Cardiovascular risk prediction in type 2 diabetes: a comparison of 22 risk scores in primary care settings

Digital twins: reimagining the future of cardiovascular risk prediction and personalised care

The rapid evolution of highly adaptable and reusable artificial intelligence models facilitates the implementation of digital twinning and has the potential to redefine cardiovascular risk prevention. Digital twinning combines vast amounts of data from diverse sources to construct virtual models of an individual. Emerging artificial intelligence models, called generalist AI, enable the processing of different types of data, including data from electronic health records, laboratory results, medical texts, imaging, genomics, or graphs. Among their unprecedented capabilities are an easy adaptation of a model to previously unseen medical tasks and the ability to reason and explain output using precise medical language derived from scientific literature, medical guidelines, or knowledge graphs. The proposed combination of a digital twinning approach with generalist AI is a path to accelerate the implementation of precision medicine and enhance early recognition and prevention of cardiovascular disease. This proposed strategy may extend to other domains to advance predictive, preventive, and precision medicine and also boost health research discoveries.

Plasma 16:0 ceramide as a marker of cardiovascular risk estimated by carotid intima-media thickness in people with type 2 diabetes

AIM

New tools are required to better assess cardiovascular risk in individuals with type 2 diabetes mellitus (T2DM). Plasma ceramides emerge as promising candidates, given their substantial influence on the pathogenesis of both T2DM and atherosclerosis. The current study aimed to investigate whether plasma ceramides in patients with T2DM are a predictive factor for carotid intima-media thickness (CIMT), a well-established noninvasive marker for atherosclerosis that predicts adverse cardiovascular outcomes.

METHODS

A lipidomic analysis was carried out on the circulating ceramides of a large cohort consisting of 246 patients with T2DM who underwent a high-resolution real-time B ultrasonography to measure CIMT.

RESULTS

Both plasma 16:0 ceramide and the 16:0/24:0 ceramide ratio were positively associated with CIMT, even after adjustment for traditional cardiovascular risk factors [standardized β ± standard error: 0.168 ± 0.072 (P = 0.020) and 0.180 ± 0.068 (P = 0.009), respectively]. Similar independent associations were found with respect to the prediction of CIMT ≥ 0.80 mm [β = 8.07 ± 3.90 (P = 0.038) and 16.5 ± 7.0 (P = 0.019), respectively]. The goodness-of-fit for multivariate models in predicting CIMT was 5.7 and 7.6 times higher when plasma 16:0 ceramide or the 16:0/24:0 ceramide ratio were included in combination with traditional cardiovascular risk factors (P = 0.020 and 0.015, respectively). This reached a 3.1 and 10.0-fold increase regarding the ability to predict CIMT ≥ 0.80 mm (P = 0.039 and 0.008, respectively).

CONCLUSIONS

Our findings suggest that 16:0 ceramide and the 16:0/24:0 ceramide ratio may serve as plasma biomarkers to improve cardiovascular risk assessment in individuals with T2DM.

Risk Prediction Scores for Type 2 Diabetes Microvascular and Cardiovascular Complications Derived and Validated With Real-world Data From 2 Provinces: The DIabeteS COmplications (DISCO) Risk Scores

OBJECTIVES

Existing tools to predict the risk of complications among people with type 2 diabetes poorly discriminate high- from low-risk patients. Our aim in this study was to develop risk prediction scores for major type 2 diabetes complications using real-world clinical care data, and to externally validate these risk scores in a different jurisdiction.

METHODS

Using health-care administrative data and electronic medical records data, risk scores were derived using data from 25,088 people with type 2 diabetes from the Canadian province of Ontario, followed between 2002 and 2017. Scores were developed for major clinically important microvascular events (treatment for retinopathy, foot ulcer, incident end-stage renal disease), cardiovascular disease events (acute myocardial infarction, heart failure, stroke, amputation), and mortality (cardiovascular, noncardiovascular, all-cause). They were then externally validated using the independent data of 11,416 people with type 2 diabetes from the province of Manitoba.

RESULTS

The 10 derived risk scores had moderate to excellent discrimination in the independent validation cohort, ranging from 0.705 to 0.977. Their calibration to predict 5-year risk was excellent across most levels of predicted risk, albeit with some displaying underestimation at the highest levels of predicted risk.

CONCLUSIONS

The DIabeteS COmplications (DISCO) risk scores for major type 2 diabetes complications were derived and externally validated using contemporary real-world clinical data. As a result, they may be more accurate than other risk prediction scores derived using randomized trial data. The use of more accurate risk scores in clinical practice will help improve personalization of clinical care for patients with type 2 diabetes.

Derivation of an Annualized Claims-Based Major Adverse Cardiovascular Event Estimator in Type 2 Diabetes

Background

Major adverse cardiovascular events (MACE) are a leading cause of morbidity and mortality among adults with type 2 diabetes. Currently, available MACE prediction models have important limitations, including reliance on data that may not be routinely available, narrow focus on primary prevention, limited patient populations, and longtime horizons for risk prediction.

Objectives

The purpose of this study was to derive and internally validate a claims-based prediction model for 1-year risk of MACE in type 2 diabetes.

Methods

Using medical and pharmacy claims for adults with type 2 diabetes enrolled in commercial, Medicare Advantage, and Medicare fee-for-service plans between 2014 and 2021, we derived and internally validated the annualized claims-based MACE estimator (ACME) model to predict the risk of MACE (nonfatal acute myocardial infarction, nonfatal stroke, and all-cause mortality). The Cox proportional hazards model was composed of 30 covariates, including patient age, sex, comorbidities, and medications.

Results

The study cohort comprised 6,623,526 adults with type 2 diabetes, mean age 68.1 ± 10.6 years, 49.8% women, and 73.0% Non-Hispanic White. ACME had a concordance index of 0.74 (validation index range: 0.739-0.741). The predicted 1-year risk of the study cohort ranged from 0.4% to 99.9%, with a median risk of 3.4% (IQR: 2.3%-6.5%).

Conclusions

ACME was derived in a large usual care population, relies on routinely available data, and estimates short-term MACE risk. It can support population risk stratification at the health system and payer levels, participant identification for decentralized clinical trials of cardiovascular disease, and risk-stratified observational studies using real-world data.

Erythrocyte membrane fluidity: A novel biomarker of residual cardiovascular risk in type 2 diabetes

AIMS

Improving the composition of circulating fatty acids (FA) leads to a reduction in cardiovascular diseases (CVD) in high-risk individuals. The membrane fluidity of red blood cells (RBC), which reflects circulating FA status, may be a valid biomarker of cardiovascular (CV) risk in type 2 diabetes (T2D).

METHODS

Red blood cell membrane fluidity, quantified as general polarization (GP), was assessed in 234 subjects with T2D, 86 with prior major CVD. Based on GP distribution, a cut-off of .445 was used to divide the study cohort into two groups: the first with higher GP, called GEL, and the second, defined as lower GP (LGP). Lipidomic analysis was performed to evaluate FA composition of RBC membranes.

RESULTS

Although with comparable CV risk factors, the LGP group had a greater percentage of patients with major CVD than the GEL group (40% vs 24%, respectively, p < .05). Moreover, in a logistic regression analysis, a lower GP value was independently associated with the presence of macrovascular complications. Lipidomic analysis showed a clear shift of LGP membranes towards a pro-inflammatory condition due to higher content of arachidonic acid and increased omega 6/omega 3 index.

CONCLUSIONS

Increased membrane fluidity is associated with a higher CV risk in subjects with T2D. If confirmed in prospective studies, membrane fluidity could be a new biomarker for residual CV risk assessment in T2D.

Non-alcoholic fatty liver disease biomarkers estimate cardiovascular risk based on coronary artery calcium score in type 2 diabetes: a cross-sectional study with two independent cohorts

BACKGROUND

Studies have demonstrated that coronary artery calcification on one hand and non-alcoholic fatty liver disease (NAFLD) on the other hand are strongly associated with cardiovascular events. However, it remains unclear whether NAFLD biomarkers could help estimate cardiovascular risk in individuals with type 2 diabetes (T2D). The primary objective of the present study was to investigate whether the biomarkers of NAFLD included in the FibroMax® panels are associated with the degree of coronary artery calcification in patients with T2D.

METHODS

A total of 157 and 460 patients with T2D were included from the DIACART and ACCoDiab cohorts, respectively. The coronary artery calcium score (CACS) was measured in both cohorts using computed tomography. FibroMax® panels (i.e., SteatoTest®, FibroTest®, NashTest®, and ActiTest®) were determined from blood samples as scores and stages in the DIACART cohort and as stages in the ACCoDiab cohort.

RESULTS

CACS significantly increased with the FibroTest® stages in both the DIACART and ACCoDiab cohorts (p-value for trend = 0.0009 and 0.0001, respectively). In DIACART, the FibroTest® score was positively correlated with CACS in univariate analysis (r = 0.293, p = 0.0002) and remained associated with CACS independently of the traditional cardiovascular risk factors included in the SCORE2-Diabetes model [β = 941 ± 425 (estimate ± standard error), p = 0.028]. In the ACCoDiab cohort, the FibroTest® F3-F4 stage was positively correlated with CACS in point-biserial analysis (rpbi = 0.104, p = 0.024) and remained associated with CACS after adjustment for the traditional cardiovascular risk factors included in the SCORE2-Diabetes model (β = 234 ± 97, p = 0.016). Finally, the prediction of CACS was improved by adding FibroTest® to the traditional cardiovascular risk factors included in the SCORE2-Diabetes model (goodness-of-fit of prediction models multiplied by 4.1 and 6.7 in the DIACART and ACCoDiab cohorts, respectively). In contrast, no significant relationship was found between FibroMax® panels other than FibroTest® and CACS in either cohort.

CONCLUSIONS

FibroTest® is independently and positively associated with the degree of coronary artery calcification in patients with T2D, suggesting that FibroTest® could be a relevant biomarker of coronary calcification and cardiovascular risk.

TRIAL REGISTRATION

ClinicalTrials.gov identifiers NCT02431234 and NCT03920683.

Blood Monocyte Phenotype Is A Marker of Cardiovascular Risk in Type 2 Diabetes

BACKGROUND

Diabetes is a major risk factor for atherosclerotic cardiovascular diseases with a 2-fold higher risk of cardiovascular events in people with diabetes compared with those without. Circulating monocytes are inflammatory effector cells involved in both type 2 diabetes (T2D) and atherogenesis.

METHODS

We investigated the relationship between circulating monocytes and cardiovascular risk progression in people with T2D, using phenotypic, transcriptomic, and metabolomic analyses. cardiovascular risk progression was estimated with coronary artery calcium score in a cohort of 672 people with T2D.

RESULTS

Coronary artery calcium score was positively correlated with blood monocyte count and frequency of the classical monocyte subtype. Unsupervised k-means clustering based on monocyte subtype profiles revealed 3 main endotypes of people with T2D at varying risk of cardiovascular events. These observations were confirmed in a validation cohort of 279 T2D participants. The predictive association between monocyte count and major adverse cardiovascular events was validated through an independent prospective cohort of 757 patients with T2D. Integration of monocyte transcriptome analyses and plasma metabolomes showed a disruption of mitochondrial pathways (tricarboxylic acid cycle, oxidative phosphorylation pathway) that underlined a proatherogenic phenotype.

CONCLUSIONS

In this study, we provide evidence that frequency and monocyte phenotypic profile are closely linked to cardiovascular risk in patients with T2D. The assessment of monocyte frequency and count is a valuable predictive marker for risk of cardiovascular events in patients with T2D.

REGISTRATION

URL: https://www.clinicaltrials.gov; Unique identifier: NCT04353869.

Identifying and ranking novel independent features for cardiovascular disease prediction in people with type 2 diabetes

Background

CVD prediction models do not perform well in people with diabetes. We therefore aimed to identify novel predictors for six facets of CVD, (including coronary heart disease (CHD), Ischemic stroke, heart failure (HF), and atrial fibrillation (AF)) in people with T2DM.

Methods

Analyses were conducted using the UK biobank and were stratified on history of CVD and of T2DM: 459,142 participants without diabetes or a history of CVD, 14,610 with diabetes but without CVD, and 4,432 with diabetes and a history of CVD. Replication was performed using a 20% hold-out set, ranking features on their permuted c-statistic.

Results

Out of the 600+ candidate features, we identified a subset of replicated features, ranging between 32 for CHD in people with diabetes to 184 for CVD+HF+AF in people without diabetes. Classical CVD risk factors (e.g. parental or maternal history of heart disease, or blood pressure) were relatively highly ranked for people without diabetes. The top predictors in the people with diabetes without a CVD history included: cystatin C, self-reported health satisfaction, biochemical measures of ill health (e.g. plasma albumin). For people with diabetes and a history of CVD top features were: self-reported ill health, and blood cell counts measurements (e.g. red cell distribution width). We additionally identified risk factors unique to people with diabetes, consisting of information on dietary patterns, mental health and biochemistry measures. Consideration of these novel features improved risk classification, for example per 1000 people with diabetes 133 CVD and 165 HF cases appropriately received a higher risk.

Conclusion

Through data-driven feature selection we identified a substantial number of features relevant for prediction of cardiovascular risk in people with diabetes, the majority of which related to non-classical risk factors such as mental health, general illness markers, and kidney disease.

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.

Combining serum metabolomic profiles with traditional risk factors improves 10-year cardiovascular risk prediction in people with type 2 diabetes

AIMS

To identify a group of metabolites associated with incident cardiovascular disease (CVD) in people with type 2 diabetes and assess its predictive performance over-and-above a current CVD risk score (QRISK3).

METHODS AND RESULTS

A panel of 228 serum metabolites was measured at baseline in 1066 individuals with type 2 diabetes (Edinburgh Type 2 Diabetes Study) who were then followed up for CVD over the subsequent 10 years. We applied 100 repeats of Cox least absolute shrinkage and selection operator to select metabolites with frequency >90% as components for a metabolites-based risk score (MRS). The predictive performance of the MRS was assessed in relation to a reference model that was based on QRISK3 plus prevalent CVD and statin use at baseline. Of 1021 available individuals, 255 (25.0%) developed CVD (median follow-up: 10.6 years). Twelve metabolites relating to fluid balance, ketone bodies, amino acids, fatty acids, glycolysis, and lipoproteins were selected to construct the MRS that showed positive association with 10-year cardiovascular risk following adjustment for traditional risk factors [hazard ratio (HR) 2.67; 95% confidence interval (CI) 1.96, 3.64]. The c-statistic was 0.709 (95%CI 0.679, 0.739) for the reference model alone, increasing slightly to 0.728 (95%CI 0.700, 0.757) following addition of the MRS. Compared with the reference model, the net reclassification index and integrated discrimination index for the reference model plus the MRS were 0.362 (95%CI 0.179, 0.506) and 0.041 (95%CI 0.020, 0.071), respectively.

CONCLUSION

Metabolomics data might improve predictive performance of current CVD risk scores based on traditional risk factors in people with type 2 diabetes. External validation is warranted to assess the generalizability of improved CVD risk prediction using the MRS.

Validation and comparison of cardiovascular risk prediction equations in Chinese patients with Type 2 diabetes

AIMS

For patients with diabetes, the European guidelines updated the cardiovascular disease (CVD) risk prediction recommendations using diabetes-specific models with age-specific cut-offs, whereas American guidelines still advise models derived from the general population. We aimed to compare the performance of four cardiovascular risk models in diabetes populations.

METHODS AND RESULTS

Patients with diabetes from the CHERRY study, an electronic health records-based cohort study in China, were identified. Five-year CVD risk was calculated using original and recalibrated diabetes-specific models [Action in Diabetes and Vascular disease: PreterAx and diamicroN-MR Controlled Evaluation (ADVANCE) and the Hong Kong cardiovascular risk model (HK)] and general population-based models [Pooled Cohort Equations (PCE) and Prediction for Atherosclerotic cardiovascular disease Risk in China (China-PAR)]. During a median 5.8-year follow-up, 46 558 patients had 2605 CVD events. C-statistics were 0.711 [95% confidence interval: 0.693-0.729] for ADVANCE and 0.701 (0.683-0.719) for HK in men, and 0.742 (0.725-0.759) and 0.732 (0.718-0.747) in women. C-statistics were worse in two general population-based models. Recalibrated ADVANCE underestimated risk by 1.2% and 16.8% in men and women, whereas PCE underestimated risk by 41.9% and 24.2% in men and women. With the age-specific cut-offs, the overlap of the high-risk patients selected by every model pair ranged from only 22.6% to 51.2%. When utilizing the fixed cut-off at 5%, the recalibrated ADVANCE selected similar high-risk patients in men (7400) as compared to the age-specific cut-offs (7102), whereas age-specific cut-offs exhibited a reduction in the selection of high-risk patients in women (2646 under age-specific cut-offs vs. 3647 under fixed cut-off).

CONCLUSION

Diabetes-specific CVD risk prediction models showed better discrimination for patients with diabetes. High-risk patients selected by different models varied significantly. Age-specific cut-offs selected fewer patients at high CVD risk especially in women.

[Luces y sombras de la Guía Europea esc-2021 de Prevención de la Enfermedad Cardiovascular en la Práctica Clínica.]

General practitioners see in their consultation a a significant number of patients at high vascular risk (VR). The European Guidelines for Cardiovascular Disease Prevention (2021) recommend a new risk classification and intervention strategies on on vascular risk factors (RF), with the aim of providing a shared decision-making recommendations between professionals and patients. In this document we present a critical analysis of these guidelines, offering possible solutions that can be implemented in Primary Care. It should be noted that there are positive aspects (lights) such as that the SCORE2 (from forty to sixty-nine years) and SCORE2-OP models (from seventy to eighty-nine years) are based on more current cohorts and measure cardiovascular risk in a more accurately manner. In addition, it is proposed to differentiate different risk thresholds according to age-groups. For sake of practicality, cardiovascular risk can be estimated using different websites with the new computer models. However, among the negative aspects (shadows), it seems to be add complexity implementing nine subgroups of subjects according to their age or level of risk, with a defined thresholds that could cause a substantial increase in the potential number of subjects susceptible to treatment without a clear evidence that supports it. In addition, two-step RF interventions could delay achievement of therapeutic goals, especially in very high-risk patients, diabetics, or patients with cardiovascular disease. Given these limitations, in this document we propose practical recommendations in order to simplify and facilitate the implementation of the guideline in primary care.

Trends in baseline triglyceride-glucose index and association with predicted 10-year cardiovascular disease risk among type 2 diabetes patients in Thailand

Triglyceride-glucose (TyG) index is an independent risk factor for cardiovascular diseases (CVD). Our study determined the trends of the TyG index and its relationship to predicted CVD risk among patients with type 2 diabetes (T2D). A serial cross-sectional study was conducted including 63,815 participants with T2D aged 30-74 years without a history of CVD. The predicted CVD risk was based on the Framingham Heart Study (FHS). The receiver operating characteristic (ROC) curve was utilized for identifying the cutoff point of TyG index to predict intermediate-to-high CVD risk. The relationship between TyG index and predicted CVD risk was tested using linear and logistic regression. Decreasing trends of TyG index were observed between 2014 and 2018 (p < 0.001). ROC curve analysis of the TyG index indicated an AUC of 0.57 (95% CI 0.56-0.57, p < 0.001) in predicting intermediate-to-high predicted CVD risk, with a cutoff value of TyG index > 9.2 (sensitivity of 55.7%, specificity of 46.8%). An independent relationship between the TyG index and predicted CVD risk was observed. High TyG index was independently associated with intermediate-to-high predicted CVD risk. From our study, the TyG index was positively related to predicted 10-year CVD risk. However, the predictive ability of the TyG index in predicting the intermediate-to-high predicted 10-year CVD risk among patients with T2D remained questionable.

SCORE2-Diabetes: 10-year cardiovascular risk estimation in type 2 diabetes in Europe

AIMS

To develop and validate a recalibrated prediction model (SCORE2-Diabetes) to estimate the 10-year risk of cardiovascular disease (CVD) in individuals with type 2 diabetes in Europe.

METHODS AND RESULTS

SCORE2-Diabetes was developed by extending SCORE2 algorithms using individual-participant data from four large-scale datasets comprising 229 460 participants (43 706 CVD events) with type 2 diabetes and without previous CVD. Sex-specific competing risk-adjusted models were used including conventional risk factors (i.e. age, smoking, systolic blood pressure, total, and HDL-cholesterol), as well as diabetes-related variables (i.e. age at diabetes diagnosis, glycated haemoglobin [HbA1c] and creatinine-based estimated glomerular filtration rate [eGFR]). Models were recalibrated to CVD incidence in four European risk regions. External validation included 217 036 further individuals (38 602 CVD events), and showed good discrimination, and improvement over SCORE2 (C-index change from 0.009 to 0.031). Regional calibration was satisfactory. SCORE2-Diabetes risk predictions varied several-fold, depending on individuals' levels of diabetes-related factors. For example, in the moderate-risk region, the estimated 10-year CVD risk was 11% for a 60-year-old man, non-smoker, with type 2 diabetes, average conventional risk factors, HbA1c of 50 mmol/mol, eGFR of 90 mL/min/1.73 m2, and age at diabetes diagnosis of 60 years. By contrast, the estimated risk was 17% in a similar man, with HbA1c of 70 mmol/mol, eGFR of 60 mL/min/1.73 m2, and age at diabetes diagnosis of 50 years. For a woman with the same characteristics, the risk was 8% and 13%, respectively.

CONCLUSION

SCORE2-Diabetes, a new algorithm developed, calibrated, and validated to predict 10-year risk of CVD in individuals with type 2 diabetes, enhances identification of individuals at higher risk of developing CVD across Europe.

Trends in predicted 10-year risk for cardiovascular diseases among patients with type 2 diabetes in Thailand, from 2014 to 2018

BACKGROUND

Cardiovascular diseases (CVD) are the leading causes of death globally, including Thailand. Approximately one-tenth of Thai adults have type 2 diabetes (T2D), a significantly increasing CVD. Our study aimed to determine the trends of predicted 10-year CVD risk among patients with T2D.

METHODS

A series of hospital-based cross-sectional studies were conducted in 2014, 2015 and 2018. We included Thai patients with T2D aged 30-74-year-old without a history of CVD. The predicted 10-year risk for CVD was calculated based on Framingham Heart Study equations both with simple office-based nonlaboratory and laboratory-based. Age- and sex-adjusted means and proportions of predicted 10-year risk for CVD were calculated.

RESULTS

A total of 84,602 patients with T2D were included in the present study. The average SBP among study participants was 129.3 ± 15.7 mmHg in 2014 and rose to 132.6 ± 14.9 mmHg in 2018. Likewise, the average body mass index was 25.7 ± 4.5 kg/m² in 2014 and elevated to 26.0 ± 4.8 kg/m² in 2018. The age- and sex-adjusted mean of the predicted 10-year CVD risk (simple office-based) was 26.2% (95% CI: 26.1-26.3%) in 2014 and rose to 27.3% (95% CI: 27.2-27.4%) in 2018 (p-for trend < 0.001). While the age- and sex-adjusted mean of the predicted 10-year CVD risk (laboratory-based) ranged from 22.4-22.9% from 2014 to 2018 (p-for trend < 0.001). The age- and sex-adjusted prevalence of the high predicted 10-year CVD risk (simple office-based) was 67.2% (95% CI: 66.5-68.0%) in 2014 and significantly rose to 73.1% (95% CI: 72.4-73.7%) in 2018 (p-for trend < 0.001). Nevertheless, the age- and sex-adjusted prevalence of the high predicted 10-year CVD risk (laboratory-based) ranged from 46.0-47.4% from 2014 to 2018 (p-for trend = 0.405). However, among patients with available laboratory results, a significantly positive correlation was noted between predicted 10-year CVD risk, simple office-based and laboratory-based (r = 0.8765, p-value < 0.001).

CONCLUSION

Our study demonstrated significant rising trends in the predicated 10-year CVD risk among Thai patients with T2D. In addition, the results empowered further improved modifiable CVD risks, especially regarding high BMI and high blood pressure.

Development of models to predict 10-30-year cardiovascular disease risk using the Da Qing IGT and diabetes study

BACKGROUND

This study aimed to develop cardiovascular disease (CVD) risk equations for Chinese patients with newly diagnosed type 2 diabetes (T2D) to predict 10-, 20-, and 30-year of risk.

METHODS

Risk equations for forecasting the occurrence of CVD were developed using data from 601 patients with newly diagnosed T2D from the Da Qing IGT and Diabetes Study with a 30-year follow-up. The data were randomly assigned to a training and test data set. In the training data set, Cox proportional hazard regression was used to develop risk equations to predict CVD. Calibration was assessed by the slope and intercept of the line between predicted and observed probabilities of outcomes by quintile of risk, and discrimination was examined using Harrell's C statistic in the test data set. Using the Sankey flow diagram to describe the change of CVD risk over time.

RESULTS

Over the 30-year follow-up, corresponding to a 10,395 person-year follow-up time, 355 of 601 (59%) patients developed incident CVD; the incidence of CVD in the participants was 34.2 per 1,000 person-years. Age, sex, smoking status, 2-h plasma glucose level of oral glucose tolerance test, and systolic blood pressure were independent predictors. The C statistics of discrimination for the risk equations were 0.748 (95%CI, 0.710-0.782), 0.696 (95%CI, 0.655-0.704), and 0.687 (95%CI, 0.651-0.694) for 10-, 20-, and 30- year CVDs, respectively. The calibration statistics for the CVD risk equations of slope were 0.88 (P = 0.002), 0.89 (P = 0.027), and 0.94 (P = 0.039) for 10-, 20-, and 30-year CVDs, respectively.

CONCLUSIONS

The risk equations forecast the long-term risk of CVD in patients with newly diagnosed T2D using variables readily available in routine clinical practice. By identifying patients at high risk for long-term CVD, clinicians were able to take the required primary prevention measures.

Cardiovascular disease and type 2 diabetes in older adults: a combined protocol for an individual participant data analysis for risk prediction and a network meta-analysis of novel anti-diabetic drugs

Introduction

Older and multimorbid adults with type 2 diabetes (T2D) are at high risk of cardiovascular disease (CVD) and chronic kidney disease (CKD). Estimating risk and preventing CVD is a challenge in this population notably because it is underrepresented in clinical trials. Our study aims to (1) assess if T2D and haemoglobin A1c (HbA1c) are associated with the risk of CVD events and mortality in older adults, (2) develop a risk score for CVD events and mortality for older adults with T2D, (3) evaluate the comparative efficacy and safety of novel antidiabetics.

Methods and analysis

For Aim 1, we will analyse individual participant data on individuals aged ≥65 years from five cohort studies: the Optimising Therapy to Prevent Avoidable Hospital Admissions in Multimorbid Older People study; the Cohorte Lausannoise study; the Health, Aging and Body Composition study; the Health and Retirement Study; and the Survey of Health, Ageing and Retirement in Europe. We will fit flexible parametric survival models (FPSM) to assess the association of T2D and HbA1c with CVD events and mortality. For Aim 2, we will use data on individuals aged ≥65 years with T2D from the same cohorts to develop risk prediction models for CVD events and mortality using FPSM. We will assess model performance, perform internal-external cross validation, and derive a point-based risk score. For Aim 3, we will systematically search randomized controlled trials of novel antidiabetics. Network meta-analysis will be used to determine comparative efficacy in terms of CVD, CKD, and retinopathy outcomes, and safety of these drugs. Confidence in results will be judged using the CINeMA tool.

Ethics and dissemination

Aims 1 and 2 were approved by the local ethics committee (Kantonale Ethikkommission Bern); no approval is required for Aim 3. Results will be published in peer-reviewed journals and presented in scientific conferences.

Machine learning predicts cardiovascular events in patients with diabetes: The Silesia Diabetes-Heart Project

We aimed to develop a machine learning (ML) model for predicting cardiovascular (CV) events in patients with diabetes (DM). This was a prospective, observational study where clinical data of patients with diabetes hospitalized in the diabetology center in Poland (years 2015 - 2020) were analyzed using ML. The occurrence of new CV events following discharge was collected in the follow-up time for up to 5 years and 9 months. An end-to-end ML technique which exploits the neighborhood component analysis for elaborating discriminative predictors, followed by a hybrid sampling/boosting classification algorithm, multiple logistic regression, or unsupervised hierarchical clustering was proposed. In 1735 patients with diabetes (53% female), there were 150 (8.65%) ones with a new CV event in the follow-up. Twelve most discriminative patients' parameters included coronary artery disease, heart failure, peripheral artery disease, stroke, diabetic foot disease, chronic kidney disease, eosinophil count, serum potassium level, and being treated with clopidogrel, heparin, proton pump inhibitor, and loop diuretic. Utilizing those variables resulted in the area under the receiver operating characteristic curve (AUC) ranging from 0.62 (95% Confidence Interval [CI] 0.56-0.68, p<0.01) to 0.72 (95%CI 0.66-0.77, p<0.01) across five non-overlapping test folds, whereas multiple logistic regression correctly determined 111/150 (74.00%) high-risk patients, and 989/1585 (62.40%) low-risk patients, resulting in 1100/1735 (63.40%) correctly classified patients (AUC: 0.72, 95%CI 0.66-0.77). ML algorithms can identify patients with diabetes at a high risk of new CV events based on a small number of interpretable and easy-to-obtain patients' parameters.

Cardiovascular risk assessment in periodontitis patients and controls using the European Systematic COronary Risk Evaluation (SCORE) model. A pilot study

Aim: To investigate the use of the European SCORE model in a dental setting by exploring the frequency of a 'high' and 'very high' 10-year CVD mortality risk in patients with and without periodontitis. The secondary aim was to investigate the association of SCORE with various periodontitis parameters adjusting for remaining potential confounders. Material and methods: In this study, we recruited periodontitis patients and non-periodontitis controls, all aged ≥40 years. We determined the 10-year CVD mortality risk per individual with the European Systematic Coronary Risk Evaluation (SCORE) model by using certain patient characteristics and biochemical analyses from blood by finger stick sampling. Results: In total, 105 periodontitis patients (61 localized, 44 generalized stage III/IV) and 88 non-periodontitis controls were included (mean age: 54.4 years). The frequency of a 'high' and 'very high' 10-year CVD mortality risk was 43.8% in all periodontitis patients and 30.7% in controls (p = .061). In total, 29.5% generalized periodontitis patients had a 'very high' 10-year CVD mortality risk, compared to 16.4% in localized periodontitis patients and 9.1% in controls (p = .003). After adjustment for potential confounders, the total periodontitis group (OR 3.31; 95% CI 1.35-8.13), generalized periodontitis group (OR 5.32; 95% CI 1.90-14.90), lower number of teeth (OR .83; 95% CI .73-1.00) and higher number of teeth with radiographic bone loss ≥33% (OR 1.06; 95% CI 1.00-1.12) were associated with a "very high" SCORE category. In addition, various biochemical risk markers for CVD were more frequently elevated in periodontitis compared to controls (e.g., total cholesterol, triglycerides, C-reactive protein). Conclusion: The periodontitis group as well as the control group had a sizable frequency of a 'high' and 'very high' 10-year CVD mortality risk. The presence and extent of periodontitis, lower number of teeth and higher number of teeth with bone loss ≥33% are significant risk indicators for a 'very high' 10-year CVD mortality risk. Therefore, SCORE in a dental setting can be a very useful tool to employ for primary and secondary prevention of CVD, especially among the dental attenders who have periodontitis.

Stroke risk in older British men: Comparing performance of stroke-specific and composite-CVD risk prediction tools

Stroke risk is currently estimated as part of the composite risk of cardiovascular disease (CVD). We investigated if composite-CVD risk prediction tools QRISK3 and Pooled Cohort Equations-PCE, derived from middle-aged adults, are as good as stroke-specific Framingham Stroke Risk Profile-FSRP and QStroke for capturing the true risk of stroke in older adults. External validation for 10y stroke outcomes was performed in men (60-79y) of the British Regional Heart Study. Discrimination and calibration were assessed in separate validation samples (FSRP n = 3762, QStroke n = 3376, QRISK3 n = 2669 and PCE n = 3047) with/without adjustment for competing risks. Sensitivity/specificity were examined using observed and clinically recommended thresholds. Performance of FSRP, QStroke and QRISK3 was further compared head-to-head in 2441 men free of a range of CVD, including across age-groups. Observed 10y risk (/1000PY) ranged from 6.8 (hard strokes) to 11 (strokes/transient ischemic attacks). All tools discriminated weakly, C-indices 0.63-0.66. FSRP and QStroke overestimated risk at higher predicted probabilities. QRISK3 and PCE showed reasonable calibration overall with minor mis-estimations across the risk range. Performance worsened on adjusting for competing non-stroke deaths. However, in men without CVD, QRISK3 displayed relatively better calibration for stroke events, even after adjustment for competing deaths, including in oldest men. All tools displayed similar sensitivity (63-73 %) and specificity (52-54 %) using observed risks as cut-offs. When QRISK3 and PCE were evaluated using thresholds for CVD prevention, sensitivity for stroke events was 99 %, with false positive rate 97 % suggesting existing intervention thresholds may need to be re-examined to reflect age-related stroke burden.

Evaluation of available risk scores to predict multiple cardiovascular complications for patients with type 2 diabetes mellitus using electronic health records

Aims

Various cardiovascular risk prediction models have been developed for patients with type 2 diabetes mellitus. Yet few models have been validated externally. We perform a comprehensive validation of existing risk models on a heterogeneous population of patients with type 2 diabetes using secondary analysis of electronic health record data.

Methods

Electronic health records of 47,988 patients with type 2 diabetes between 2013 and 2017 were used to validate 16 cardiovascular risk models, including 5 that had not been compared previously, to estimate the 1-year risk of various cardiovascular outcomes. Discrimination and calibration were assessed by the c-statistic and the Hosmer-Lemeshow goodness-of-fit statistic, respectively. Each model was also evaluated based on the missing measurement rate. Sub-analysis was performed to determine the impact of race on discrimination performance.

Results

There was limited discrimination (c-statistics ranged from 0.51 to 0.67) across the cardiovascular risk models. Discrimination generally improved when the model was tailored towards the individual outcome. After recalibration of the models, the Hosmer-Lemeshow statistic yielded p-values above 0.05. However, several of the models with the best discrimination relied on measurements that were often imputed (up to 39% missing).

Conclusion

No single prediction model achieved the best performance on a full range of cardiovascular endpoints. Moreover, several of the highest-scoring models relied on variables with high missingness frequencies such as HbA1c and cholesterol that necessitated data imputation and may not be as useful in practice. An open-source version of our developed Python package, cvdm, is available for comparisons using other data sources.

Validation of risk prediction models applied to longitudinal electronic health record data for the prediction of major cardiovascular events in the presence of data shifts

Aims

Deep learning has dominated predictive modelling across different fields, but in medicine it has been met with mixed reception. In clinical practice, simple, statistical models and risk scores continue to inform cardiovascular disease risk predictions. This is due in part to the knowledge gap about how deep learning models perform in practice when they are subject to dynamic data shifts; a key criterion that common internal validation procedures do not address. We evaluated the performance of a novel deep learning model, BEHRT, under data shifts and compared it with several ML-based and established risk models.

Methods and results

Using linked electronic health records of 1.1 million patients across England aged at least 35 years between 1985 and 2015, we replicated three established statistical models for predicting 5-year risk of incident heart failure, stroke, and coronary heart disease. The results were compared with a widely accepted machine learning model (random forests), and a novel deep learning model (BEHRT). In addition to internal validation, we investigated how data shifts affect model discrimination and calibration. To this end, we tested the models on cohorts from (i) distinct geographical regions; (ii) different periods. Using internal validation, the deep learning models substantially outperformed the best statistical models by 6%, 8%, and 11% in heart failure, stroke, and coronary heart disease, respectively, in terms of the area under the receiver operating characteristic curve.

Conclusion

The performance of all models declined as a result of data shifts; despite this, the deep learning models maintained the best performance in all risk prediction tasks. Updating the model with the latest information can improve discrimination but if the prior distribution changes, the model may remain miscalibrated.

Risk of all-cause mortality according to the European Society of Cardiology risk categories in individuals with type 2 diabetes: the Renal Insufficiency And Cardiovascular Events (RIACE) Italian Multicenter Study

AIMS

The 2019 and 2021 European Society of Cardiology (ESC) classifications stratified patients with type 2 diabetes into three categories according to the 10-year risk of death from atherosclerotic cardiovascular disease (ASCVD). The very high-risk category included individuals with established ASCVD, target organ damage (TOD), and/or, in the 2019 classification only, ≥ 3 additional ASCVD risk factors. We assessed risk of all-cause mortality according to the two ESC classifications in the Renal Insufficiency And Cardiovascular Events cohort.

METHODS

Participants (n = 15,773) were stratified based on the presence of ASCVD, TOD, and ASCVD risk factors at baseline (2006-2008). Vital status was retrieved in 2015.

RESULTS

Less than 1% of participants fell in the moderate-risk category. According to the 2019 classification, ~ 1/3 fell in the high-risk and ~ 2/3 in the very high-risk category, whereas the opposite occurred with the 2021 classification. Mortality risk increased across categories according to both classifications. Among very high-risk patients, mortality was much lower in those with ≥ 3 additional ASCVD risk factors and almost equal in those with TOD and ASCVD ± TOD, using the 2019 classification, whereas it was much higher in those with ASCVD + TOD and, to a lesser extent, TOD only than in those with ASCVD only, using the 2021 classification.

CONCLUSIONS

The negligible number of moderate-risk patients suggests that these classifications might overestimate risk of ASCVD death. Downgrading patients with ≥ 3 additional ASCVD risk factors to the high-risk category is consistent with mortality data. Risk of death is very high in the presence of TOD irrespective of established ASCVD.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT00715481.

How dysregulation of the immune system promotes diabetes mellitus and cardiovascular risk complications

Diabetes mellitus (DM) is a chronic metabolic disorder characterized by persistent hyperglycemia due to insulin resistance or failure to produce insulin. Patients with DM develop microvascular complications that include chronic kidney disease and retinopathy, and macrovascular complications that mainly consist in an accelerated and more severe atherosclerosis compared to the general population, increasing the risk of cardiovascular (CV) events, such as stroke or myocardial infarction by 2- to 4-fold. DM is commonly associated with a low-grade chronic inflammation that is a known causal factor in its development and its complications. Moreover, it is now well-established that inflammation and immune cells play a major role in both atherosclerosis genesis and progression, as well as in CV event occurrence. In this review, after a brief presentation of DM physiopathology and its macrovascular complications, we will describe the immune system dysregulation present in patients with type 1 or type 2 diabetes and discuss its role in DM cardiovascular complications development. More specifically, we will review the metabolic changes and aberrant activation that occur in the immune cells driving the chronic inflammation through cytokine and chemokine secretion, thus promoting atherosclerosis onset and progression in a DM context. Finally, we will discuss how genetics and recent systemic approaches bring new insights into the mechanisms behind these inflammatory dysregulations and pave the way toward precision medicine.

Association of Gonadotropin-Releasing Hormone Agonists for Prostate Cancer With Cardiovascular Disease Risk and Hypertension in Men With Diabetes

IMPORTANCE

Men with type 2 diabetes have an increased risk of cardiovascular disease (CVD). Meanwhile, gonadotropin-releasing hormone (GnRH) agonists used in prostate cancer (PCa) are associated with increased risk of CVD.

OBJECTIVE

To evaluate the association between GnRH agonist use, PCa diagnosis per se, and CVD risk in men with type 2 diabetes.

DESIGN, SETTING, AND PARTICIPANTS

This nationwide population-based cohort study identified men with type 2 diabetes by use of data in the Prostate Cancer Data Base Sweden version 4.1 and the Swedish National Diabetes Register, with longitudinal data from 2006 to 2016. These data were used to create 2 cohorts, 1 including men with and without PCa and the other including men with PCa who received and did not receive GnRH agonists. Data analysis was conducted from January 2006 to December 2016.

EXPOSURES

Treatment with GnRH agonists and PCa diagnosis were the primary exposures.

MAIN OUTCOMES AND MEASURES

Primary outcome was a 10% increase in predicted 5-year CVD risk score. Secondary outcome was worsening hypertension as defined by the European Society of Hypertension Guidelines. Cox proportional hazards regression models were used to analyze the association.

RESULTS

The PCa exposure cohort included 5714 men (median [IQR] age, 72.0 [11.0]), and the non-PCa cohort included 28 445 men without PCa (median [IQR] age, 72.0 [11.0]). The GnRH agonist-exposure cohort included 692 men with PCa who received a GnRH agonist, compared with 3460 men with PCa who did not receive a GnRH agonist. Men with PCa receiving GnRH agonists had an increased estimated 5-year CVD risk score compared with men without PCa (hazard ratio [HR], 1.25; 95% CI, 1.16-1.36) and compared with men with PCa not receiving GnRH agonists (HR, 1.53; 95% CI, 1.35-1.74). Men receiving GnRH agonists had decreased blood pressure compared with men without PCa (HR, 0.70; 95% CI, 0.61-0.80) and compared with men with PCa not receiving GnRH agonists (HR, 0.68; 95% CI, 0.56-0.82).

CONCLUSIONS AND RELEVANCE

In this population-based cohort study, there was an increased risk of CVD in men with type 2 diabetes who received a GnRH agonist for PCa. These findings highlight the need to closely control CVD risk factors in men with type 2 diabetes treated with GnRH agonists. The association between GnRH agonist use and decreased blood pressure levels warrants further study.

Incremental value of risk factor variability for cardiovascular risk prediction in individuals with type 2 diabetes: results from UK primary care electronic health records

BACKGROUND

Cardiovascular disease (CVD) risk prediction models for individuals with type 2 diabetes are important tools to guide intensification of interventions for CVD prevention. We aimed to assess the added value of incorporating risk factors variability in CVD risk prediction for people with type 2 diabetes.

METHODS

We used electronic health records (EHRs) data from 83 910 adults with type 2 diabetes but without pre-existing CVD from the UK Clinical Practice Research Datalink for 2004-2017. Using a landmark-modelling approach, we developed and validated sex-specific Cox models, incorporating conventional predictors and trajectories plus variability of systolic blood pressure (SBP), total and high-density lipoprotein (HDL) cholesterol, and glycated haemoglobin (HbA1c). Such models were compared against simpler models using single last observed values or means.

RESULTS

The standard deviations (SDs) of SBP, HDL cholesterol and HbA1c were associated with higher CVD risk (P < 0.05). Models incorporating trajectories and variability of continuous predictors demonstrated improvement in risk discrimination (C-index = 0.659, 95% CI: 0.654-0.663) as compared with using last observed values (C-index = 0.651, 95% CI: 0.646-0.656) or means (C-index = 0.650, 95% CI: 0.645-0.655). Inclusion of SDs of SBP yielded the greatest improvement in discrimination (C-index increase = 0.005, 95% CI: 0.004-0.007) in comparison to incorporating SDs of total cholesterol (C-index increase = 0.002, 95% CI: 0.000-0.003), HbA1c (C-index increase = 0.002, 95% CI: 0.000-0.003) or HDL cholesterol (C-index increase= 0.003, 95% CI: 0.002-0.005).

CONCLUSION

Incorporating variability of predictors from EHRs provides a modest improvement in CVD risk discrimination for individuals with type 2 diabetes. Given that repeat measures are readily available in EHRs especially for regularly monitored patients with diabetes, this improvement could easily be achieved.

Serum Levels of Irisin Predict Cumulative Clinical Outcomes in Heart Failure Patients With Type 2 Diabetes Mellitus

Background: The aim of this study was to investigate the role of serum irisin level in predicting clinical outcome in heart failure (HF) patients with type 2 diabetes mellitus (T2DM).

Methods: 153 T2DM patients with HF aged 41–62 years were prospectively recruited for the study. Serum levels of irisin and NT-proBNP were measured by ELISA. Laboratory tests including HbA1c, fasting glucose, blood creatinine, insulin, lipids and creatinine with estimation of GFR were performed along with echocardiography at baseline. The observation period was 56 weeks.

Results: We identified 76 composite cardiovascular (CV) outcomes, which included CV death and death from all causes, resuscitated cardiac death, non-fatal/fatal acute myocardial infarction or stroke, and HF hospitalization. Therefore, the entire patient cohort was divided into 2 groups with (n = 76) and without (n = 77) composite CV outcomes. We found that the concentrations of NT-proBNP were higher in HF patients with T2DM who had a CV composite outcome than in patients without CV composite outcome (p = 0.001). In contrast, the relationship was exactly reversed for irisin, as HF and T2DM patients with CV composite outcome had significantly lower irisin levels (p = 0.001). Unadjusted multivariate Cox regression analyses showed that LVEF &lt; 40%, LAVI &gt; 39 ml/m2, NT-proBNP &gt; 2,250 pmol/ml, and irisin &lt; 6.50 ng/ml were the strongest predictors of CV outcomes in HF patients with T2DM. After adjustment for LVEF, serum levels of NT-proBNP and irisin remained independent predictors of end points. Furthermore, divergence of Kaplan-Meier curves pointed out that patients with NT-proBNP &gt; 2,250 pmol/ml and irisin &lt; 6.50 ng/ml had worse prognosis than those with any other compartment of the bomarkers’ levels.

Conclusion: Adding irisin to NT-proBNP significantly improved discriminative value of the whole model. HF patients with T2DM had significantly worse clinical outcomes when showing the constellation NT-proBNP &gt; 2,250 pmol/ml and irisin &lt; 6.50 ng/ml, respectively, in comparison to patients with opposite trends for both biomarkers.

Assessment of QRISK3 as a predictor of cardiovascular disease events in type 2 diabetes mellitus

BACKGROUND

The risk of cardiovascular disease (CVD) in diabetes mellitus (DM) patients is two- to three-fold higher than in the general population. We designed a 10-year cohort trial in T2DM patients to explore the performance of QRESEARCH risk estimator version 3 (QRISK3) as a CVD risk assessment tool and compared to Framingham Risk Score (FRS).

METHOD

This is a single-center analysis of prospective data collected from 566 newly-diagnosed patients with type 2 DM (T2DM). The risk scores were compared to CVD development in patients with and without CVD. The risk variables of CVD were identified using univariate analysis and multivariate cox regression analysis. The number of patients classified as low risk (<10%), intermediate risk (10%-20%), and high risk (>20%) for two tools were identified and compared, as well as their sensitivity, specificity, positive and negative predictive values, and consistency (C) statistics analysis.

RESULTS

Among the 566 individuals identified in our cohort, there were 138 (24.4%) CVD episodes. QRISK3 classified most CVD patients as high risk, with 91 (65.9%) patients. QRISK3 had a high sensitivity of 91.3% on a 10% cut-off dichotomy, but a higher specificity of 90.7% on a 20% cut-off dichotomy. With a 10% cut-off dichotomy, FRS had a higher specificity of 89.1%, but a higher sensitivity of 80.1% on a 20% cut-off dichotomy. Regardless of the cut-off dichotomy approach, the C-statistics of QRISK3 were higher than those of FRS.

CONCLUSION

QRISK3 comprehensively and accurately predicted the risk of CVD events in T2DM patients, superior to FRS. In the future, we need to conduct a large-scale T2DM cohort study to verify further the ability of QRISK3 to predict CVD events.