A machine learning algorithm for the identification elevated Lp(a) in patients with, or high-risk of having, coronary heart disease.

BACKGROUND: Decision tree algorithms, obtained by machine learning, provide clusters of patients with similar clinical patterns by the identification of variables that best merge with a given dependent variable. METHODS: We performed a multicenter registry, with 7 hospitals form Spain, of patients with, or high-risk of having, coronary heart disease (CHD). Elevated Lp(a) was defined as >50 mg/dl. Machine learning based decision trees were obtained by Chi-square automatic interaction detection. RESULTS: We analyzed 2301 patients. Median Lp(a) was 26.7 (9.3-79.9) mg/dl and 887 (38.6 %) patients had Lp(a) >50 mg/dl. The machine learning algorithm identified 6 clusters based on LDLc, CHD, FH of premature CHD and age (Fig. 1). Clusters 1 (LDLc <100 mg/dl, no CHD and, no FH of CHD) and 3 (LDLc <100 mg/dl, CHD and, no FH and, age < 50 yo) had the lowest Lp(a) values (Fig. 2); patients classified in cluster 5 (LDLc >100 mg/dl, CHD and, FH of CHD) and 6 (LDLc >100 mg/dl) had the highest values. We collapsed clusters in 3 groups: group 1 with clusters 1 and 3; group 2 with clusters 2 and 4; group 3 with clusters 5 and 6. The 3 groups have significantly different (p < 0.001) and progressively higher Lp(a) values. The prevalence of Lp(a) >50 mg/dl was 15.4 % in group 1, 29.2 % in group 2 and 91.1 % in group 3; similarly, the prevalence of Lp(a) >180 mg/dl was 1.0 %, 3.0 % and 7.6 % respectively. CONCLUSIONS: A decision tree algorithm, performed by machine learning, identified patients with, or at high risk of having, CHD have higher probabilities of having elevated Lp(a).

Patients With High Cardiovascular Risk as Candidates to Bempedoic Acid, After Treatment With Statins, Ezetimibe and PCSK9 Inhibitors: An Estimation and Cost-Effectiveness Analysis.

ABSTRACT: Low-density lipoprotein cholesterol (LDLc) is the lead effector of atherosclerosis and main treatment target. Bempedoic acid is a novel oral drug in the therapeutic armamentarium which is able to reduce LDLc. The objectives of this study were (1) to select the potential patients for administering bempedoic acid such as those with a very high cardiovascular risk in which objectives of LDLc were not achieved despite conventional treatment with PCSK9 inhibitors (PCSK9i) and/or statins and ezetimibe and (2) to estimate the cost-effectiveness of bempedoic acid in different scenarios. The methods used were a multicenter and retrospective study of 652 patients initiating treatment with any PCSK9 inhibitor in 17 different hospitals. Before and on-treatment LDLc cholesterol levels, medical treatments, clinical indication, and baseline characteristics were recorded. The results obtained from 443 subjects in secondary prevention were analyzed. The mean (±) LDLc level at baseline was 142.5 ± 46.4 mg/dL and 61.5 ± 40.5 mg/dL in the follow-up, with a reduction of 55.9% ( P < 0.0001); 71.6% of the patients reached the target of LDL < 55 mg/dL or >50% reduction. Of those patients treated with medium-intensity and low-intensity statins plus PCSK9 inhibitors (with or without ezetimibe), only 5.7% of them were able to reduce LDL below 55 mg/dL and the main LDLc reduction in this group was the lowest (42.9% on average). Patients with TG values >135 mg/dL represented 41.6% of the sample, of which approximately 10% of them were using fibrates. Assuming only LDLc reduction and the UK price, the incremental cost-effectiveness ratio was 88,359€; 83,117€; 82,378€; and 79,015€ for different discount rates. In conclusion, one-third of the patients could achieve the target LDL proposed in the 2019 ESC/EAS guidelines. Approximately 10% of them could also benefit from treating hypertriglyceridemia as indicated in the 2021 ESC guidelines on cardiovascular disease prevention. Patients with medium-intensity and low-intensity statins plus PCSK9i and ezetimibe would be the most benefited. Bempedoic acid could be a not cost-efficacy therapy in all the scenarios, but we need to wait for the CLEAR OUTCOMES Trial results.

Effect of PCSK9 inhibitors on remnant cholesterol and lipid residual risk: The LIPID-REAL registry.

BACKGROUND: Monoclonal antibodies that inhibit the proprotein convertase subtilisin/kexin type 9 (PCSK9) reduce low-density lipoprotein cholesterol (LDLc) by 55%, regardless of baseline treatments. Nonetheless, the effect of other lipid parameters, such as cholesterol remnants or, the so-called lipid residual risk, is unknown. METHODS: Multicenter and retrospective registry of patients treated with PCSK9 inhibitors from 14 different hospitals in Spain. Before and on-treatment lipid parameters were recorded. Residual lipid risk was estimated by (1) cholesterol remnants, (2) triglycerides/HDLc ratio (TG/HDL), (3) total cholesterol/HDLc (TC/HDL) and (4) the triglycerides-to-glucose index (TGGi). RESULTS: Six hundred fifty-two patients were analysed, mean age of 60.2 (9.63) years, 24.69% women and mean LDLc before treatment 149.24 (49.86) mg/dl. Median time to second blood determination was 187.5 days. On-treatment LDLc was 67.46 (45.78) mg/dl, which represented a 55% reduction. Significant reductions were observed for TG/HDL ratio, cholesterol remnants, TC/HDL ratio and TGGi. As consequence, 34.61% patients had LDLc <55 mg/dl and cholesterol remnants <30 mg/dl; additionally, 31.95% had cholesterol remnants <30 mg/dl but LDLc >55 mg/dl. Patients who had levels of cholesterol remnants >30 mg/dl before initiating the treatment with PCSK9 had higher reductions in cholesterol remnants, TG/HDL ratio, TC/HDL and TGGi. By contrast, no reduction differences were observed according to baseline LDLc (< or > the mean), age, gender or obesity. CONCLUSIONS: This multicenter and retrospective registry of real-world patients treated with PCSK9 inhibitors demonstrates a positive effect on cholesterol remnants and lipid residual risk beyond LDLc reductions.

One-year efficacy and safety of prasugrel and ticagrelor in patients with acute coronary syndromes: Results from a prospective and multicentre ACHILLES registry.

BACKGROUND: Prasugrel and ticagrelor have demonstrated higher efficacy than clopidogrel in their main clinical trials for patients with acute coronary syndrome (ACS). However, the long-term prognosis and different clinical characteristics related to the type of antiplatelet prescription in current clinical practice ACS patients have not been analysed in depth. The objective of this study was to analyse the clinical profile of ACS and the efficacy and safety of novel oral P2Y12 inhibitors in current clinical practice patients discharged afterACS. METHODS: We collected data from the ACHILLES registry, and an observational, prospective and multicentre registry of patients discharged after ACS. We analysed baseline characteristics, clinical profile and therapy during ACS admission and compared with the different treatments at discharge. After 1 year of follow-up, ischaemic and major bleeding events were analysed. Multivariate Cox regression analysis and Kaplan Meier curves were also plotted. RESULTS: Of 1717 consecutive patients, 1294 (75.4%) were discharged with a P2Y12 inhibitor without oral anticoagulation. Novel oral P2Y12 inhibitors were indicated in 47%. Patients treated with clopidogrel were elderly (69.1 ± 13.4 vs 60.4 ± 11.5 years; P < .001) and had a higher prevalence of cardiovascular risk factors. GRACE and CRUSADE scores were higher in the clopidogrel than in novel oral P2Y12 inhibitors group (P < .001). After 1 year of follow-up, 64(5.0%/year) patients had a new myocardial infarction, 127(10.0%/year) had a major adverse cardiovascular event (MACE) and 78(6.1%/year) died. Patients treated with clopidogrel had a significantly higher annual rate of cardiovascular mortality, MACE and all-cause mortality (allP < .001) without differences in major bleeding (P = .587) compared with novel oral P2Y12 inhibitors. After multivariate adjustment for the main clinical variables related to adverse prognosis in ACS patients, the discharge with novel oral P2Y12 inhibitors therapy was independently associated with lower risk of all-cause mortality (HR0.49, 95% CI [0.24-0.98], P = .044) and lower risk of MACE (HR0.64, 95% CI [0.41-0.98], P = .044). CONCLUSIONS: In this prospective, observational and current clinical practice ACS registry, the use of novel oral P2Y12 inhibitors was associated with a reduction in adverse events compared with clopidogrel in patients with ACS. Novel oral P2Y12 inhibitors prescription at discharge was independently associated with lower all-cause mortality and MACE without differences in bleeding events. However, clopidogrel remained the most common P2Y12 inhibitor employed for ACS, especially in older and high-risk patients.

Conservatively managed patients with non-ST-segment elevation acute coronary syndrome are undertreated with indicated medicines.

INTRODUCTION AND AIMS: Patients with non-ST-elevation acute coronary syndrome (NSTE-ACS) are often managed conservatively. Clinical practice guidelines recommend treating these patients with the same pharmacological drugs as those who receive invasive treatment. We analyze the use of new antiplatelet drugs (NADs) and other recommended treatments in people discharged following an NSTE-ACS according to the treatment strategy used, comparing the medium-term prognosis between groups. METHODS: Prospective observational multicenter registry study in 1717 patients discharged from hospital following an ACS; 1143 patients had experienced an NSTE-ACS. We analyzed groups receiving the following treatment: No cardiac catheterization (NO CATH): n = 134; 11.7%; Cardiac catheterization without revascularization (CATH-NO REVASC): n = 256; 22.4%; percutaneous coronary intervention (PCI): n = 629; 55.0%; and coronary artery bypass graft (CABG): n = 124; 10.8%. We assessed major adverse cardiovascular events (MACE), all-cause mortality, and hemorrhagic complications at one year. RESULTS: NO CATH was the oldest, had the most comorbidities, and was at the highest risk for ischemic and hemorrhagic events. Few patients who were not revascularized with PCI received NADs (NO CATH: 3.7%; CATH-NO REVASC: 10.6%; PCI: 43.2%; CABG: 3.2%; p<0.001). Non-revascularized patients also received fewer beta-blockers, angiotensin-converting enzyme (ACE) inhibitors, angiotensin II receptor blockers (ARB), and statins (p<0.001). At one year, MACE incidence in NO CATH group was three times that of the other groups (30.1%, p<0.001), and all-cause mortality was also much higher (26.3%, p<0.001). There were no significant differences in hemorrhagic events. Belonging to NO CATH group was an independent predictor for MACE at one year in the multivariate analysis (HR 2.72, 95% CI 1.29-5.73; p = 0.008). CONCLUSIONS: Despite current invasive management of NSTE-ACS, patients not receiving catheterization are at very high risk for under treatment with recommended drugs, including NADs. Their medium-term prognosis is poor, with high mortality. Patients treated with PCI receive better pharmacological management, with high use of NADs.

The CHADS2 Score to Predict Stroke Risk in the Absence of Atrial Fibrillation in Hypertensive Patients Aged 65 Years or Older.

INTRODUCTION AND OBJECTIVES: The CHADS2 score is a proven, essential tool for estimating cardioembolic risk (mainly stroke) in patients with nonvalvular atrial fibrillation, with the purpose of determining the indication for anticoagulant therapy. In this study we analyzed the use of CHADS2 in hypertensive patients without known atrial fibrillation in a Mediterranean population. METHODS: The study included 887 hypertensive patients aged 65 years or older without atrial fibrillation or anticoagulant therapy, who attended a medical consultation. Data on the patients' main risk factors, cardiovascular history, and medication were collected, basic laboratory analyses and electrocardiography were performed, and the CHADS2 score (heart failure, hypertension, age ≥ 75 years, diabetes mellitus, and previous stroke or transient ischemic attack) was calculated. A clinical follow-up was carried out, recording hospital admissions for a stroke or transient ischemic attack. The median duration of follow-up was 804 days. RESULTS: Mean age was 72.5 (SD,5.7) years, 46.6% were men, 27.8% had diabetes, and 8.6% were smokers. During follow-up, 40 patients were hospitalized for a stroke or transient ischemic attack (4.5%). The event-free survival analysis showed significant differences according to the CHADS2 score (log rank test, P < .001). On multivariate analysis, smoking and CHADS2 ≥3 were independent predictors of stroke or transient ischemic attack. CONCLUSIONS: The CHADS2 may be useful for estimating the risk of stroke or transient ischemic attack in hypertensive patients without known atrial fibrillation.

Does pacemaker implantation provide long-term benefits in severe obstructive hypertrophic cardiomyopathy?

INTRODUCTION AND OBJECTIVES: About 25% of patients with obstructive hypertrophic cardiomyopathy (HCM) remain symptomatic despite optimal medical treatment. Some may benefit from pacemaker implantation. The aim of this study was to determine the effect of pacemaker implantation on the left ventricular outflow tract (LVOT) gradient, the maximum thickness of the left ventricle, and functional capacity. METHODS: In total, 72 patients with obstructive HCM and incapacitating symptoms underwent pacemaker implantation. Clinical examination, echocardiography (in 61 patients) and treadmill testing (in 34 patients) were performed before and after implantation. RESULTS: Subjective functional capacity, as assessed using the New York Heart Association (NYHA) classification, improved in 43.1% of patients, but treadmill testing showed no change. There were significant reductions in subaortic gradient, from a median of 87.0 mmHg (interquartile range [IQR] 61.5-115.2 mmHg) to 30.0 mmHg (IQR 18.0-54.5 mmHg; P< .001), and maximum left ventricular thickness, from 22.1+/-4.5 mm to 19.8+/-3.6 mm (P=.001). Univariate analysis identified two factors associated with clinical improvement: female sex (odds ratio [OR]=3.43; P=.020) and functional class III/IV (OR=4.17; P=.009). On multivariate analysis, only functional class III/IV remained a significant predictor (OR=3.12; P=.048). CONCLUSIONS: In patients with obstructive HCM and incapacitating symptoms, pacemaker implantation reduced the LVOT gradient and the maximum left ventricular thickness, but only 43.1% of patients experienced clinical improvement. The only factor predictive of improvement was advanced NYHA functional class.