A Framework to Understand the Progression of Cardiovascular Disease for Type 2 Diabetes Mellitus Patients Using a Network Approach

Hossain, Ekramul; Uddin, Shahadat; Khan, Arif; Moni, Mohammad Ali

doi:10.3390/ijerph17020596

Cited by 20 publications

(10 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have attempted to predict T2D outcomes using a variety of machine learning techniques [19,21,29,29,40,51,57 method named Prediction algorithm for the classification of T2D on imbalanced data with Missing values (DMP_ MI) where NB compensated this missing records. The adaptive synthetic sampling method (ADASYN) was then used to balance this dataset and applied RF to achieve a classification result.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning models for classification and identification of significant attributes to detect type 2 diabetes

Howlader

Satu

Awal

et al. 2022

Health Inf Sci Syst

Self Cite

View full text Add to dashboard Cite

Type 2 Diabetes (T2D) is a chronic disease characterized by abnormally high blood glucose levels due to insulin resistance and reduced pancreatic insulin production. The challenge of this work is to identify T2D-associated features that can distinguish T2D sub-types for prognosis and treatment purposes. We thus employed machine learning (ML) techniques to categorize T2D patients using data from the Pima Indian Diabetes Dataset from the Kaggle ML repository. After data preprocessing, several feature selection techniques were used to extract feature subsets, and a range of classification techniques were used to analyze these. We then compared the derived classification results to identify the best classifiers by considering accuracy, kappa statistics, area under the receiver operating characteristic (AUROC), sensitivity, specificity, and logarithmic loss (logloss). To evaluate the performance of different classifiers, we investigated their outcomes using the summary statistics with a resampling distribution. Therefore, Generalized Boosted Regression modeling showed the highest accuracy (90.91%), followed by kappa statistics (78.77%) and specificity (85.19%). In addition, Sparse Distance Weighted Discrimination, Generalized Additive Model using LOESS and Boosted Generalized Additive Models also gave the maximum sensitivity (100%), highest AUROC (95.26%) and lowest logarithmic loss (30.98%) respectively. Notably, the Generalized Additive Model using LOESS was the top-ranked algorithm according to non-parametric Friedman testing. Of the features identified by these machine learning models, glucose levels, body mass index, diabetes pedigree function, and age were consistently identified as the best and most frequently accurate outcome predictors. These results indicate the utility of ML methods in constructing improved prediction models for T2D and successfully identified outcome predictors for this Pima Indian population.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Numerous studies have attempted to predict T2D outcomes using a variety of machine learning techniques [ 19 , 21 , 29 , 29 , 40 , 51 , 57 ]. Proposed methods were employed various data preprocessing and machine learning techniques to isolate T2D patients from controls.…”

Section: Related Workmentioning

confidence: 99%

Machine learning models for classification and identification of significant attributes to detect type 2 diabetes

Howlader

Satu

Awal

et al. 2022

Health Inf Sci Syst

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent developments in network medicine have led to a proliferation of studies that used complex networks for medical research to explore the comorbidity of various diseases [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. For instance, Hidalgo et al [ 29 ] used network methods to study the disease progression.…”

Section: Introductionmentioning

confidence: 99%

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

et al. 2022

View full text Add to dashboard Cite

Ischemic heart disease (IHD) exhibits elevated comorbidity. However, few studies have systematically analyzed the comorbid status of IHD patients with respect to the entire spectrum of chronic diseases. This study applied network analysis to provide a complete picture of physical and mental comorbidities in hospitalized patients with IHD using large-scale administrative data. Hospital discharge records from a provincial healthcare database of IHD inpatients (n = 1,035,338) and one-to-one matched controls were included in this retrospective analysis. We constructed the phenotypic disease networks in IHD and control patients and further assessed differences in comorbidity patterns. The community detection method was applied to cluster diagnoses within the comorbidity network. Age- and sex-specific patterns of IHD comorbidities were also analyzed. IHD inpatients showed 50% larger comorbid burden when compared to controls. The IHD comorbidity network consisted of 1941 significant associations between 71 chronic conditions. Notably, the more densely connected comorbidities in IHD patients were not within the highly prevalent ones but the rarely prevalent ones. Two highly interlinked communities were detected in the IHD comorbidity network, where one included hypertension with heart and multi-organ failures, and another included cerebrovascular diseases, cerebrovascular risk factors and anxiety. Males exhibited higher comorbid burden than females, and thus more complex comorbidity relationships were found in males. Sex-specific disease pairs were detected, e.g., 106 and 30 disease pairs separately dominated in males and females. Aging accounts for the majority of comorbid burden, and the complexity of the comorbidity network increased with age. The network-based approach improves our understanding of IHD-related comorbidities and enhances the integrated management of patients with IHD.

show abstract

“…Cardiovascular disease (CVD) is the leading cause of death in patients with type 2 diabetes mellitus (T2DM) worldwide [ 1 ]. CVD risks are often considered the main indicator of safety issues in the evaluation of glucose-lowering therapies [ 2 , 3 ].…”

Section: Introductionmentioning

confidence: 99%

Generalizability of the Results of Cardiovascular Outcome Trials of Glucagon-Like Peptide 1 Receptor Agonists in Chinese Patients with Type 2 Diabetes Mellitus

Cai

2021

Diabetes Ther

View full text Add to dashboard Cite

Introduction: This study aimed to investigate the generalizability of the results of cardiovascular outcome trials (CVOTs) of glucagon-like peptide 1 receptor agonists (GLP-1 RAs) to Chinese patients with type 2 diabetes mellitus (T2DM). Methods: The 3B (Blood Glucose, Blood Pressure, and Blood Lipid) population, a nationally representative population of patients with T2DM in China (n = 25,411), was examined for eligibility of enrollment in four GLP-1 RAs CVOTs (Dulaglutide-REWIND, Exenatide-EXSCEL, Liraglutide-LEADER, and Semaglutide-SUSTAIN-6). We first estimated the proportion of 3B population who would meet the six inclusion and exclusion (I/E) criteria, namely age, hemoglobin A1c (HbA1c), body mass index (BMI), estimated glomerular filtration rate (eGFR), history of cardiovascular disease (CVD), and antidiabetic medication, in each CVOT. Then we compared 11 baseline characteristics, namely age, gender, duration of diabetes, HbA1c, BMI, eGFR, history of CVD, prior myocardial infarction (MI), low-density lipoprotein cholesterol (LDL-c), diastolic blood pressure (DBP), and systolic blood pressure, between the population in each CVOT and the 3B population. Lastly, we estimated the proportion of 3B population that matched the characteristics in each CVOT population. Results: On the basis of the I/E criteria, 31.1% of the 3B population would have been eligible for enrollment in REWIND, 15.0% for SUSTAIN-6, 12.9% for LEADER, and 11.3% for EXSCEL. On the basis of the baseline characteristics, REWIND most closely matched the 3B population on gender, duration of diabetes, HbA1c, DBP, LDL-c, history of CVD, and prior MI. The proportion of 3B population matching on at least eight or at least ten baseline characteristics with CVOT populations was highest for REWIND compared to other CVOTs. Conclusion: Among the four GLP-1 RA CVOTs, the REWIND trial using once-weekly dulaglutide is most generalizable to Chinese patients with T2DM. TrialRegistration: Trial registration: NCT01128205 (www.clinicaltrials.gov).

show abstract

A Framework to Understand the Progression of Cardiovascular Disease for Type 2 Diabetes Mellitus Patients Using a Network Approach

Cited by 20 publications

References 48 publications

Machine learning models for classification and identification of significant attributes to detect type 2 diabetes

Machine learning models for classification and identification of significant attributes to detect type 2 diabetes

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

Generalizability of the Results of Cardiovascular Outcome Trials of Glucagon-Like Peptide 1 Receptor Agonists in Chinese Patients with Type 2 Diabetes Mellitus

Contact Info

Product

Resources

About