BACKGROUND:Clinical trials are an important part of evidence generation in medicine but remain burdened by escalating costs, inefficiencies and manual processes. Artificial intelligence (AI) has emerged as a promising approach to address these limitations by improving efficiency across the trial lifecycle. METHODS:In this review, we examine emerging applications of AI across the clinical trial lifecycle. We highlight key examples demonstrating feasibility and potential impact. RESULTS:AI-based approaches show promise in optimizing trial design, improving recruitment, streamlining conduct and enhancing data interpretation. Despite the potential of AI in trials, challenges persist, including data quality, regulatory and privacy concerns, as well as infrastructure issues. Ethical use will require strong governance frameworks emphasizing transparency and human oversight. The success of these technologies will depend on their continuous validation and monitoring of these technologies. CONCLUSIONS:With appropriate validation, monitoring and governance, AI could enable a more efficient, cost-saving and effective clinical trial landscape that accelerates discovery.

The ACC/AHA Heart Failure Stages categorize patients based on risk and disease progression, from preclinical risk to advanced heart failure. The system links each stage to guideline-directed management, emphasizing prevention, early intervention, and escalation of therapy.

BACKGROUND:The direct acting oral anticoagulant (DOAC) score is a bleeding risk score that incorporates 10 common clinical variables to risk stratify major bleeding in patients with atrial fibrillation and demonstrated improved risk stratification compared with HAS-BLED in patients receiving DOACs. This study evaluates the discriminative performance of the DOAC score among patients taking vitamin K antagonists (VKAs). METHODS:Data were obtained from COMBINE-AF and GARFIELD-AF. COMBINE-AF included patients with atrial fibrillation randomized to warfarin from 4 clinical trials: RE-LY, ARISTOTLE, ROCKET-AF, and ENGAGE AF-TIMI 48. GARFIELD-AF included patients with atrial fibrillation prescribed VKAs in a registry. The DOAC score of each patient was determined, based on commonly obtained clinical variables. Patients were then stratified by DOAC score clinical risk categories (very low [score: 0-3], low [score: 4-5], moderate [score: 6-7], high [score: 8-9], and very high [score: 10]), and the rate of major bleeding at 1 year was compared between groups. Discrimination was assessed using C-statistics and compared with HAS-BLED using DeLong's test. RESULTS:A total of 28,818 patients in COMBINE-AF and 20,183 patients in GARFIELD-AF receiving vitamin K antagonists were included. Of these individuals, 994 (3.4%) in COMBINE-AF and 313 (1.6%) in GARFIELD-AF experienced a major bleeding event at 1 year. Patients in higher DOAC score risk categories experienced greater 1-year major bleeding rates in COMBINE-AF, including very low (1.8 events per 100 person-years [events/100p-y]), low (3.0 events/100 p-y), moderate (4.6 events/100 p-y), high (5.6 events/100 p-y), and very high (7.9 events/100 p-y). Discrimination in COMBINE-AF was moderate and higher than HAS-BLED at 1 year (C-statistic: 0.62 vs 0.59, P < .001). In GARFIELD-AF, higher risk categories also had higher 1-year major bleeding rates: very low (0.8 events per 100 person-years [events/100 p-y]), low (1.5 events/100 p-y), moderate (2.2 events/100 p-y), high (3.2 events/100 p-y), and very high (7.6 events/100 p-y). Discrimination in GARFIELD-AF was moderate and higher than the HAS-BLED score at 1 year (C-statistic: 0.65 vs 0.62, P < .001). CONCLUSION:In patients with atrial fibrillation taking VKAs, the DOAC score was able to risk stratify patients based on bleeding risk, had moderate discrimination, and out-performed the HAS-BLED score in both a pooled clinical trials cohort and a usual care registry.

The PREVENT equations are contemporary risk prediction models developed to estimate 10- and 30-year risk of total cardiovascular disease (CVD), atherosclerotic cardiovascular disease (ASCVD), heart failure, coronary artery disease, and stroke in adults without established CVD (primary prevention). Derived from large, diverse US populations, PREVENT incorporates traditional risk factors along with kidney function and optional cardiovascular-kidney-metabolic (CKM) variables to improve individualized risk assessment. Compared with the prior Pooled Cohort Equations, PREVENT demonstrates improved calibration and broader applicability, including prediction of heart failure risk. These equations are now incorporated into recent US prevention guidelines to support risk-based primary prevention strategies, including lipid-lowering decisions using PREVENT-ASCVD risk and antihypertensive treatment decisions using PREVENT-total CVD risk. PREVENT generally yields lower estimated ASCVD risk than the prior Pooled Cohort Equations, likely reflecting improved calibration in contemporary populations. However, the downstream impact on treatment eligibility and the optimal treatment thresholds for PREVENT-based risk estimates remain areas of ongoing study.

Background and aims The VICTORION-1 PREVENT (V-1P) trial is evaluating the efficacy of inclisiran versus placebo on cardiovascular events in primary prevention patients at high-risk for ASCVD. We assessed whether V-1P eligibility, based on Pooled Cohort Equations (PCE) and Predicting Risk of Cardiovascular Disease Events (PREVENT) equations, was associated with subclinical cardiovascular and inflammatory abnormalities in a healthy European population. Methods We included individuals from the STANISLAS cohort in France aged 40–79 years, LDL-C 70–189 mg/dL and without ASCVD or liver disease. Participants were categorized as V-1P eligible using 10-year ASCVD risk using PCE and PREVENT. Associations with vascular, echocardiographic, and biomarkers were assessed using age- and sex-adjusted linear regression. Results Among 848 participants (mean age 60 years, 51% female), 16% were eligible per PCE, of which 7% were also eligible with PREVENT. Only one participant was eligible by PREVENT alone. Compared with non-eligible participants, V-1P-eligible individuals, whether by PCE alone or PCE and PREVENT, displayed significant subclinical abnormalities. Compared with V-1P ineligible participants, V-1P eligible participants had increased intima media thickness (+51 µm, p < 0.009 for PCE+PREVENT) and increased mean pulse wave velocity (+0.89 m/s, p < 0.001 for both PCE and PCE+PREVENT) on vascular ultrasound. V-1P eligible participants by PCE+PREVENT also showed signs of subclinical myocardial injury and inflammation, with a 1.3 fold higher troponin (p = 0.015), 1.6-fold higher interleukin-6 (p < 0.001) and a 2-fold higher high sensitivity C-reactive protein (p < 0.001). Conclusions A large proportion of asymptomatic individuals without known cardiovascular disease would be eligible for the V-1P trial based on both PCE and PREVENT equations. V-1P eligible participants had evidence of subclinical cardiovascular and inflammatory abnormalities.

The PRECISE-DAPT score is a validated five-item tool (age, creatinine clearance, hemoglobin, white blood cell count, and prior bleeding) designed to estimate bleeding risk in patients on dual antiplatelet therapy (DAPT) after PCI. Derived from pooled randomized trial data, it helps identify patients at high bleeding risk (score ≥25) who may derive greater net benefit from shorter DAPT (3–6 months) versus those at lower risk suitable for standard or extended therapy. Multiple external validations demonstrate moderate discrimination (AUC/C-statistic ~0.61–0.75) across different populations types. The PRECISE-DAPT score remains a practical, evidence-based tool to aid in clinical risk-benefit evaluation for DAPT duration after PCI.

This study uses data from the National Health and Nutrition Examination Survey to evaluate trends in the prevalence and control of diabetes among US adults overall and by age and sex between 2013 and 2023.

Background The efficacy of icosapent ethyl among patients with very well‐controlled baseline low‐density lipoprotein cholesterol (LDL‐C) is unknown. Methods In this post hoc analysis of the REDUCE‐IT (Reduction of Cardiovascular Events With Icosapent Ethyl–Intervention Trial) randomized clinical trial, statin‐treated patients with high cardiovascular risk, elevated triglycerides (135–499 mg/dL), and baseline LDL‐C of 41 to 100 mg/dL were included. Patients were randomized to icosapent ethyl (2 g twice daily) or placebo and then post hoc stratified by baseline LDL‐C (<55 mg/dL versus ≥55 mg/dL). The primary composite end point included cardiovascular death, nonfatal myocardial infarction, nonfatal stroke, coronary revascularization, or unstable angina. Results Among 8175 patients with baseline LDL‐C data, 7117 (87.1%) had LDL‐C ≥55 mg/dL and 1058 (12.9%) had LDL‐C <55 mg/dL. In patients with LDL‐C <55 mg/dL, the rate of the primary composite end point was lower in the icosapent ethyl group (16.2% versus 22.8%) than in the placebo group (hazard ratio [HR], 0.66 [95% CI, 0.50–0.87]; absolute risk reduction, 6.6%; P=0.003). Among patients with LDL‐C ≥55 mg/dL, a primary composite end point event occurred in a lower proportion of patients in the icosapent ethyl group (17.4% versus 21.9%) than in the placebo group (HR, 0.76 [95% CI, 0.69–0.85]; absolute risk reduction, 4.5%; P<0.0001). No significant interaction was observed between baseline LDL‐C and treatment group (P for interaction=0.40). Findings were consistent among secondary cardiovascular end points and in sensitivity analyses. Conclusions Among statin‐treated patients with elevated triglycerides and high cardiovascular risk, icosapent ethyl reduced the rate of cardiovascular end points irrespective of baseline LDL‐C, including among eligible patients with optimal LDL‐C control. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT01492361.

Within the United States, cardiovascular disease is the leading cause of death. There are well‐established inequities in cardiovascular care; individuals from medically underserved populations—including those with low socioeconomic status, rural populations, a plethora of racial and ethnic groups, women, and those living with disabilities—are often at increased risk of cardiovascular morbidity and mortality. Despite their critically unmet needs, these populations remain underrepresented within cardiovascular clinical trials, therefore deepening inequities in cardiovascular care. The inclusion of representative populations within cardiovascular clinical research ensures that data derived from clinical trials translate into effectiveness for all populations, particularly as cardiovascular therapeutics move toward personalized approaches. In this article, we review the importance of including underserved populations in cardiovascular clinical research and the key barriers to their participation. We explore system‐level strategies that have only recently demonstrated large‐scale feasibility within the cardiovascular research paradigm, such as community‐engaged research and clinical trial decentralization, to increase access and engage underserved communities. Decentralizing clinical trials can overcome many of the barriers associated with performing clinical trials at traditional study sites. Additionally, increasing clinical trial workforce diversity and including community clinicians and stakeholders during study design, recruitment, and administration can improve representation within clinical trials. Finally, we propose a holistic approach to improving the diversity of cardiovascular clinical trial participants through the application of the hub‐and‐spoke organizational model.