Search

OBJECTIVE Sodium–glucose cotransporter 2 (SGLT2) inhibitors have well-documented cardioprotective effects but are underused, partly because of high cost. We aimed to develop a machine learning–based decision support tool to individualize the atherosclerotic cardiovascular disease (ASCVD) benefit of canagliflozin in type 2 diabetes. RESEARCH DESIGN AND METHODS We constructed a topological representation of the Canagliflozin Cardiovascular Assessment Study (CANVAS) using 75 baseline variables collected from 4,327 patients with type 2 diabetes randomly assigned 1:1:1 to one of two canagliflozin doses (n = 2,886) or placebo (n = 1,441). Within each patient’s 5% neighborhood, we calculated age- and sex-adjusted risk estimates for major adverse cardiovascular events (MACEs). An extreme gradient boosting algorithm was trained to predict the personalized ASCVD effect of canagliflozin using features most predictive of topological benefit. For validation, this algorithm was applied to the CANVAS-Renal (CANVAS-R) trial, comprising 5,808 patients with type 2 diabetes randomly assigned 1:1 to canagliflozin or placebo. RESULTS In CANVAS (mean age 60.9 ± 8.1 years; 33.9% women), 1,605 (37.1%) patients had a neighborhood hazard ratio (HR) more protective than the effect estimate of 0.86 reported for MACEs in the original trial. A 15-variable tool, INSIGHT, trained to predict the personalized ASCVD effects of canagliflozin in CANVAS, was tested in CANVAS-R (mean age 62.4 ± 8.4 years; 2,164 [37.3%] women), where it identified patient phenotypes with greater ASCVD canagliflozin effects (adjusted HR 0.60 [95% CI 0.41–0.89] vs. 0.99 [95% CI 0.76–1.29]; Pinteraction = 0.04). CONCLUSIONS We present an evidence-based, machine learning–guided algorithm to personalize the prescription of SGLT2 inhibitors for patients with type 2 diabetes for ASCVD effects.

The cardiovascular benefits of intensive systolic blood pressure control vary across clinical populations tested in large randomised clinical trials. We aimed to evaluate the application of machine learning to clinical trials of patients without and with type 2 diabetes to define the personalised cardiovascular benefit of intensive control of systolic blood pressure.In SPRINT, a trial of intensive (systolic blood pressurelt;120 mm Hg) versus standard (systolic blood pressurelt;140 mm Hg) systolic blood pressure control in patients without type 2 diabetes, we defined a phenotypic representation of the study population using 59 baseline variables. We extracted personalised treatment effect estimates for the primary outcome, time-to-first major adverse cardiovascular event (MACE; cardiovascular death, myocardial infarction or acute coronary syndrome, stroke, and acute decompensated heart failure), through iterative Cox regression analyses providing average hazard ratio (HR) estimates weighted for the phenotypic distance of each participant from the index patient of each iteration. Next, we trained an extreme gradient boosting algorithm (known as XGBoost) to predict the personalised effect of intensive systolic blood pressure control using features most consistently linked to increased personalised benefit, before evaluating its performance in the ACCORD BP trial of patients with type 2 diabetes randomly assigned to receive intensive versus standard systolic blood pressure control. We stratified patients based on their predicted treatment effect, and key demographic groups (age, sex, cardiovascular disease, and smoking). We assessed the presence of heterogeneity with an interaction test, and assessed the performance of the algorithm in a simulation analysis of SPRINT in the presence or absence of an artificially introduced heterogeneous treatment effect.From SPRINT, we included all 9361 study participants (mean age 67·9 years [SD 9·4], 3332 [35·6%] female) who underwent randomisation to either intensive (n=4678) or standard (n=4683) treatment. The median individualised HR for MACE was 0·63 (IQR 0·53-0·78). An eight-feature tool built for this analysis to predict personalised benefit in SPRINT was externally tested in ACCORD BP (4733 participants (mean age 62·7 years [SD 6·7], 2258 [47·7%] female), wherein it successfully identified individuals with differential benefit from intensive versus standard systolic blood pressure control (adjusted HR for MACE of 0·70 [95% CI 0·55-0·90] in individuals with above-median MACE benefit versus 1·05 [95% CI 0·84-1·32] for below-median predicted benefit; psubinteraction/sub=0·0184). Subgroup analysis based on age (lt;65 years: HR 0·89 [95% CI 0·71-1·12]; ≥65 years: 0·85 [0·67-1·09]), sex (male: 0·89 [0·72-1·10]; female: 0·85 [0·65-1·10]), established cardiovascular disease (no: 0·89 [0·70-1·14]; yes: 0·84 [0·67-1·06]), or active smoking (no: 0·85 [0·71-1·02]; yes: 1·01 [0·64-1·60]) did not identify groups with heterogeneity of treatment effect. In a simulation analysis of SPRINT, the proposed algorithm detected groups with heterogeneous treatment effects in the presence, but not absence, of simulated subgroup differences.By use of machine learning to define an individual's personalised benefit through phenotypic representations of clinical trials, we created a practical tool for individualising the selection of intensive versus standard systolic blood pressure control in patients without and with type 2 diabetes.National Heart, Lung, and Blood Institute of the US National Institutes of Health.

OBJECTIVE: To investigate the association between Raynaud phenomenon (RP) and coronary microvascular dysfunction, we measured myocardial flow reserve (MFR) using positron emission tomography/computed tomography (PET/CT) in primary and secondary RP patients and controls. METHODS: RP patients, patient controls and healthy participants who underwent dynamic rest-stress 82-Rubidium PET/CT were studied. Differences in heart rate-blood pressure product corrected MFR and clinical predictors of reduced MFR (< 2.0) were determined. RESULTS: 49 RP patients (80% female, 65 ± 11 years): 11 primary RP, 18 systemic sclerosis (SSc) and 20 other autoimmune diseases (AID) (n=6 systemic lupus erythematosus, n=6 rheumatoid arthritis, n=4 overlap syndrome, n=2 Sjogren’s syndrome, n=2 inflammatory arthritis), 49 matched patients without RP or AID (78% female, 64 ± 13 years) and 14 healthy participants (50% female, 35 ± 5 years) were studied. Primary RP patients, matched patient controls and healthy participants had comparable MFR. SSc-RP patients had significantly reduced MFR (1.62 ± 0.32) compared to matched patient controls (p=0.03, 2.06 ± 0.61) and to healthy participants (p=0.01, 2.22 ± 0.44). In multivariable logistic regression, SSc was an independent predictor of reduced MFR. We identified a correlation between time since AID diagnosis and MFR (r= −0.37; 95% CI: −0.61 to −0.09; p=0.01). CONCLUSION: Our findings suggest that only secondary, not primary, RP is associated with reduced MFR, and that SSc-RP patients have reduced MFR compared to primary RP and other autoimmune disease patients. Larger prospective studies are warranted to fully elucidate the prognostic value of MFR in patients with secondary RP.

Objectives Early saphenous vein graft (SVG) occlusion is typically attributed to technical factors. We aimed at exploring clinical, anatomical, and operative factors associated with the risk of early SVG occlusion (within 12 months postsurgery). Methods Published literature in MEDLINE was searched for studies reporting the incidence of early SVG occlusion. Individual patient data (IPD) on early SVG occlusion were used from the SAFINOUS-CABG Consortium. A derivation (n = 1492 patients) and validation (n = 372 patients) cohort were used for model training (with 10-fold cross-validation) and external validation respectively. Results In aggregate data meta-analysis (48 studies, 41,530 SVGs) the pooled estimate for early SVG occlusion was 11%. The developed IPD model for early SVG occlusion, which included clinical, anatomical, and operative characteristics (age, sex, dyslipidemia, diabetes mellitus, smoking, serum creatinine, endoscopic vein harvesting, use of complex grafts, grafted target vessel, and number of SVGs), had good performance in the derivation (c-index = 0.744; 95% confidence interval [CI], 0.701-0.774) and validation cohort (c-index = 0.734; 95% CI, 0.659-0.809). Based on this model. we constructed a simplified 12-variable risk score system (SAFINOUS score) with good performance for early SVG occlusion (c-index = 0.700, 95% CI, 0.684-0.716). Conclusions From a large international IPD collaboration, we developed a novel risk score to assess the individualized risk for early SVG occlusion. The SAFINOUS risk score could be used to identify patients that are more likely to benefit from aggressive treatment strategies.

The aim of this systematic review was to explore the prognostic value of late gadolinium enhancement (LGE) in patients with aortic stenosis (AS).Myocardial fibrosis is a common feature of many cardiac diseases. Cardiac magnetic resonance (CMR) has the ability to noninvasively detect regional fibrosis by using the LGE technique. Several studies have explored whether LGE is associated with adverse outcome in patients with AS.Electronic databases were searched to identify studies investigating the ability of LGE to predict all-cause mortality in patients with AS. A random effects model meta-analysis was conducted. Heterogeneity was assessed with the ISix studies comprising 1,151 patients met our inclusion criteria. LGE was present in 49.1% of patients with AS. In the pooled analysis, LGE was found to be a strong univariate predictor of all-cause mortality (pooled unadjusted odds ratio: 2.56; 95% confidence interval: 1.83 to 3.57; IFibrosis on LGE-CMR is a powerful predictor of all-cause mortality in patients with AS and may serve as a novel marker for risk stratification. Future studies should explore whether LGE-CMR can also be used to optimize timing of AS-related interventions.

Experimental evidence suggests that telomere length (TL) is shortened by oxidative DNA damage, reflecting biological aging. We explore the value of blood (BTL) and vascular TL (VTL) as biomarkers of systemic/vascular oxidative stress in humans and test the clinical predictive value of BTL in acute myocardial infarction (AMI).In a prospective cohort of 290 patients surviving recent AMI, BTL measured on admission was a strong predictor of all-cause [hazard ratio (HR) [95% confidence interval (CI)]: 3.21 [1.46-7.06], P = 0.004] and cardiovascular mortality (HR [95% CI]: 3.96 [1.65-9.53], P = 0.002) 1 year after AMI (for comparisons of short vs. long BTL, as defined by a T/S ratio cut-off of 0.916, calculated using receiver operating characteristic analysis; P adjusted for age and other predictors). To explore the biological meaning of these findings, BTL was quantified in 727 consecutive patients undergoing coronary artery bypass grafting (CABG), and superoxide (O2.-) was measured in peripheral blood mononuclear cells (PBMNC). VTL/vascular O2.- were quantified in saphenous vein (SV) and mammary artery (IMA) segments. Patients were genotyped for functional genetic polymorphisms in P22ph°x (activating NADPH-oxidases) and vascular smooth muscle cells (VSMC) selected by genotype were cultured from vascular tissue. Short BTL was associated with high O2.- in PBMNC (P = 0.04) but not in vessels, whereas VTL was related to O2.- in IMA (ρ = -0.49, P = 0.004) and SV (ρ = -0.52, P = 0.01). Angiotensin II (AngII) incubation of VSMC (30 days), as a means of stimulating NADPH-oxidases, increased O2.- and reduced TL in carriers of the high-responsiveness P22ph°x alleles (P = 0.007).BTL predicts cardiovascular outcomes post-AMI, independently of age, whereas VTL is a tissue-specific (rather than a global) biomarker of vascular oxidative stress. The lack of a strong association between BTL and VTL reveals the importance of systemic vs. vascular factors in determining clinical outcomes after AMI.