BACKGROUND:Ethnic inequalities exist in the management of patients with cancer with acute coronary syndrome (ACS). Given their under-representation in trials, ethnic minority patients are often studied using large registries, but the quality of ethnicity coding in these datasets remains unclear. METHODS:Agreement of ethnicity coding and outcomes for patients with cancer with ACS (2000-2018) was examined across four national datasets: National Cancer Registration and Analysis Service (NCRAS), Myocardial Ischaemia National Audit Project (MINAP), British Cardiovascular Intervention Society database (BCIS) and Hospital Episode Statistics (HES). Three linkages were performed: NCRAS-MINAP, NCRAS-MINAP-BCIS, NCRAS-MINAP-HES, with four groups based on ethnicity agreement: Concordant, Discordant, Missing (1 and ≥2 datasets). Multivariable logistic regression and Cox's Proportional Hazards models assessed 1-year and long-term (≤5 years) cardiac and cancer-related death for each agreement group. RESULTS:Among three linkages, just over half of the ethnicities were concordant (range: 52.4%-53.8%). Discordance was relatively low (range 1.2%-5.5%) while missingness ranged between 28.6% and 43.4% in 1 dataset and 1.6%-12.6% in ≥2 datasets. Ethnicity correlation between individual datasets was poor, lowest between NCRAS and BCIS (r=0.318). We observed higher 1-year and long-term cardiac and cancer deaths in several of the Missing (1 and ≥2 datasets) groups across the three linkages, compared with the Concordant group. CONCLUSION:Across four national datasets for patients with cancer with ACS, nearly half of patients had missing ethnicity in at least one dataset, which was associated with higher cardiac or cancer mortality. Inconsistency in ethnicity coding represents a missed opportunity to examine health inequalities in this high-risk and understudied population.

BACKGROUND:Following myocardial infarction, late gadolinium enhancement (LGE) assessed by cardiovascular magnetic resonance (CMR) provides a reliable metric for risk stratification and therapeutic planning. However, conventional segmentation methods are time-consuming and labor-intensive, with high inter-observer variability and inconsistent performance in routine clinical practice. This study sought to develop an interactive deep learning system for scar segmentation and quantification. METHODS:The framework was developed and evaluated using LGE-CMR images from 348 patients with chronic myocardial infarction (244 training, 51 validation, and 53 test). The model incorporates prompt-guided segmentation and leverages a vision foundation model adapted for medical imaging, integrated into a clinician-facing interface for real-time interaction, and automated quantification. Training used a composite loss function combining Dice overlap, voxel-wise cross-entropy, and Kullback-Leibler divergence against soft labels to address annotation uncertainty. Performance was evaluated on a held-out test set using expert manual annotations as the reference standard, with assessment of segmentation accuracy, repeatability, and agreement with the conventional full-width at half-maximum method (FWHM). RESULTS:The framework achieved expert-level segmentation performance on the test set (Dice similarity coefficient = 0.74 ± 0.10; Hausdorff distance = 5.87 ± 6.79 mm) with a median scar mass error of 1.28 g (interquartile range [IQR] 0.74-2.34), corresponding to 1.4% (IQR 0.81-2.47) of left ventricular mass. Repeatability analysis (n = 41) demonstrated excellent agreement, with both inter- and intra-observer concordance correlation coefficients of 0.999 (compared with 0.737 and 0.952, respectively, for the conventional FWHM). Segmentation time was substantially reduced when using the interactive tool compared with the conventional workflow, averaging 65 ± 34 s per patient. Performance and repeatability remained high across the test set with differing levels of image quality. CONCLUSION:The proposed framework for scar segmentation with a human-in-the-loop design enables fast, accurate, and highly reproducible myocardial scar quantification from LGE-CMR. This may provide more consistent performance in routine clinical workflows.

Aims:In patients with heart failure with reduced ejection fraction (HFrEF), determining the aetiology of cardiac dysfunction has important therapeutic and prognostic implications. Cardiovascular magnetic resonance (CMR) enables comprehensive phenotyping of HFrEF; however, it remains uncertain whether the choice of pharmacological stress agent influences the hyperaemic response required for reliable ischaemia assessment. We sought to compare the hyperaemic effects of adenosine and dobutamine in patients with HFrEF using quantitative perfusion CMR. Methods and results:Patients with HFrEF [left ventricular ejection fraction (LVEF) ≤40%] prospectively underwent 3-Tesla CMR comprising functional cine imaging, late gadolinium enhancement (LGE), and first-pass perfusion imaging at rest and during pharmacological stress with (i) adenosine (140-210 μg/kg/min) and (ii) dobutamine (10-30 µg/kg/min). Perfusion maps were reconstructed inline with automated, pixel-wise quantification of myocardial blood flow (MBF). The hyperaemic response, defined by global myocardial perfusion reserve (MPR), was calculated as the quotient of stress and rest MBF and compared between stress protocols. Fifty-three patients with HFrEF (mean age 63 ± 10 years, 77% male, mean LVEF 36 ± 10%, infarction 59%, and non-ischaemic focal fibrosis 21%) with paired adenosine and dobutamine stress-perfusion data were analysed. Compared with dobutamine, adenosine produced a higher global MPR [mean difference: +0.61 (95% CI: 0.35, 0.88); P < 0.001], which remained significant at the segmental level following adjustment for age, sex, type 2 diabetes, LVEF, and LGE presence [mean difference: +0.63 (95% CI: 0.55, 0.71); P < 0.001]. Conclusion:In patients with HFrEF, adenosine induces a greater hyperaemic response than dobutamine; however, whether this impacts on the diagnostic assessment of ischaemia remains to be established (Trial registration: NCT03661827).

Spontaneous coronary artery dissection (SCAD) is a cause of acute myocardial infarction predominantly affecting adult women. A proportion of SCAD cases are associated with rare heritable connective tissue disorders. Vascular EDS (vEDS), due to deleterious variants in COL3A1, is one of the most common of these. Our aim was to identify specific features of SCAD in vEDS which may aid patient selection for genetic testing. A systematic review of published cases of individuals with SCAD and vEDS was conducted. Additionally, patients with SCAD and genetically confirmed vEDS (SCAD-vEDS) were identified through the UK national EDS service and UK SCAD registry. Data were collected on presentation, management and extra-cardiac findings. Angiography was compared with an age and sex-matched, exome sequenced, control cohort with SCAD but without vEDS (SCAD-nonvEDS). Data from ten SCAD-vEDS patients were identified. There was a lower average age of SCAD and higher proportion of males in individuals with SCAD-vEDS, however differences should be interpreted carefully given cohort size. Fifty-six cases of SCAD-vEDS were identified through systematic review. Systemic features were present in most but not all cases. This report presents a new, angiographically characterised case-control cohort along with a systematic review of the current literature. Whilst clinical differences appear between the SCAD-vEDS and SCAD-nonvEDS groups, these are insufficient to accurately distinguish SCAD-vEDS from the general SCAD population. All individuals with SCAD should be evaluated for underlying vEDS but clinical assessment will miss some cases. Wider genetic testing in some SCAD patients may be merited to enable appropriate management. Systematic review registration: https://www.crd.york.ac.uk/prospero/536751 Identifier: 536751.

BACKGROUND:In the assessment of patients with suspected coronary artery disease (CAD), the diagnostic role of stress-perfusion cardiovascular magnetic resonance (CMR) is well established. However, its reliance on gadolinium-based contrast agents may restrict its application in certain populations. T1 mapping during vasodilatory stress has been proposed as a contrast-free alternative for detecting CAD. This study sought to compare the diagnostic accuracy of adenosine-stress T1 reactivity (ΔT1) with that of stress-perfusion CMR for identifying hemodynamically significant CAD. METHODS:Patients with suspected angina referred for diagnostic invasive coronary angiography underwent 3-Tesla CMR consisting of the following: (1) T1 mapping at rest and following intravenous adenosine using a modified Look-Locker inversion recovery sequence, (2) stress and rest perfusion, and (3) late-gadolinium enhancement. Significant CAD was defined invasively as fractional flow reserve ≤0.80 in epicardial vessels ≥2 mm diameter (or quantitative flow ratio ≤0.80 if unavailable). A ΔT1 vessel threshold (% increase in T1 from rest to stress) was derived from receiver operating characteristic analysis, using invasive coronary angiography as the reference standard. Stress-perfusion CMR was assessed qualitatively with CAD determined by the presence of ischemia and/or infarction, (A) per-vessel (as determined by two independent readers) and (B) per-patient (following consensus read). RESULTS:Of 121 prospectively recruited patients, 115 had paired T1 mapping and coronary angiography data (mean age 66 ± 9 years, 72% [83/115] male, CAD prevalence 51% [59/115]). ΔT1 demonstrated poor diagnostic performance for detecting significant CAD (area under the curve 0.59 [95% CI: 0.52, 0.65], p = 0.011), with an optimal vessel threshold ≤4.36% giving accuracy 54.9%, sensitivity 68.3%, and specificity 49.2%. Stress-perfusion CMR demonstrated superior diagnostic accuracy compared to ΔT1: (A) per-vessel (for the two independent reads, +26.2% [19.4%, 32.6%] and +26.7% [19.9%, 33.3%], both p<0.001) and (B) per-patient (for consensus read, +21.7% [10.2%, 32.6%], p<0.001). CONCLUSION:In patients with suspected angina, ΔT1 demonstrates limited diagnostic accuracy for the detection of obstructive CAD. Future efforts should be directed toward alternative contrast-free methods for the reliable detection of CAD in this population.

BACKGROUND:Spontaneous coronary artery dissection (SCAD) is an uncommon cause of myocardial infarction that disproportionately affects women, particularly during pregnancy and the peripartum period. Limited understanding of its underlying pathophysiology hinders the development of effective preventive and therapeutic strategies. METHODS:This study investigated associations between genetically predicted circulating proteins and tissue-specific RNA levels with genetically predicted SCAD risk using Mendelian randomization and Bayesian colocalization. Genetic scores for >1500 circulating proteins were derived from the UK Biobank (N=34 557) and deCODE (N=35 559). Scores for 13 848 gene transcripts in arterial and fibroblast tissues were generated from Genotype-Tissue Expression data. Associations between these scores and SCAD were assessed in a genome-wide association study meta-analysis of 1917 individuals with SCAD and 9292 controls. Findings were validated in vitro using mass spectrometry-based proteomic analysis of extracellular vesicles from 50 patients with SCAD and 50 healthy controls. RESULTS:Genetic associations of 4 circulating proteins with SCAD (AFAP1 [actin filament-associated protein 1], ECM1 [extracellular matrix protein 1], SPON1 [spondin 1], and STAT6 [signal transducer and activator of transcription 6]) were identified. Two were supported by gene expression data (AFAP1 and ECM1), and one by tissue-specific Bayesian colocalization analyses (ECM1). Protein interaction mapping identified potential shared pathways through the JAK-STAT (Janus kinases and signal transducers and activators of transcription) signaling pathway and inflammatory regulation. Mass spectrometry-based proteomic analysis demonstrated that ECM1 was significantly upregulated in SCAD cases versus controls. CONCLUSIONS:Integrative analysis of proteomic, transcriptomic, and experimental data revealed 4 circulating proteins genetically associated with SCAD risk, with ECM1 emerging as a key protein with a likely causal role in SCAD pathogenesis. These findings highlight biological pathways for mechanistic studies and protein targets for potential therapeutic interventions.

Background Epicardial adipose tissue (EAT) is a metabolically active visceral fat depot that is both a sensor and a modulator of myocardial biology and changes its composition in response to paracrine signals from the myocardium. We hypothesized that radiomic characterization of EAT from routine coronary computed tomographic angiography (CCTA) can noninvasively capture this adverse remodeling and enable early heart failure (HF) risk stratification. Objectives We sought to develop and externally validate a reproducible radiomic signature of EAT associated with incident HF. Methods We conducted a multicenter cohort study of 72,751 adults without known HF or myocardial infarction undergoing CCTA across 9 UK centers (2007-2022). We deployed a fully automated pipeline to segment EAT and extract 1,655 volumetric, shape, and higher-order radiomic texture features. Using a harmonized survival autoencoder architecture, we derived the fat radiomic profile for HF (FRPHF). The model was developed in 59,327 individuals from 7 centers (age 57 ± 13 years, 47.5% female) and externally tested in 13,424 participants from 2 geographically distinct centers (58 ± 12 years, 49.4% female). Survival models were adjusted for age, sex, and conventional risk factors, including coronary artery disease (CAD) severity and EAT volume. Results Over a median follow-up of 5.1 and 4.0 years, 1,737 (2.9%) and 363 (2.7%) participants developed HF in the internal and external validation cohorts, respectively. FRPHF demonstrated robust discrimination (C-statistics: 0.869 [95% CI: 0.850-0.889] internal; 0.850 [95% CI: 0.831-0.870] external). Each 25-percentile increase in FRPHF was associated with a nearly 4-fold higher adjusted HF risk (adjusted HRs: 3.90 [95% CI: 3.13-4.84] internal; 3.79 [95% CI: 3.01-4.76] external; both P < 0.001), with individuals in the highest decile exhibiting a nearly 20-fold higher risk compared with the lowest decile. In the external cohort, addition of FRPHF to conventional risk models, including EAT volume and CAD severity, significantly improved 5-year discrimination (ΔAUC: 0.047; 95% CI: 0.029-0.065) and net reclassification (NRI: 0.39; 95% CI: 0.29-0.48) and suggested net clinical benefit on decision curve analysis. The associations were consistent across demographic subgroups and across the ejection fraction spectrum. Conclusions Automated radiomic phenotyping of EAT from routine CCTA enables scalable, biologically informed stratification of future HF risk before clinical onset, positioning opportunistic imaging-based visceral fat profiling as a potential tool for precision prevention.

BACKGROUND:Accurate assessment of mortality, bleeding, and atherothrombotic risk in patients with cancer and acute coronary syndrome could inform novel personalised treatment strategies, but no standardised tools for this purpose exist. We aimed to develop and validate a clinically applicable risk score for mortality, bleeding, and ischaemic events in patients with cancer and acute coronary syndrome. METHODS:In this model development and validation study, we obtained data for 1 017 759 patients who presented with acute coronary syndrome in England, UK (n=815 170; 36 771 with cancer), Sweden (n=194 059; 10 262 with cancer), and Switzerland (n=8530; 203 with cancer) between Jan 1, 2004, and Aug 8, 2023. Machine learning models were developed to predict all-cause mortality, major bleeding events, and ischaemic events, defined as a composite of cardiovascular death, myocardial infarction, and ischaemic stroke, in patients with cancer and acute coronary syndrome from England in a competing risks framework with a prediction horizon of 6 months. Final models (the ONCO-ACS score) were externally validated in geographically distinct held out datasets from the English Midlands, Sweden, and Switzerland. FINDINGS:Patients with cancer and with acute coronary syndrome were characterised by high rates of mortality (cumulative incidence 27·8% [95% CI 27·3-28·3]), major bleeding (7·3% [7·0-7·5]), and ischaemic events (16·1% [15·7-16·4]) and had a distinct risk profile. The ONCO-ACS score was informed by a single set of variables: tumour type, time since cancer diagnosis, metastatic disease, age, haemoglobin, heart rate, estimated glomerular filtration rate, BMI, Killip class, cardiac arrest, and major bleed within 6 months. Accounting for traditional and cancer-related risk factors, ONCO-ACS showed a time-dependent area under the receiver operating characteristic curve (tAUC) at 6 months of 0·84 (0·83-0·85) for all-cause mortality, 0·70 (0·68-0·73) for major bleeding, and 0·79 (0·78-0·81) for ischaemic events on internal validation. On external validation, ONCO-ACS achieved similar performance for all-cause mortality (tAUC at 6 months 0·84 [0·82-0·85] for the English Midlands, 0·80 [0·79-0·82] for Sweden, and 0·83 [0·76-0·91] for Switzerland), major bleeding events (0·70 [0·67-0·74] for the English Midlands, 0·67 [0·65-0·70] for Sweden, and 0·74 [0·57-0·91] for Switzerland), and ischaemic events (0·76 [0·74-0·78] for the English Midlands, 0·70 [0·69-0·72] for Sweden, and 0·73 [0·61-0·86] for Switzerland). ONCO-ACS was well calibrated and decision curve analyses suggested favourable clinical utility. Applying ONCO-ACS to current guidelines suggests that most patients with cancer and acute coronary syndrome qualify for invasive management and long dual antiplatelet therapy using clopidogrel. INTERPRETATION:The ONCO-ACS score provides a validated practical tool for predicting mortality, bleeding, and ischaemic risk in patients with cancer and acute coronary syndrome. Combined assessment of competing outcome risks could facilitate balancing treatment benefits and harms. FUNDING:British Heart Foundation, Cancer Research UK, Swiss Heart Foundation, University of Zurich Foundation, Kurt-Senta-Herrmann Foundation, Theodor-Ida-Herzog-Egli Foundation, Foundation for Cardiovascular Research-Zurich Heart House, Swedish ALF Research Funds.

AIMS:In patients with suspected coronary artery disease (CAD), the role of adenosine-stress cardiovascular magnetic resonance (CMR) is well established. However, to meet increasing demand, improving its time efficiency and cost-effectiveness is critical. Recent advances in accelerated, free-breathing cine and scar imaging now enable accelerated stress-perfusion protocols. This study evaluated whether an accelerated, stress-only perfusion protocol achieves non-inferior diagnostic accuracy compared with a standard stress-rest perfusion CMR protocol for detecting significant CAD. METHODS AND RESULTS:Patients with suspected angina referred for invasive coronary angiography (ICA) underwent two 3-Tesla CMR scans (standard and accelerated protocols), on separate days in randomized order. Significant CAD was defined as fractional flow reserve (FFR) ≤ 0.80 in epicardial vessels ≥2 mm diameter (or quantitative flow ratio ≤0.80 if FFR unavailable). CMR images were evaluated qualitatively with (i) primary per-vessel analysis (determined by two independent readers) and (ii) secondary per-patient analysis (following consensus read). Of 167 prospectively recruited patients, 150 completed both CMR protocols and ICA (mean age 66 ± 10 years, 71% male, CAD prevalence 51%). The accelerated scan was better tolerated by patients, with scan duration 19 ± 5 min (24 min shorter than the standard protocol [95% CI: 23, 25], P < 0.001). Compared with standard CMR, accelerated CMR achieved non-inferior per-vessel diagnostic accuracy at a pre-specified 5% non-inferiority margin (+0.7% [-2.7%, 4.0%], pnon-inferiority = 0.001 and +3.4% [-0.1%, 6.8%], pnon-inferiority < 0.001 for the two readers). Accelerated CMR also achieved comparable per-patient accuracy (+4.6% [-1.5%, 11.0%], P = 0.189 for consensus read; accuracy 88.6%, sensitivity 84.2%, and specificity 93.2%). CONCLUSION:Compared to standard stress-perfusion CMR, an accelerated stress-perfusion protocol achieves non-inferior diagnostic accuracy at the vessel level, with a time saving of over 20 min per scan. Accelerated imaging may prove effective in the clinical arena to evaluate patients with suspected angina.

Objectives We hypothesised that there is substantial variation in acute myocardial infarction (AMI) treatment across English hospitals, particularly for people hospitalised for non-ST-elevation myocardial infarction (NSTEMI) and with reduced kidney function. This study aimed to describe this variation at the hospital and the individual level to understand treatment variation and potential disparities in AMI management among people with reduced kidney function. Design Cross-sectional study. Setting Secondary care in England. Participants People hospitalised for AMI (ST-elevation myocardial infarction (STEMI) or NSTEMI) in English hospitals and captured in the Myocardial Ischaemia National Audit Project, 2014 to 2019. Kidney function was defined using estimated glomerular filtration rate (eGFR) derived from the serum creatinine recorded within 24 hours of AMI admission. Outcome measure The primary outcome was recorded invasive cardiac intervention (at least one of angiography, percutaneous coronary intervention and coronary artery bypass graft) compared with conservative management. Results We included 361 259 people with a first hospitalisation for AMI (STEMI or NSTEMI) at 209 hospitals for hospital-level analyses and 292 572 people with complete covariable data at 207 hospitals for individual-level analyses. We found substantial variation in the mean proportion of people with NSTEMI managed invasively across hospitals in England. At the individual level, using multivariable logistic regression to derive adjusted predicted probabilities to describe the association between kidney function and AMI management (invasive vs conservative management), we found that people had a lower adjusted predicted probability of being treated with invasive cardiac management with worsening eGFR range, particularly for NSTEMI cases (eGFR range 2: 76.6% (95% CI 76.3 to 76.8) vs eGFR range 5: 44.5% (95% CI 41.2 to 47.5)). Conclusions There is substantial AMI treatment variation across hospitals in England, particularly among people hospitalised for NSTEMI with reduced kidney function. Further research is needed to evaluate the comparative effectiveness of NSTEMI management strategies for complex patients.

Current data on spontaneous coronary artery dissection (SCAD) predominantly originate from Europe or Caucasians with limited information about other ethnicities. This scoping review presents the evidence on SCAD in non-Western countries. The prevalence of SCAD diagnosis was 1.0% [95% confidence interval (95% CI): 0.0-3.0, I 2 = 99%] among patients presenting with myocardial infarction, increasing to 5.0% (95% CI: 1.0-16.0, I 2 = 99%) among females. The mean age was 51.3 years with females accounting for 54.0% of patients. A conservative revascularization management was reported in 48.0% (95% CI: 32.0-65.0, I 2 = 85%) of patients. Antiplatelet therapy was reported as dual (68.0%, 95% CI: 37.0-89.0, I 2 = 90%) in only three studies. A death rate (3.0%) was similar during hospitalization and at mean follow-up of 23.42 months. In conclusion, there is a marked variability in the clinical course of patients with SCAD as well heterogeneity among the included studies. This review identified knowledge gaps in our understanding of SCAD in non-Western countries that should be addressed in future prospective studies.

BACKGROUND:Fluoropyrimidine chemotherapy is administered first-line for many gastrointestinal cancers. However, patients with cardiovascular disease commonly receive alternative treatment due to cardiotoxicity concerns. OBJECTIVES:This study sought to assess the risks of all-cause mortality and acute cardiovascular events with fluoropyrimidine treatment. METHODS:We conducted an observational cohort study applying a target trial emulation framework to linked national cancer, cardiac, and hospitalization registry data from the Virtual Cardio-Oncology Research Initiative. Adults diagnosed with tumors eligible for fluoropyrimidine-based chemotherapy as first-line therapy were included. All-cause mortality and a composite of hospitalization for acute cardiovascular events (acute coronary syndrome, heart failure, cardiac arrhythmia, cardiac intervention, cardiac arrest, and cardiac death) were compared in patients treated with fluoropyrimidine-based chemotherapy vs alternative management. Adjusted, weighted pooled logistic regression models were used to estimate the 1-year risk difference (RD). RESULTS:Among 103,110 patients (mean age 69.7 years, 59% male), the absolute risk of death at 1 year was significantly lower in fluoropyrimidine-treated patients (RD: -7.7%; 95% CI: -8.7% to -6.7%) with a small increased risk of acute cardiovascular events (RD: 0.9%; 95% CI: 0.0% to 1.9%). This was primarily due to arrhythmias (RD: 0.8%; 95% CI: 0.1% to 1.6%) and cardiac arrest (RD: 0.3%; 95% CI: 0.1% to 0.5%), with no increased risk of acute coronary syndromes including in the subgroup of patients with pre-existing coronary artery disease. CONCLUSIONS:The markedly improved overall survival with fluoropyrimidines in patients with gastrointestinal cancer significantly outweighs the small risk of cardiac arrhythmia and arrest. Oncologists should take this into consideration for decision making to avoid undue clinical conservatism, particularly in patients with cardiovascular disease.

AIMS:Coronary computed tomography angiography (CCTA) is a first-line investigation for chest pain in patients with suspected obstructive coronary artery disease (CAD). However, many acute cardiac events occur in the absence of obstructive CAD. We assessed the lifetime cost-effectiveness of integrating a novel artificial intelligence-enhanced image analysis algorithm (AI-Risk) that stratifies the risk of cardiac events by quantifying coronary inflammation, combined with the extent of coronary artery plaque and clinical risk factors, by analysing images from routine CCTA. METHODS AND RESULTS:A hybrid decision-tree with population cohort Markov model was developed from 3393 consecutive patients who underwent routine CCTA for suspected obstructive CAD and followed up for major adverse cardiac events over a median (interquartile range) of 7.7(6.4-9.1) years. In a prospective real-world evaluation survey of 744 consecutive patients undergoing CCTA for chest pain investigation, the availability of AI-Risk assessment led to treatment initiation or intensification in 45% of patients. In a further prospective study of 1214 consecutive patients with extensive guidelines recommended cardiovascular risk profiling, AI-Risk stratification led to treatment initiation or intensification in 39% of patients beyond the current clinical guideline recommendations. Treatment guided by AI-Risk modelled over a lifetime horizon could lead to fewer cardiac events (relative reductions of 11%, 4%, 4%, and 12% for myocardial infarction, ischaemic stroke, heart failure, and cardiac death, respectively). Implementing AI-Risk Classification in routine interpretation of CCTA is highly likely to be cost-effective (incremental cost-effectiveness ratio £1371-3244), both in scenarios of current guideline compliance, or when applied only to patients without obstructive CAD. CONCLUSIONS:Compared with standard care, the addition of AI-Risk assessment in routine CCTA interpretation is cost-effective, by refining risk-guided medical management.