Development and Validation of a Chronic Kidney Disease Prediction Model for Type 2 Diabetes Mellitus in Thailand

Tuntayothin, Wilailuck; Kerr, Stephen J.; Boonyakrai, Chanchana; Udomkarnjananun, Suwasin; Chukaew, Sumitra; Sakulbumrungsil, Rungpetch

doi:10.1016/j.vhri.2020.10.006

Cited by 3 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study found seven variables routinely collected in clinical care that could be used to predict the risk of incident CKD or CKD progression, suggesting that this can easily be implemented in clinical practice and be integrated into electronic health records to identify people at increased risk of developing CKD. The results of our study are largely in line with other studies which reported that demographics such as gender as well as laboratory data such as HbA1c, serum creatinine and eGFR could be used in CKD prediction [ 13 , 14 , 18 , 42 ]. Our study also identified several other risk factors, such as presence of retinopathy and TG levels, for incident CKD and CKD progression.…”

Section: Discussionsupporting

confidence: 90%

“…[ 13 ] in Singapore examined CKD progression prediction among T2D patients using logistic regression while Tuntayothin et al . 2021 [ 14 ] in Thailand examined CKD disease prediction using Cox model, both of which had a good performance. The performance of our model is comparable to the existing studies for the primary outcome incident CKD model (C-index: 0.61–0.81) and secondary outcome of CKD progression (C-index: 0.73–0.85), albeit slightly lower [ 10 ].…”

Section: Discussionmentioning

confidence: 99%

“…These studies reported that individuals who were older in age, of Black, American Indian, Hispanic or Asian race, who had high albuminuria levels, high haemoglobin A1c (HbA1c), and comorbidities including hypertension, dyslipidaemia, obesity and smoking history were at higher risk of developing CKD [ 11 , 12 ]. However, very few studies have developed a prediction model for Asians with T2D [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of a chronic kidney disease predictive model for type 2 diabetes mellitus in Malaysia using Cox regression versus machine learning approach

Sim

Chong

Loganadan

et al. 2022

Clinical Kidney Journal

View full text Add to dashboard Cite

Background Diabetes is one of the leading cause of chronic kidney disease (CKD) and end stage renal disease. This study aims to develop and validate different risk predictive models for incident CKD and CKD progression in people with type 2 diabetes (T2D). Methods We reviewed a cohort of people with T2D seeking care from two tertiary hospitals in the metropolitan cities of the state of Selangor and Negeri Sembilan from January 2012 to May 2021. To identify the three-year predictor of developing CKD (primary outcome) and CKD progression (secondary outcome), the dataset was randomly split into a training and test set. A Cox proportional hazards (CoxPH) model was developed to identify for predictors of developing CKD. The resultant CoxPH model was compared with other machine learning models on their performance using C-statistic. Results The cohorts included 1 992 participants, of which 295 had developed CKD and 442 reported worsening of kidney function. Equation for the three-year risk of developing CKD included gender, haemoglobin A1c, triglyceride and serum creatinine levels, estimated glomerular filtration rate, history of cardiovascular disease and diabetes duration. For risk of CKD progression, the model included systolic blood pressure, retinopathy and proteinuria. The CoxPH model was better at prediction compared to other machine learning models examined for incident CKD (C-statistic: training 0.826; test 0.874) and CKD progression (C-statistic: training 0.611; test 0.655). Risk calculator can be found at https://rs59.shinyapps.io/071221/. Conclusions The Cox regression model was the best performing modelto predict people with T2D who will develop a 3-year risk of incident CKD and CKD progression in a Malaysian cohort.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of a chronic kidney disease predictive model for type 2 diabetes mellitus in Malaysia using Cox regression versus machine learning approach

Sim

Chong

Loganadan

et al. 2022

Clinical Kidney Journal

View full text Add to dashboard Cite

show abstract

“…Two studies were not retrieved because they were not fully published, leaving 31 studies retrieved for full-text analysis. Of these, 17 were eliminated because they 1) were prediction models for advanced CKD, 2) were about prevalence of CKD, 3) had insufficient data for analysis, or 4) had a sample that mixed type 2 diabetes and type 1 diabetes populations ( 9 ). From other methods (reference scanning, manual searching, and gray literature), 7 studies were retrieved.…”

Section: Resultsmentioning

confidence: 99%

Risk Prediction Score for Chronic Kidney Disease in Healthy Adults and Adults With Type 2 Diabetes: Systematic Review

2023

View full text Add to dashboard Cite

Introduction Chronic kidney disease (CKD) is an important public health problem. In 2017, the global prevalence was estimated at 9.1%. Appropriate tools to predict the risk of developing CKD are necessary to prevent its progression. Type 2 diabetes is a leading cause of CKD; screening the population living with the disease is a cost-effective solution to prevent CKD. The aim of our study was to identify the existing prediction scores and their diagnostic accuracy for detecting CKD in apparently healthy populations and populations with type 2 diabetes. Methods We conducted an electronic search in databases, including Medline/PubMed, Embase, Health Evidence, and others. For the inclusion criteria we considered studies with a risk predictive score in healthy populations and populations with type 2 diabetes. We extracted information about the models, variables, and diagnostic accuracy, such as area under the receiver operating characteristic curve (AUC), C statistic, or sensitivity and specificity. Results We screened 2,359 records and included 13 studies for healthy population, 7 studies for patients with type 2 diabetes, and 1 for both populations. We identified 12 models for patients with type 2 diabetes; the range of C statistic was from 0.56 to 0.81, and the range of AUC was from 0.71 to 0.83. For healthy populations, we identified 36 models with the range of C statistics from 0.65 to 0.91, and the range of AUC from 0.63 to 0.91. Conclusion This review identified models with good discriminatory performance and methodologic quality, but they need more validation in populations other than those studied. This review did not identify risk models with variables comparable between them to enable conducting a meta-analysis.

show abstract

“…As the DK instrument measures knowledge of diabetes, its items are binary (correct or incorrect answers) [25]. Consequently, standard factor analytic techniques which are designed for quantitative items are inappropriate.…”

Section: Measurement Of Diabetes Knowledgementioning

confidence: 99%

The Factor of Association of Diabetes Knowledge in Diabetes Mellitus type 2 patients

Sangruangake

Srisuwan

Ruangsuksud

et al. 2022

Dis.Prev.Public Heal J.

View full text Add to dashboard Cite

Background: T2DM is a chronic illness associated with numerous comorbidities and leads to chronic complications, resulting in high morbidity and mortality, rising health care costs. However, patients with this disease, through self-care, can significantly mitigate the risk, or delay the onset of these T2DM complications Objective: To investigate factors along with Diabetes Knowledge Method: A cross-sectional study was carried out among T2DM patients living in both rural and urban areas from the Central and Northeastern regions of Thailand were recruited from outpatient diabetes clinics of both community and university hospitals in both the Khon Kaen and Bangkok provinces of Thailand. Patients were sampled using a stratified sampling design where strata were based on locality (Province) - hospital size combinations. Firstly, we had translated all questionnaires from English to the local language then again back translated simultaneously. Then, the third step was to perform psychometric testing of the DK instrument Lastly, binary logistics mixed effect regression was used to investigate the clustering effect of the participant’s characteristic on this study. Results: After adjust for covariates derivate that age, KK and smaller hospitals, higher education, monthly income, underweight and overweight, DM treatment, and smoking nor alcohol where all found to be associated with various DK Conclusion: In future DK measurement is likely to provide valuable insights in to the epidemiology of diabetes self-management and may also be used to evaluate interventions to reduce poor self-care in T2DM patients, in turn, politically reducing the incidence of, and mortality from, type 2 diabetes mellitus complications.

show abstract

Development and Validation of a Chronic Kidney Disease Prediction Model for Type 2 Diabetes Mellitus in Thailand

Cited by 3 publications

References 34 publications

Comparison of a chronic kidney disease predictive model for type 2 diabetes mellitus in Malaysia using Cox regression versus machine learning approach

Comparison of a chronic kidney disease predictive model for type 2 diabetes mellitus in Malaysia using Cox regression versus machine learning approach

Risk Prediction Score for Chronic Kidney Disease in Healthy Adults and Adults With Type 2 Diabetes: Systematic Review

The Factor of Association of Diabetes Knowledge in Diabetes Mellitus type 2 patients

Contact Info

Product

Resources

About