk. Patients' beliefs about medications were correlated with their level of adherence to medications for CVD prevention. Many knowledge gaps were identified, including the basic disease expectations at the time of diagnosis, identification of individuals' CVD risk factors and management aspects. Knowledge and perceptions were affected by patients' demographic characteristics, e.g., educational level, race, age, and area of residence. Conclusion: There are knowledge gaps concerning the understanding of CVD risk among patients with T2DM. The findings necessitate educational initiatives to boost CVD prevention among patients with T2DM. Furthermore, these should be individualised based on patients' characteristics and knowledge gaps, disease duration and estimated CVD risk.

scholarly journals Risk Prediction Models of Chronic Disease in Chinese Medicine: A Systematic Review

2021 ◽  
Author(s):  
Yi-tong Li ◽  
Yan Liu ◽  
Wei Yang ◽  
Xinlong Li ◽  
Deqiang Gao
Keyword(s):  
Diabetes Mellitus ◽  
Cardiovascular Disease ◽  
Chronic Disease ◽  
Chinese Medicine ◽  
Risk Prediction ◽  
Prediction Models ◽  
China National Knowledge Infrastructure ◽  
Laboratory Findings ◽  
Risk Prediction Models ◽  
Subjective Judgement

Abstract Objective: To summarize the risk prediction models of chronic disease in Chinese medicine, describe their performance, and assess suitability of clinical or administrative use. Methods: The China National Knowledge Infrastructure and Wanfang Data were searched through February 2021, and hand searches were performed of the retrieved reference lists. Dual review was conducted to identify studies of prediction models of chronic disease in Chinese medicine. Results: From 399 citations reviewed, 17 studies were included in the analysis. Most of the studies were from single-centers (50%) or did not external validated (81.25%). The sample sizes were smaller and the models’ discrimination were larger compared with studies in fully western medicine. All the models used both laboratory findings and subjective judgements from doctors or patients. 9 models concentrated on diabetes mellitus or cardiovascular disease, and showed better performance and clinical application. Conclusions: The prediction models of chronic disease in Chinese medicine have unique advantages due to their considerations of doctors’ and patients’ subjective judgement. Diabetes mellitus and cardiovascular disease prediction models were in higher quality and clinical usability. Efforts to improve their quality are needed as use becomes more widespread.

scholarly journals Acetylcarnitine Is Associated With Cardiovascular Disease Risk in Type 2 Diabetes Mellitus

2021 ◽  
Vol 12 ◽  
Author(s):  
Shuo Zhao ◽  
Ming-Li Liu ◽  
Bing Huang ◽  
Fu-Rong Zhao ◽  
Ying Li ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Type 2 Diabetes Mellitus ◽  
Disease Risk ◽  
Tertiary Care ◽  
Short Chain ◽  
Forward Selection ◽  
Cvd Risk

ObjectiveThis study aimed to identify the association between specific short-chain acylcarnitines and cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM).MethodWe retrieved 1,032 consecutive patients with T2DM who meet the inclusion and exclusion criteria from the same tertiary care center and extracted clinical information from electronic medical records from May 2015 to August 2016. A total of 356 T2DM patients with CVD and 676 T2DM patients without CVD were recruited. Venous blood samples were collected by finger puncture after 8 h fasting and stored as dried blood spots. Restricted cubic spline (RCS) analysis nested in binary logistic regression was used to identify possible cutoff points and obtain the odds ratios (ORs) and 95% confidence intervals (CIs) of short-chain acylcarnitines for CVD risk in T2DM. The Ryan–Holm step-down Bonferroni procedure was performed to adjust p-values. Stepwise forward selection was performed to estimate the effects of acylcarnitines on CVD risk.ResultThe levels of C2, C4, and C6 were elevated and C5-OH was decreased in T2DM patients with CVD. Notably, only elevated C2 was still associated with increased CVD inT2DM after adjusting for potential confounders in the multivariable model (OR = 1.558, 95%CI = 1.124–2.159, p = 0.008). Furthermore, the association was independent of previous adjusted demographic and clinical factors after stepwise forward selection (OR = 1.562, 95%CI = 1.132–2.154, p = 0.007).ConclusionsElevated C2 was associated with increased CVD risk in T2DM.

scholarly journals Roles of Anxiety and Depression in Predicting Cardiovascular Disease Among Patients With Type 2 Diabetes Mellitus: A Machine Learning Approach

2021 ◽  
Vol 12 ◽  
Author(s):  
Haiyun Chu ◽  
Lu Chen ◽  
Xiuxian Yang ◽  
Xiaohui Qiu ◽  
Zhengxue Qiao ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Type 2 Diabetes Mellitus ◽  
Integrated Treatment ◽  
Health Improvement ◽  
Cvd Risk ◽  
Test Set

Cardiovascular disease (CVD) is a major complication of type 2 diabetes mellitus (T2DM). In addition to traditional risk factors, psychological determinants play an important role in CVD risk. This study applied Deep Neural Network (DNN) to develop a CVD risk prediction model and explored the bio-psycho-social contributors to the CVD risk among patients with T2DM. From 2017 to 2020, 834 patients with T2DM were recruited from the Department of Endocrinology, Affiliated Hospital of Harbin Medical University, China. In this cross-sectional study, the patients' bio-psycho-social information was collected through clinical examinations and questionnaires. The dataset was randomly split into a 75% train set and a 25% test set. DNN was implemented at the best performance on the train set and applied on the test set. The receiver operating characteristic curve (ROC) analysis was used to evaluate the model performance. Of participants, 272 (32.6%) were diagnosed with CVD. The developed ensemble model for CVD risk achieved an area under curve score of 0.91, accuracy of 87.50%, sensitivity of 88.06%, and specificity of 87.23%. Among patients with T2DM, the top five predictors in the CVD risk model were body mass index, anxiety, depression, total cholesterol, and systolic blood pressure. In summary, machine learning models can provide an automated identification mechanism for patients at CVD risk. Integrated treatment measures should be taken in health management, including clinical care, mental health improvement, and health behavior promotion.

Cardiovascular disease prevention and therapy in women with Type 2 diabetes

2021 ◽  
Author(s):  
Camilla Cocchi ◽  
Francesca Coppi ◽  
Alberto Farinetti ◽  
Anna Vittoria Mattioli
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Type 2 Diabetes Mellitus ◽  
Cardiovascular Risk ◽  
Risk Category ◽  
Cvd Risk ◽  
Men And Women ◽  
Delay In Diagnosis

Cardiovascular disease (CVD) is the leading cause of death among men and women, although women are usually underdiagnosed and experience a delay in diagnosis. This also occurs in women with type 2 diabetes mellitus, despite the fact that diabetes is recognized as a major cardiovascular risk factor. Several factors influence the gap between diagnosis and treatment of cardiovascular disease in women: lack of perception of cardiovascular risk, effects of sex-related risk factors and the action of drugs in women. Women with Type 2 diabetes mellitus are more likely to be assigned a lower CVD risk category and to receive lifestyle counseling as well as less intensive CVD therapy compared with men. The present narrative review aims to analyze the risk of CVD in women with Type 2 diabetes mellitus and whether there is a difference between men and women in the efficacy of SGLT-2 inhibitors, new hypoglycemic drugs.

scholarly journals Importance of Prandial Glucose Regulation in the Management of Cardiovascular Complications in Type 2 Diabetes Mellitus

2013 ◽  
Vol 20 (1) ◽  
pp. 77-84
Author(s):  
Rodica Teodora Străchinariu
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Cardiovascular Disease ◽  
Postprandial Glucose ◽  
Cardiovascular Complications ◽  
Glucose Regulation ◽  
Cvd Risk ◽  
Apparent Paradox

AbstractThere is a worldwide epidemic increase in the number of type 2 diabetes (T2DM)patients who frequently associate with cardiovascular disease (CVD). There are datasuggesting that glycemic control does not substantially reduce CVD risk buthyperglycemia increases the risk of CVD. This apparent paradox could be explainedby the role of post-prandial hyperglycemia in the pathogenesis of cardiovascularcomplications in T2DM. There is numerous evidences, both experimental andclinical, for this association but controversies on this topic persist. The aim of thispaper was to review the current literature regarding the role of postprandial glucosein the genesis of CVD in T2DM.

Sign in / Sign up

Export Citation Format

Share Document