A risk prediction model for heart failure hospitalization in type 2 diabetes mellitus

Williams, Brent A.; Geba, Daniela; Cordova, Jeanine M.; Shetty, Sharash

doi:10.1002/clc.23298

Cited by 18 publications

(31 citation statements)

References 32 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been a trend for developing simultaneous risk equations for individual CVD outcomes in type 2 diabetes [35], or for stand-alone CVD complications such as MI [7], stroke [6,36], and HF [16]. We recommend that a global CVD risk score that predicts the combination of the main causes of morbidity and mortality in type 2 diabetes should be prioritised.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Contemporary Cardiovascular Risk Assessment for Type 2 Diabetes Including Heart Failure as an Outcome: The Fremantle Diabetes Study Phase II

Davis

Hellbusch

Hunter³

et al. 2020

JCM

View full text Add to dashboard Cite

Background: Type 2 diabetes (T2D) cardiovascular disease (CVD) risk assessment has limitations. The aim of this study was to develop a risk equation adding heart failure (HF) to conventional major adverse cardiovascular events (MACE, myocardial infarction, stroke, and CVD death) and allowing for non-CVD death. Methods: 1551 community-based people with T2D (mean age 66 years, 52% males) were followed from baseline in 2008–2011 for five years to the first CVD event/death. Cox and competing risk regression identified predictors of three-point MACE and four-point MACE (including HF). Discrimination was assessed by the area under the receiver-operating characteristic curve (AUC) and calibration by the Hosmer-Lemeshow test. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were determined for a 10% five-year CVD risk cut-off. Results: 143 participants (9.2%) experienced a three-point MACE during 7,111 person-years of follow-up and 245 (15.8%) a four-point MACE during 6,896 person-years. The best model was the competing risk four-point MACE (221 predicted events (14.3%), AUC 0.82 (95% CI: 0.79–0.85), Hosmer-Lemeshow test, p = 0.17, sensitivity 79.2%, specificity 68.1%, PPV 31.8%, NPV 94.6%) with validation in 177 adults with T2D from an independent population (AUC 0.81 (0.74–0.89). Conclusions: A validated four-point MACE competing risk model reliably predicts key T2D CVD outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

“…While the three-point MACE remains the conventional endpoint in intervention trials and risk calculation in type 2 diabetes, heart failure (HF) has emerged as an additional key outcome [15]. Stand-alone risk prediction equations for HF hospitalisation complicating type 2 diabetes have been developed [16].…”

Section: Introductionmentioning

confidence: 99%

Contemporary Cardiovascular Risk Assessment for Type 2 Diabetes Including Heart Failure as an Outcome: The Fremantle Diabetes Study Phase II

Davis

Hellbusch

Hunter³

et al. 2020

JCM

View full text Add to dashboard Cite

show abstract

“…112 Most selected studies included adults only, either up to 60 years old (n=11) 39,40,42,[44][45][46]64,82,96,98,99 or without an upper age limit (n=65). [35][36][37][38]43,[47][48][49][50][51][52][53][54][56][57][58][59][60][61][62][63][65][66][67][68][69][70][71][72][73][74][75][76][77][78][79][80][81][83][84]…”

Section: Studies and Models Descriptionmentioning

confidence: 99%

“…55 Most studies included people of diverse race/ethnicity (n=40). 35,39,47,48,51,52,[57][58][59][62][63][64]67,69,70,73,76,[79][80][81][82][83][84][85][86][87][88]93,[95][96][97][100][101][102][103][104][105][108][109][110] A small number of studies studied only either white people (n=2), 54,56 Black people (n=1) 48 or Asian people (n=9). [36][37][38]68,74,75,[89]…”

Section: Studies and Models Descriptionmentioning

confidence: 99%

“…We included 42 studies reporting 116 validated prediction models. 36,39,40,43,44,[47][48][49][50][51]53,60,[63][64][65][70][71][72][73][75][76][77][78][80][81][82]84,86,[88][89][90][92][93][94]96,100,105,[108][109][110] The most common outcomes predicted in these models were: fatal and non-fatal coronary heart diseases/myocardial infarction/heart failure (n=43/116), fatal and non-fatal cerebrovascular disease and stroke (n=10/116), revascularization surgery (n=1), and other unspecified or combined fatal and non-fatal cardiovascular conditions (n=63/116). Of these models, 6 focused on deaths from cardiovascular conditions.…”

Section: Cardiovascular Complicationsmentioning

confidence: 99%

See 1 more Smart Citation

A scoping review of the predictive models of diabetes complications

Ndjaboué¹,

Ngueta²,

Rochefort-Brihay³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

A machine learning tool for identifying newly diagnosed heart failure in individuals with known diabetes in primary care

Wändell,

Carlsson,

Eriksson

et al. 2024

ESC Heart Failure

View full text Add to dashboard Cite

AimsWe aimed to create a predictive model utilizing machine learning (ML) to identify new cases of congestive heart failure (CHF) in individuals with diabetes in primary health care (PHC) through the analysis of diagnostic data.MethodsWe used a sex‐ and age‐matched case–control design. Cases of new CHF were identified across all outpatient care settings 2015–2022 (n = 9098). We included individuals 30 years and above, by sex and age groups of 30–65 years and >65 years. The controls (five per case) were sampled from the individuals in 2015–2022 without CHF at any time between 2010 and 2022, in total 45 490. From the stochastic gradient boosting (SGB) technique model, we obtained a rank of the 10 most important factors related to newly diagnosed CHF in individuals with diabetes, with the normalized relative influence (NRI) score and a corresponding odds ratio of marginal effects (ORME). Area under curve (AUC) was calculated.ResultsFor women 30–65 years and >65 years, we identified 488 and 3240 new cases of CHF, respectively, and men 30–65 years and >65 years 1196 and 4174 new cases. Among the 10 most important factors in the four groups (divided by sex and lower and higher age) for newly diagnosed CHF, we found the number of visits 12 months before diagnosis (NRI 44.3%–55.9%), coronary artery disease (NRI 2.9%–7.8%), atrial fibrillation and flutter (NRI 6.6%–12.2%) and ‘abnormalities of breathing’ (ICD‐10 code R06) (NRI 2.6%–4.4%) were predictive in all groups. For younger women, a diagnosis of COPD (NRI 2.7%) contributed to the predictive effect, while for older women, oedema (NRI 3.1%) and number of years with diabetes (NRI 3.5%) contributed to the predictive effect. For men in both age groups, chronic renal disease had predictive effect (NRI 3.9%–5.1%) The model prediction of CHF among patients with diabetes was high, AUC around 0.85 for the four groups, and with sensitivity over 0.783 and specificity over 0.708 for all four groups.ConclusionsAn SGB model using routinely collected data about diagnoses and number of visits in primary care, can accurately predict risk for diagnosis of heart failure in individuals with diabetes. Age and sex difference in predictive factors warrant further examination.

show abstract

A risk prediction model for heart failure hospitalization in type 2 diabetes mellitus

Cited by 18 publications

References 32 publications

Contemporary Cardiovascular Risk Assessment for Type 2 Diabetes Including Heart Failure as an Outcome: The Fremantle Diabetes Study Phase II

Contemporary Cardiovascular Risk Assessment for Type 2 Diabetes Including Heart Failure as an Outcome: The Fremantle Diabetes Study Phase II

A scoping review of the predictive models of diabetes complications

A machine learning tool for identifying newly diagnosed heart failure in individuals with known diabetes in primary care

Contact Info

Product

Resources

About