Predicting incident heart failure among patients with type 2 diabetes mellitus: The DM-CURE risk score

Leveraging calcium score CT radiomics for heart failure risk prediction

Studies have used extensive clinical information to predict time-to-heart failure (HF) in patients with and without diabetes mellitus (DM). We aimed to determine a screening method using only computed tomography calcium scoring (CTCS) to assess HF risk. We analyzed CTCS scans from 1,998 patients (336 with type 2 diabetes) from a no-charge coronary artery calcium score registry (CLARIFY Study, Clinicaltrials.gov NCT04075162). We used deep learning to segment epicardial adipose tissue (EAT) and engineered radiomic features of calcifications ("calcium-omics") and EAT ("fat-omics"). We developed models incorporating radiomics to predict risk of incident HF in patients with and without type 2 diabetes. At a median follow-up of 1.7 years, 5% had incident HF. In the overall cohort, fat-omics (C-index: 77.3) outperformed models using clinical factors, EAT volume, Agatston score, calcium-omics, and calcium-and-fat-omics to predict HF. For DM patients, the calcium-omics model (C-index: 81.8) outperformed other models. In conclusion, CTCS-based models combining calcium and fat-omics can predict incident HF, outperforming prediction scores based on clinical factors.Please check article title if captured correctly.YesPlease check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary.Yes.

Prediction of new-onset heart failure in patients with type 2 diabetes derived from ALTITUDE and CANVAS

AIM

To create and validate a prediction model to identify patients with type 2 diabetes (T2D) at high risk of new-onset heart failure (HF), including those treated with a sodium-glucose cotransporter-2 (SGLT2) inhibitor.

METHODS

A prediction model was developed from the Aliskiren Trial in Type 2 Diabetes Using Cardiorenal Endpoints (ALTITUDE), a trial in T2D patients with albuminuria or cardiovascular disease. We included 5081 patients with baseline N-terminal pro B-type natriuretic peptide (NT-proBNP) measurement and no history of HF. The model was developed using Cox regression and validated externally in the placebo arm of the Canagliflozin Cardiovascular Assessment Study (CANVAS), which included 996 participants with T2D and established cardiovascular disease or high cardiovascular risk, and in patients treated with canagliflozin.

RESULTS

ALTITUDE participants (mean age 64 ± 9.8 years) had a median serum NT-proBNP level of 157 (25th-75th percentile 70-359) pg/mL. Higher NT-proBNP level, troponin T (TnT) level and body mass index (BMI) emerged as significant and independent predictors of new-onset HF in both cohorts. The model further contained urinary albumin-to-creatinine ratio, glycated haemoglobin, age, haematocrit, and use of calcium channel blockers. A prediction model including these variables had a C-statistic of 0.828 (95% confidence interval [CI] 0.801-0.855) in ALTITUDE and 0.800 (95% CI 0.720-0.880) in CANVAS. The C-statistic of this model increased to 0.847 (95% CI 0.792-0.902) in patients after 1 year of canagliflozin treatment.

CONCLUSION

In patients with T2D, higher NT-proBNP level, TnT level and BMI are independent and externally validated predictors of new-onset HF, including patients using an SGLT2 inhibitor. This newly developed model may identify patients at high risk of new-onset HF, contributing to early recognition and possibly prevention.

Diabetic myocardial disorder. A clinical consensus statement of the Heart Failure Association of the ESC and the ESC Working Group on Myocardial & Pericardial Diseases

The association between type 2 diabetes mellitus (T2DM) and heart failure (HF) has been firmly established; however, the entity of diabetic myocardial disorder (previously called diabetic cardiomyopathy) remains a matter of debate. Diabetic myocardial disorder was originally described as the occurrence of myocardial structural/functional abnormalities associated with T2DM in the absence of coronary heart disease, hypertension and/or obesity. However, supporting evidence has been derived from experimental and small clinical studies. Only a minority of T2DM patients are recognized as having this condition in the absence of contributing factors, thereby limiting its clinical utility. Therefore, this concept is increasingly being viewed along the evolving HF trajectory, where patients with T2DM and asymptomatic structural/functional cardiac abnormalities could be considered as having pre-HF. The importance of recognizing this stage has gained interest due to the potential for current treatments to halt or delay the progression to overt HF in some patients. This document is an expert consensus statement of the Heart Failure Association of the ESC and the ESC Working Group on Myocardial & Pericardial Diseases. It summarizes contemporary understanding of the association between T2DM and HF and discuses current knowledge and uncertainties about diabetic myocardial disorder that deserve future research. It also proposes a new definition, whereby diabetic myocardial disorder is defined as systolic and/or diastolic myocardial dysfunction in the presence of diabetes. Diabetes is rarely exclusively responsible for myocardial dysfunction, but usually acts in association with obesity, arterial hypertension, chronic kidney disease and/or coronary artery disease, causing additive myocardial impairment.

Optimal Screening for Predicting and Preventing the Risk of Heart Failure Among Adults With Diabetes Without Atherosclerotic Cardiovascular Disease: A Pooled Cohort Analysis

BACKGROUND

The optimal approach to identify individuals with diabetes who are at a high risk for developing heart failure (HF) to inform implementation of preventive therapies is unknown, especially in those without atherosclerotic cardiovascular disease (ASCVD).

METHODS

Adults with diabetes and no HF at baseline from 7 community-based cohorts were included. Participants without ASCVD who were at high risk for developing HF were identified using 1-step screening strategies: risk score (WATCH-DM [Weight, Age, Hypertension, Creatinine, HDL-C, Diabetes Control, QRS Duration, MI, and CABG] ≥12), NT-proBNP (N-terminal pro-B-type natriuretic peptide ≥125 pg/mL), hs-cTn (high-sensitivity cardiac troponin T ≥14 ng/L; hs-cTnI ≥31 ng/L), and echocardiography-based diabetic cardiomyopathy (echo-DbCM; left atrial enlargement, left ventricular hypertrophy, or diastolic dysfunction). High-risk participants were also identified using 2-step screening strategies with a second test to identify residual risk among those deemed low risk by the first test: WATCH-DM/NT-proBNP, NT-proBNP/hs-cTn, NT-proBNP/echo-DbCM. Across screening strategies, the proportion of HF events identified, 5-year number needed to treat and number needed to screen to prevent 1 HF event with an SGLT2i (sodium-glucose cotransporter 2 inhibitor) among high-risk participants, and cost of screening were estimated.

RESULTS

The initial study cohort included 6293 participants (48.2% women), of whom 77.7% without prevalent ASCVD were evaluated with different HF screening strategies. At 5-year follow-up, 6.2% of participants without ASCVD developed incident HF. The 5-year number needed to treat to prevent 1 HF event with an SGLT2i among participants without ASCVD was 43 (95% CI, 29-72). In the cohort without ASCVD, high-risk participants identified using 1-step screening strategies had a low 5-year number needed to treat (22 for NT-proBNP to 37 for echo-DbCM). However, a substantial proportion of HF events occurred among participants identified as low risk using 1-step screening approaches (29% for echo-DbCM to 47% for hs-cTn). Two-step screening strategies captured most HF events (75-89%) in the high-risk subgroup with a comparable 5-year number needed to treat as the 1-step screening approaches (30-32). The 5-year number needed to screen to prevent 1 HF event was similar across 2-step screening strategies (45-61). However, the number of tests and associated costs were lowest for WATCH-DM/NT-proBNP ($1061) compared with other 2-step screening strategies (NT-proBNP/hs-cTn: $2894; NT-proBNP/echo-DbCM: $16 358).

CONCLUSIONS

Selective NT-proBNP testing based on the WATCH-DM score efficiently identified a high-risk primary prevention population with diabetes expected to derive marked absolute benefits from SGLT2i to prevent HF.

Machine learning identification of risk factors for heart failure in patients with diabetes mellitus with metabolic dysfunction associated steatotic liver disease (MASLD): the Silesia Diabetes-Heart Project

BACKGROUND

Diabetes mellitus (DM), heart failure (HF) and metabolic dysfunction associated steatotic liver disease (MASLD) are overlapping diseases of increasing prevalence. Because there are still high numbers of patients with HF who are undiagnosed and untreated, there is a need for improving efforts to better identify HF in patients with DM with or without MASLD. This study aims to develop machine learning (ML) models for assessing the risk of the HF occurrence in patients with DM with and without MASLD.

RESEARCH DESIGN AND METHODS

In the Silesia Diabetes-Heart Project (NCT05626413), patients with DM with and without MASLD were analyzed to identify the most important HF risk factors with the use of a ML approach. The multiple logistic regression (MLR) classifier exploiting the most discriminative patient's parameters selected by the χ2 test following the Monte Carlo strategy was implemented. The classification capabilities of the ML models were quantified using sensitivity, specificity, and the percentage of correctly classified (CC) high- and low-risk patients.

RESULTS

We studied 2000 patients with DM (mean age 58.85 ± SD 17.37 years; 48% women). In the feature selection process, we identified 5 parameters: age, type of DM, atrial fibrillation (AF), hyperuricemia and estimated glomerular filtration rate (eGFR). In the case of MASLD( +) patients, the same criterion was met by 3 features: AF, hyperuricemia and eGFR, and for MASLD(-) patients, by 2 features: age and eGFR. Amongst all patients, sensitivity and specificity were 0.81 and 0.70, respectively, with the area under the receiver operating curve (AUC) of 0.84 (95% CI 0.82-0.86).

CONCLUSION

A ML approach demonstrated high performance in identifying HF in patients with DM independently of their MASLD status, as well as both in patients with and without MASLD based on easy-to-obtain patient parameters.

A prediction model on incident chronic kidney disease among individuals with type 2 diabetes in the United States

AIM

Early identification of incident chronic kidney disease (CKD) in individuals with diabetes may help improve patients' clinical outcomes. This study aimed to develop a prediction equation for incident CKD among people with type 2 diabetes (T2D).

MATERIALS AND METHODS

A time-varying Cox model was applied to data from the ACCORD trial to predict the risk of incident CKD. A list of candidate variables was chosen based on literature reviews and experts' consultations, including demographic characteristics, vitals, laboratory results, medical history, drug use and health care utilization. Model performance was evaluated. Decomposition analysis was conducted, and external validation was performed.

RESULTS

In total, 6006 patients with diabetes free of CKD were included, with a median follow-up of 3 years and 2257 events. The risk model included age at T2D diagnosed, smoking status, body mass index, high-density lipoprotein, very-low-density lipoprotein, alanine aminotransferase, estimated glomerular filtration rate, urine albumin-creatinine ratio, hypoglycaemia, retinopathy, congestive heart failure, coronary heart disease history, antihyperlipidaemic drug use, antihypertensive drug use and hospitalization. The urine albumin-creatinine ratio, estimated glomerular filtration rate and congestive heart failure were the top three factors that contributed most to the incident CKD prediction. The model showed acceptable discrimination [C-statistic: 0.772 (95% CI 0.767-0.805)] and calibration [Brier Score: 0.0504 (95% CI 0.0477-0.0531)] in the Harmony Outcomes Trial.

CONCLUSION

Incident CKD prediction among individuals with T2D was developed and validated for use in decision support of CKD prevention.

Prognostic models for heart failure in patients with type 2 diabetes: a systematic review and meta-analysis

OBJECTIVE

To provide a systematic review, critical appraisal, assessment of performance and generalisability of all the reported prognostic models for heart failure (HF) in patients with type 2 diabetes (T2D).

METHODS

We performed a literature search in Medline, Embase, Central Register of Controlled Trials, Cochrane Database of Systematic Reviews and Scopus (from inception to July 2022) and grey literature to identify any study developing and/or validating models predicting HF applicable to patients with T2D. We extracted data on study characteristics, modelling methods and measures of performance, and we performed a random-effects meta-analysis to pool discrimination in models with multiple validation studies. We also performed a descriptive synthesis of calibration and we assessed the risk of bias and certainty of evidence (high, moderate, low).

RESULTS

Fifty-five studies reporting on 58 models were identified: (1) models developed in patients with T2D for HF prediction (n=43), (2) models predicting HF developed in non-diabetic cohorts and externally validated in patients with T2D (n=3), and (3) models originally predicting a different outcome and externally validated for HF (n=12). RECODe (C-statistic=0.75 95% CI (0.72, 0.78), 95% prediction interval (PI) (0.68, 0.81); high certainty), TRS-HFDM (C-statistic=0.75 95% CI (0.69, 0.81), 95% PI (0.58, 0.87); low certainty) and WATCH-DM (C-statistic=0.70 95% CI (0.67, 0.73), 95% PI (0.63, 0.76); moderate certainty) showed the best performance. QDiabetes-HF demonstrated also good discrimination but was externally validated only once and not meta-analysed.

CONCLUSIONS

Among the prognostic models identified, four models showed promising performance and, thus, could be implemented in current clinical practice.

A prediction model on incident ESKD among individuals with T2D and CKD

BACKGROUND

Diabetes is the leading cause of end-stage kidney disease (ESKD). This study aimed to predict incident ESKD among individuals with T2D and CKD.

METHOD

The Action to Control Cardiovascular Risk in Diabetes (ACCORD) clinical trial data were split into a training set and a validation set by a ratio of 7:3. A dynamic time-varying Cox model was fit to predict the development of incident ESKD. Significant predictors were identified from a list of candidate variables, including demographic characteristics, physical exam results, laboratory results, medical history, drug information, and healthcare utilization. Model performance was evaluated by Brier score and C statistics. Decomposition analysis was conducted to assess the variable importance. Patient-level data from Harmony Outcome clinical trial and CRIC study were used for external validation.

RESULTS

A total of 6982 diabetes patients with CKD were used for model development, with a median follow-up of four years and 312 ESKD events. The significant predictors for the final model were female sex, race, smoking status, age at T2D diagnosis, SBP, HR, HbA1c, estimated glomerular filtration rate (eGFR), urine albumin-creatinine ratio (UACR), retinopathy event occurring in last year, antihypertensive drug use, and an interaction term between SBP and female. The model demonstrated good performance in discrimination (C-statistic 0.764 [95 % CI 0.763-0.811]) and calibration (Brier Score 0.0083 [95 % CI 0.0063-0.0108]). The top 3 most important predictors in the prediction model were eGFR, retinopathy event, and UACR. Acceptable discrimination (C-statistic: 0.701 [95 % CI 0.665-0.716]; 0.86 [95 % CI 0.847-0.872]) and calibration (Brier Score: 0.0794 [95 % CI 0.0733-0.1022]; 0.0476 [95 % CI 0.0440, 0.0506]) were demonstrated in the Harmony Outcome and CRIC data, respectively.

CONCLUSION

The dynamic risk prediction of incident ESKD among individuals with T2D can be a useful tool to support better disease management to lower the risk of developing ESKD.

A prediction model of CKD progression among individuals with type 2 diabetes in the United States

BACKGROUND

CKD progression among individuals with T2D is associated with poor health outcomes and high healthcare costs, which have not been fully studied. This study aimed to predict CKD progression among individuals with diabetes.

METHOD

Using ACCORD trial data, a time-varying Cox model was developed to predict the risk of CKD progression among patients with CKD and T2D. CKD progression was defined as a 50 % decline, or 25 mL/min/1.73 m² decline in eGFR from baseline, doubling of the serum creatinine, or onset of ESKD. A list of candidate variables included demographic characteristics, physical exam results, laboratory results, medical history, drug use, and healthcare utilization. A stepwise algorithm was used for variable selection. Model performance was evaluated by Brier score and C-statistics. Confidence intervals (CI) were calculated using a bootstrap method. Decomposition analysis was conducted to assess the predictor contribution. Generalizability was assessed on patient-level data of the Harmony Outcome trial and CRIC study.

RESULTS

A total of 6982 diabetes patients with CKD were used for model development, with a median follow-up of 4 years and 3346 events. The predictors for CKD progression included female sex, age at T2D diagnosis, smoking status, SBP, DBP, HR, HbA1c, alanine aminotransferase (ALT), eGFR, UACR, retinopathy event, hospitalization. The model demonstrated good discrimination (C-statistics 0.745 [95 % CI 0.723-0.763]) and calibration (Brier Score 0.0923 [95 % CI 0.0873-0.0965]) performance in the ACCORD data. The most contributing predictors for CKD progression were eGFR, HbA1c, and SBP. The model demonstrated acceptable discrimination and calibration performance in the two external data.

CONCLUSION

For high-risk patients with both diabetes and CKD, the tool as a dynamic risk prediction of CKD progression may help develop novel strategies to lower the risk of CKD progression.