Valvular heart disease (VHD) affects millions worldwide and remains a major cause of morbidity and mortality, placing a substantial and growing burden on healthcare systems. Over the past two decades, transcatheter therapies have emerged to meet this challenge, transforming the management of aortic, mitral, and tricuspid valve disease. Initially developed for inoperable or high-risk surgical patients, procedures such as transcatheter aortic valve implantation (TAVI) and mitral transcatheter edge-to-edge repair (M-TEER) are now routinely offered across a broader risk spectrum. More recently, tricuspid therapies, including tricuspid transcatheter edge-to-edge repair (T-TEER) and transcatheter valve replacement (TTVR), have emerged to address a significant unmet clinical need. With transcatheter interventions becoming more widely available, clinicians across general and acute medical specialities are increasingly likely to encounter patients before and after these procedures. Familiarity with these therapies will support better decision-making and coordinated care. This review summarises the evolution of transcatheter valve therapy, its role alongside surgery, and the evidence supporting its use. Surgery remains the gold standard for younger or low-risk patients, particularly where long-term durability is essential. Transcatheter therapies now offer safe and effective treatment for older patients, including those with frailty or significant comorbidity, supported by landmark trials, which have demonstrated favourable clinical outcomes in carefully selected populations and underpinned guideline endorsement across risk categories. The importance of the multidisciplinary Heart Team is emphasised, ensuring treatment decisions reflect individual anatomy, comorbidity burden, life expectancy, and procedural risk. As device technology, imaging, and procedural expertise continue to advance, the integration of surgical and transcatheter approaches will support more individualised care and broaden access to definitive treatment for patients across the clinical spectrum.

Cardiogenic shock complicates takotsubo syndrome (TTS) in approximately 10

Background Severe native aortic regurgitation due to cusp perforation after healed infective endocarditis presents challenges for transcatheter aortic valve implantation (TAVI), particularly without annular calcification. Case Summary A 46-year-old patient with healed infective endocarditis presented with severe eccentric aortic regurgitation due to perforation of the left coronary cusp. Given prohibitive surgical risk, transfemoral TAVI using the JenaValve Trilogy system was performed. Controlled deflection and rotational repositioning enabled coaxial alignment of the valve above the native cusps prior to deployment, resulting in no paravalvular leak and excellent hemodynamic outcome. Discussion This case highlights the technical challenges of TAVI in aortic regurgitation with cusp perforation and demonstrates how leaflet-locator anchoring, delivery system deflection, and multimodality imaging enable safe and effective valve positioning. Take-Home Message Cusp perforation may cause locator misengagement during TAVI; controlled deflection and repositioning are critical to achieve safe, stable deployment.

Intracoronary (IC) imaging-guided percutaneous coronary intervention (PCI) improves clinical outcomes in patients with high clinical and anatomical risk when compared to interventions guided by angiography alone. Recent Class I recommendations for the use of IC imaging guidance when performing PCI in left main stem or complex lesions may result in a significant uptake as the technology is embraced as standard of care. Routine application of IC imaging will provide interventional cardiologists with a wealth of high-fidelity intracoronary data on plaque composition and distribution. When paired with emerging data regarding the importance of plaque anatomical characteristics, developments in artificial intelligence and computational fluid dynamics, lesion stratification with IC imaging may herald the next paradigm shift in this field. In this review, we will explore this important emerging application of IC imaging to inform morphology-guided PCI, identify high-risk lesions for targeted therapies, and consider the prospects of harnessing automated image interpretation with artificial intelligence technologies to achieve an integrated physiological and morphological assessment. Lesion stratification with IC imaging has the potential to shape the future of interventional cardiology practice to guide therapies within and beyond the confines of the cardiac catheterisation laboratory.

Background:Crossing the aortic valve with the device during transcatheter aortic valve implantation (TAVI) can be challenging, with several troubleshooting techniques described. Balloon-assisted valve crossing is commonly considered, although the need for a second femoral access of sufficient size to accommodate the valvuloplasty balloon limits its appeal. Case summary:In this two-case series, we demonstrate the feasibility of balloon-assisted aortic valve crossing for both balloon-expandable and self-expanding TAVI platforms using percutaneous transluminal peripheral angioplasty balloons delivered via trans-radial access. Where difficulty was encountered with crossing the valve and basic techniques were unsuccessful, the BACTRA (Balloon-Assisted Crossing via Trans-Radial Access) technique facilitated valve crossing and successful valve deployment. In Case 1, the inability to cross the valve related predominantly to severe tortuosity throughout the arterial tree and a subsequent lack of torque and device manipulation to negotiate the native valve. In Case 2, the issue largely related to the horizontal aorta. Both patients had successful valve deployment and were subsequently discharged well. Discussion:Regardless of the underlying cause or the TAVI platform utilized, this report demonstrates that the BACTRA technique has several plausible benefits. Valve crossing was facilitated in both cases without additional arterial punctures or sheath upsizing, allowing the procedures to proceed efficiently and safely without any added risk of vascular complications. Procedural steps, troubleshooting, and equipment compatibility are outlined in this case series.

AIMS:The ARREST trial demonstrated that in adult patients, transfer to a cardiac catheter laboratory in a cardiac arrest centre (CAC) following resuscitated out-of-hospital cardiac arrest (OHCA) without ST-elevation did not reduce deaths at 30 days compared with delivery to the geographically closest emergency department (standard care). More than half of the CACs had a co-located emergency department to which patients were delivered as part of the standard care arm, which may have influenced outcomes. AIMS:We performed a pre-specified as-treated analysis to determine if a CAC and the location patients were delivered to, either emergency department or cardiac catheter laboratory, reduced deaths. METHODS AND RESULTS:Patients (aged ≥18 years) with resuscitated OHCA without ST elevation who were enrolled in the ARREST trial were grouped according to the location they were to delivered to- either an emergency department with or without a co-located CAC or a cardiac catheter laboratory within a CAC-at one of 35 hospitals in London, UK-by London Ambulance Service irrespective of randomized allocation. The as-treated population was therefore analysed as one of three groups: 1) emergency department in a CAC, 2) direct to a cardiac catheter laboratory in a CAC, and 3) emergency department in a non-CAC. The primary outcome of the trial was all-cause mortality at 30 days. Secondary outcomes included all-cause mortality at 3 months and neurological outcome at discharge and 3 months. A pre-specified analysis adjusting for age, sex, initial shockable rhythm, witnessed cardiac arrest, bystander CPR, the time from cardiac arrest until ROSC, and location of cardiac arrest was performed in the as-treated groups. Between 15 January 2018 and 1 December 2022, a total of 862 participants were enrolled into the trial. Data for the primary outcome for this analysis were available in 818/862 (94.9%). Patients delivered to an ED in a CAC had fewer deaths at 30 days compared with the ED in a non-CAC group (83/182, 45.6% vs. 178/233, 76.4%; adjusted OR 0.43, 95% CI 0.24 to 0.76; P = 0.0039). Patients delivered to a cardiac catheter laboratory in a CAC also had fewer deaths compared with the ED in a non-CAC group, but there was no statistical difference (250/403, 62.0%: adjusted OR 0.72, 95% CI 0.44 to 1.18; P = 0.19). Survival with a favourable neurological outcome at hospital discharge occurred in 88/177 (49.7%) of the ED in a CAC group, 130/406 (32%) of the catheter laboratory in a CAC group, and 42/228 (18.4%) of the ED in a non-CAC group. CONCLUSION:In this as-treated analysis of the ARREST trial, in adult patients with resuscitated OHCA without ST-elevation, we observed a lower 30-day mortality and favourable neurological outcomes following delivery to an ED in a CAC and cardiac catheter laboratory in CAC, when compared with delivery to ED in a non-CAC.

BACKGROUND:The purpose of this study was to prospectively validate the MIRACLE2 score in the GLOBAL-MIRACLE registry, a multicenter, international, prospective registry of patients admitted with resuscitated out-of-hospital cardiac arrest of presumed cardiac cause. METHODS:From January 1, 2022 to May 31, 2023, 770 patients were recruited from 11 centers across 5 countries. The primary end point was poor neurological outcome (Cerebral Performance Category 3-5) at hospital discharge. Model discrimination was assessed by the area under the receiver operating characteristic curve. We compared the discriminatory performance of the MIRACLE2 score against Cardiac Arrest Hospital Prognosis, out-of-hospital cardiac arrest, Target Temperature Management, NULL-PLEASE, C-GRAPH, and rCAST. RESULTS:The primary end point occurred in 395 (51.2%) patients. The MIRACLE2 score had an area under the curve of 0.861 (95% CI, 0.835-0.887). A MIRACLE2 score ≤2 had a negative predictive value of 87.8%, while a score of ≥7 had a positive predictive value of 98.3%. The MIRACLE2 score had equal performance to the TTM risk tool (P=0.12) but better discriminatory performance than other risk tools (P<0.0001). The MIRACLE2 score showed good performance in those with ST-segment-elevation myocardial infarction (0.851 [95% CI, 0.816-0.886]) and without ST-segment-elevation myocardial infarction (0.873 [95% CI, 0.834-0.912]) and in those with cardiogenic shock (0.832 [95% CI, 0.789-0.875]) and without cardiogenic shock (0.853 [95% CI, 0.810-0.895]). CONCLUSIONS:The MIRACLE2 score is a practical risk tool that shows excellent discrimination performance for poor neurological outcome after presumed cardiac cause out-of-hospital cardiac arrest, including based on hemodynamic status and admission 12-lead ECG. Early stratification of out-of-hospital cardiac arrest patients using the MIRACLE2 score should be evaluated in future randomized controlled trials.

BACKGROUND:Current risk scores inadequately predict long-term mortality after transcatheter aortic valve replacement (TAVR), limiting their ability to guide decisions around procedural futility. We aimed to develop and externally validate a machine learning (ML) model using only preprocedural variables to predict 1-year all-cause mortality. METHODS:An ML model was trained on a retrospective cohort of 1025 TAVR patients using 52 clinical and echocardiographic variables. Feature selection and model tuning were performed via a multiobjective evolutionary algorithm to optimise predictive performance and model simplicity. The final model used 13 preprocedural variables and was externally validated in an independent cohort of 270 patients. Performance was compared with European System for Cardiac Operative Risk Evaluation II (EuroSCORE II), FRANCE-2 and TAVI2-SCORE using the area under the curve (AUC), calibration and net reclassification improvement (NRI). RESULTS:The ML model demonstrated excellent discrimination, with AUCs of 0.81 in the discovery cohort and 0.84 in the external validation cohort. This exceeded the performance of EuroSCORE II (AUC: 0.61 and 0.70), FRANCE-2 (0.52 and 0.58) and TAVI2-SCORE (0.56 and 0.64). Calibration plots showed strong agreement between predicted and observed risks. NRI in the test set compared with FRANCE-2 was 0.62 (95% CI: 0.49 to 0.75); compared with TAVI2-SCORE, it was 0.36 (95% CI: 0.14 to 0.61). The final model incorporated age, atrial fibrillation, creatinine, haemoglobin, pulmonary function, frailty markers (Katz Index, poor mobility) and tricuspid regurgitation. Misclassification analysis revealed that most errors were clustered near the decision threshold, with no evidence of systematic bias. Performance was consistent across subgroups and robust to temporal and institutional variation. CONCLUSION:This externally validated ML model, using 13 routinely available variables, significantly outperforms existing risk scores in predicting 1-year mortality post-TAVR. Its simplicity and generalisability support its potential use in real-world clinical decision-making to identify patients at high risk of procedural futility.

BACKGROUND:Transcatheter tricuspid valve replacement (TTVR) is an emerging therapy for severe tricuspid regurgitation with an evolving complication profile. Fatal prosthetic valve endocarditis (PVE) following orthotopic TTVR appears exceptionally rare, with detailed pathologic description through specialist cardiovascular autopsy remaining limited. CASE SUMMARY:A 65-year-old man with severe functional tricuspid regurgitation and persistent atrial fibrillation underwent TTVR. The following day, he developed complete heart block requiring pacemaker implantation. He remained well at 1 and 3 months, with improving symptoms and unremarkable bloods. At 6 months, he developed nonspecific viral-like symptoms over 48 hours culminating in death at home. Routine postmortem examination attributed death to coronary artery disease. Specialist cardiovascular pathology demonstrated PVE with large vegetations, atrioventricular nodal obliteration, left atrial communication enabling systemic septic embolization, diffuse coronary microembolization, and widespread left ventricular microabscesses. DISCUSSION:Fatal PVE after TTVR may present with nonspecific prodromal symptoms. Unexplained death after transcatheter valve intervention warrants specialist cardiovascular pathology. TAKE HOME MESSAGE:Prosthetic valve endocarditis after transcatheter tricuspid valve replacement may present with nonspecific symptoms and rapid clinical deterioration; unexplained death should prompt specialist cardiovascular pathology.

BACKGROUND:Cardiogenic shock (CS) is a common complication of patients with resuscitated out-of-hospital cardiac arrest (OHCA). AIMS:This study investigates whether the change in SCAI Shock Grade, measured between hospital and intensive care admission (ICU), is associated with outcome after OHCA. METHODS:Patients with OHCA of suspected cardiac etiology were included from the King's Out-of-Hospital Cardiac Arrest Registry between 2012 and 2021. SCAI Shock Grade was determined on hospital and ICU admission. Patients were categorized into worsening, static, or improving SCAI Grade. The primary endpoint was in-hospital mortality at 30 days. Predictors of SCAI change and circulatory mortality were assessed using univariable and multivariable regression. RESULTS:Of 493 patients (median age 63 years, 77% male), 68% had a shockable rhythm, 80% were witnessed, and 94% had bystander CPR. SCAI Grade between hospital and ICU admission improved in 32% of patients, was static in 43% and deteriorated in 25%. Amongst the overall cohort, circulatory death occurred in 19% of patients and neurological death occurred in 28% of patients. Mortality did not differ between groups based on the change in SCAI grade (p = 0.2). However, circulatory death was more common in patients with deteriorating SCAI Grade (28%), compared to static (19%) and improving (13%) SCAI (p = 0.010). Multivariable regression modeling showed that SCAI change was independently associated with circulatory death, along with age, lactate, and MIRACLE2 score. CONCLUSION:In patients with OHCA complicated by CS, deterioration in SCAI Grade between cardiac center arrival and ICU admission is independently associated with circulatory death.

Background: Out-of-hospital cardiac arrest (OHCA) remains a global health burden where neurological injury sustained is a key predictor of mortality but there are challenges in early risk stratification. This study aims to derive the Pre-MIRACLE2 score, which excludes pH as a component from the MIRACLE2 score, as a means of stratifying neurological risk in a pre-hospital setting. Methods: To validate the Pre-MIRACLE2 score, we used (i) the EUCAR Registry retrospectively analysed from 1 May 2012 to 31 December 2021, and (ii) the GLOBAL-MIRACLE Registry, a prospective cohort analysed from 1 January 2022 to 31 May 2023. The primary outcome was poor neurological outcome (defined as Cerebral Performance Category 3-5) at hospital discharge. Results: From 1 May 2012 until 31 May 2023, 2149 patients were resuscitated from OHCA with sustained return of spontaneous circulation. After excluding patients who remained non-comatose following return of spontaneous circulation and those with incomplete scores, 1402 patients from EUCAR and 747 from GLOBAL-MIRACLE were included in the final analysis. The primary endpoint occurred in 54.4% of the study cohort. The performance of the Pre-MIRACLE2 score for the primary endpoint was excellent, with an area under the receiver operating curve (AUROC) of 0.85 (95% CI 0.83, 0.87). From the prospective validation cohort (GLOBAL-MIRACLE), the AUROC was 0.85 (95% CI 0.82-0.88) with a calibration slope of 1.11 (95% CI 0.95-1.29). Conclusion: The Pre-MIRACLE2 score has the potential to be an effective and pragmatic risk stratification tool for prediction of poor neurological outcome in a pre-hospital environment or where the pH cannot be measured. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This study did not receive any funding. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The study was performed according to the principles of the Declaration of Helsinki and was approved by local research ethics or governance committees at each centre for both EUCAR (REC Name: South Central - Hampshire A Research Ethics Committee; REC Reference: 18/SC/0008, IRAS ID: 233062) and GLOBAL-MIRACLE (REC Name: Wales REC 5; REC Reference: 21/WA/0361; IRAS ID: 289784) registries. Both studies were affiliated with King's College Hospital NHS Foundation Trust. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.

AIMS:Out-of-hospital cardiac arrest (OHCA) has high mortality, and outcomes remain heterogeneous despite guidelines recommending universal conveyance to cardiac arrest centres. Early pre-hospital risk stratification may identify patients most likely to benefit. The pre-hospital utility of MIRACLE2 is unknown, so we evaluated the feasibility of rapid point-of-care testing to enable calculation of the MIRACLE2 score after return of spontaneous circulation (ROSC). METHODS AND RESULTS:RAPID-MIRACLE was a prospective, multi-centre observational study conducted across London with the London Ambulance Service. Adult patients with suspected cardiac aetiology OHCA achieving sustained ROSC were enrolled. Pre-hospital point-of-care venous blood-gas sampling was performed with results blinded to receiving hospitals. We evaluated ROSC-MIRACLE2 incorporating post-ROSC pH, compared with a modified MIRACLE2 excluding pH (pre-MIRACLE2) and standard MIRACLE2 calculated on hospital admission. The primary outcome was poor neurological outcome at 30 days, defined as cerebral performance category (CPC) 3-5. Among 292 patients, 48% had poor neurological outcome. ROSC-MIRACLE2 demonstrated excellent discrimination [area under the receiver operating characteristic curve (AUC) 0.89 (95% CI 0.85-0.92)], comparable to pre-MIRACLE2 [AUC 0.88 (95% CI 0.84-0.92)], and admission MIRACLE2 [AUC 0.89 (95% CI 0.85-0.92)]. For ROSC-MIRACLE2, a threshold 0-2, the negative predictive value for good outcome was 0.89 (0.82-0.94). At a threshold ≥5, the positive predictive value was 0.88 (0.82-0.94). In a multi-variable regression model, post-ROSC pH was independently associated with poor neurological outcome and less than 3% of patients with a ROSC pH <7.00 had good neurological outcome. CONCLUSION:In this study, pre-hospital application of ROSC-MIRACLE2 enables early neurological risk stratification following resuscitated OHCA. Point-of-care pH improves prognostic precision, but is constrained by feasibility, whilst the simplified pre-MIRACLE2 score is more practical with comparable performance. Integration into OHCA care pathways may improve patient stratification and resource utilization but requires further study.

BACKGROUND:Out-of-hospital cardiac arrest (OHCA) remains a global health burden where neurological injury sustained is a key predictor of mortality but there are challenges in early risk stratification. This study aims to derive the Pre-MIRACLE2 score, which excludes pH as a component from the MIRACLE2 score, as a means of stratifying neurological risk in a pre-hospital setting. METHODS:To validate the Pre-MIRACLE2 score, we used (i) the EUCAR Registry retrospectively analysed from 1 May 2012 to 31 December 2021, and (ii) the GLOBAL-MIRACLE Registry, a prospective cohort analysed from 1 January 2022 to 31 May 2023. The primary outcome was poor neurological outcome (defined as Cerebral Performance Category 3-5) at hospital discharge. RESULTS:From 1 May 2012 until 31 May 2023, 2149 patients were resuscitated from OHCA with sustained return of spontaneous circulation. After excluding patients who remained non-comatose following return of spontaneous circulation and those with incomplete scores, 1402 patients from EUCAR and 747 from GLOBAL-MIRACLE were included in the final analysis. The primary endpoint occurred in 54.4% of the study cohort. The performance of the Pre-MIRACLE2 score for the primary endpoint was excellent, with an area under the receiver operating curve (AUROC) of 0.85 (95% CI 0.83, 0.87). From the prospective validation cohort (GLOBAL-MIRACLE), the AUROC was 0.85 (95% CI 0.82-0.88) with a calibration slope of 1.11 (95% CI 0.95-1.29). CONCLUSION:The Pre-MIRACLE2 score has the potential to be an effective and pragmatic risk stratification tool for prediction of poor neurological outcome in patients with resuscitated OHCA of suspected cardiac aetiology in a pre-hospital environment or where pH cannot be measured.

BACKGROUND:Long-term outcomes following percutaneous coronary intervention (PCI) or coronary artery bypass grafting (CABG) might be changing because of improved techniques and better medical therapy. This final prespecified analysis of the Fractional Flow Reserve (FFR) versus Angiography for Multivessel Evaluation (FAME) 3 trial aimed to reassess their comparative effectiveness at 5 years. METHODS:FAME 3 was a multicentre, randomised trial comparing FFR-guided PCI using current-generation zotarolimus-eluting stents versus CABG in patients with three-vessel coronary artery disease not involving the left main coronary artery. 48 hospitals in Europe, USA and Canada, Australia, and Asia participated in the trial. Patients (aged ≥21 years with no cardiogenic shock, no recent ST segment elevation myocardial infarction, no severe left ventricular dysfunction, and no previous CABG) were randomly assigned to either PCI or CABG using a web-based system. At 1 year, FFR-guided PCI did not meet the prespecified threshold for non-inferiority for the outcome of death, stroke, myocardial infarction, or repeat revascularisation versus CABG. The primary endpoint for this intention-to-treat analysis was the 5-year incidence of the prespecified composite outcome of death, stroke, or myocardial infarction. The trial was registered at ClinicalTrials.gov, NCT02100722, and is completed; this is the final report. FINDINGS:Between Aug 25, 2014 and Nov 28, 2019, 757 of 1500 participants were assigned to PCI and 743 to CABG. 5-year follow-up was achieved in 724 (96%) patients assigned to PCI and 696 (94%) assigned to CABG. At 5 years, there was no significant difference in the composite of death, stroke, or myocardial infarction between the two groups, with 119 (16%) events in the PCI group and 101 (14%) in the CABG group (hazard ratio 1·16 [95% CI 0·89-1·52]; p=0·27). There were no differences in the rates of death (53 [7%] vs 51 [7%]; 0·99 [0·67-1·46]) or stroke (14 [2%] vs 21 [3%], 0·65 [0·33-1·28]), but myocardial infarction was higher in the PCI group than in the CABG group (60 [8%] vs 38 [5%], 1·57 [1·04-2·36]), as was repeat revascularisation (112 [16%] vs 55 [8%], 2·02 [1·46-2·79]). INTERPRETATION:At the 5-year follow-up, there was no significant difference in a composite outcome of death, stroke, or myocardial infarction after FFR-guided PCI versus CABG, although myocardial infarction and repeat revascularisation were higher with PCI. These results provide contemporary evidence to allow improved shared decision making between physicians and patients. FUNDING:Medtronic and Abbott Vascular.

This clinical consensus statement of the European Association of Percutaneous Cardiovascular Interventions was developed in association with the European Society of Cardiology Working Group on Cardiovascular Surgery. It aims to define procedural and contemporary technical requirements that may improve the efficacy and safety of percutaneous coronary intervention (PCI), both in the acute phase and at long-term follow-up, in a high-risk cohort of patients on optimal medical therapy when clinical and anatomical high-risk criteria are present that entail unacceptable surgical risks, precluding the feasibility of coronary artery bypass grafting (CABG). This document pertains to patients with surgical contraindication according to the Heart Team, in whom medical therapy has failed (e.g., residual symptoms), and for whom the Heart Team estimates that revascularisation may have a prognostic benefit (e.g., left main, last remaining vessel, multivessel disease with large areas of ischaemia); however, there is a lack of data regarding the size of this patient population. This document aims to guide interventional cardiologists on how to proceed with PCI in such high-risk patients with reduced left ventricular ejection fraction after the decision of the Heart Team is made that CABG - which overall is the guideline-recommended option for revascularisation in these patients - is not an option and that PCI may be beneficial for the patient. Importantly, when a high-risk PCI is planned, a multidisciplinary decision by interventional cardiologists, cardiac surgeons, anaesthetists and noninvasive physicians with expertise in heart failure management and intensive care should be agreed upon after careful consideration of the possible undesirable consequences of PCI, including futility, similar to the approach for structural interventions.

Aims:Aortic stenosis (AS) is a condition marked by high morbidity and mortality in severe, symptomatic cases without intervention via transcatheter aortic valve implantation (TAVI) or surgical aortic valve replacement (SAVR). Racial and ethnic disparities in access to these treatments have been documented, particularly in North America, where socioeconomic factors such as health insurance confound analyses. This study evaluates disparities in AS management across racial and ethnic groups, accounting for socioeconomic deprivation, using an artificial intelligence (AI) framework. Methods and results:We conducted a retrospective cohort study using a natural language processing pipeline to analyse both structured and unstructured data from > 1 million patients at a London hospital. Key variables included age, sex, self-reported race and ethnicity, AS severity, and socioeconomic status. The primary outcomes were rates of valvular intervention and all-cause mortality. Among 6967 patients with AS, Black patients were younger, more symptomatic, and more comorbid than White patients. Black patients with objective evidence of AS on echocardiography were less likely to receive a clinical diagnosis than White patients. In severe AS, TAVI and SAVR procedures were performed at lower rates among Black patients than among White patients, with a longer time to SAVR. In multivariate analysis of severe AS, controlling for socioeconomic status, Black patients experienced higher mortality (hazard ratio = 1.42, 95% confidence interval = 1.05-1.92, P = 0.02). Conclusion:An AI framework characterizes racial and ethnic disparities in AS management, which persist in a universal healthcare system, highlighting targets for future healthcare interventions.