Recent methodological advances in federated learning for healthcare.

For healthcare datasets, it is often impossible to combine data samples from multiple sites due to ethical, privacy, or logistical concerns. Federated learning allows for the utilization of powerful machine learning algorithms without requiring the pooling of data. Healthcare data have many simultaneous challenges, such as highly siloed data, class imbalance, missing data, distribution shifts, and non-standardized variables, that require new methodologies to address. Federated learning adds significant methodological complexity to conventional centralized machine learning, requiring distributed optimization, communication between nodes, aggregation of models, and redistribution of models. In this systematic review, we consider all papers on Scopus published between January 2015 and February 2023 that describe new federated learning methodologies for addressing challenges with healthcare data. We reviewed 89 papers meeting these criteria. Significant systemic issues were identified throughout the literature, compromising many methodologies reviewed. We give detailed recommendations to help improve methodology development for federated learning in healthcare.

Coronary Atherosclerotic Plaque Activity and Risk of Myocardial Infarction.

BACKGROUND: Total coronary atherosclerotic plaque activity across the entire coronary arterial tree is associated with patient-level clinical outcomes. OBJECTIVES: We aimed to investigate whether vessel-level coronary atherosclerotic plaque activity is associated with vessel-level myocardial infarction. METHODS: In this secondary analysis of an international multicenter study of patients with recent myocardial infarction and multivessel coronary artery disease, we assessed vessel-level coronary atherosclerotic plaque activity using coronary 18F-sodium fluoride positron emission tomography to identify vessel-level myocardial infarction. RESULTS: Increased 18F-sodium fluoride uptake was found in 679 of 2,094 coronary arteries and 414 of 691 patients. Myocardial infarction occurred in 24 (4%) vessels with increased coronary atherosclerotic plaque activity and in 25 (2%) vessels without increased coronary atherosclerotic plaque activity (HR: 2.08; 95% CI: 1.16-3.72; P = 0.013). This association was not demonstrable in those treated with coronary revascularization (HR: 1.02; 95% CI: 0.47-2.25) but was notable in untreated vessels (HR: 3.86; 95% CI: 1.63-9.10; Pinteraction = 0.024). Increased coronary atherosclerotic plaque activity in multiple coronary arteries was associated with heightened patient-level risk of cardiac death or myocardial infarction (HR: 2.43; 95% CI: 1.37-4.30; P = 0.002) as well as first (HR: 2.19; 95% CI: 1.18-4.06; P = 0.013) and total (HR: 2.50; 95% CI: 1.42-4.39; P = 0.002) myocardial infarctions. CONCLUSIONS: In patients with recent myocardial infarction and multivessel coronary artery disease, coronary atherosclerotic plaque activity prognosticates individual coronary arteries and patients at risk for myocardial infarction.

Computed tomography pericoronary adipose tissue density predicts coronary allograft vasculopathy and adverse clinical outcomes after cardiac transplantation.

AIMS: To assess pericoronary adipose tissue (PCAT) density on coronary computed tomography angiography (CCTA) as a marker of inflammatory disease activity in coronary allograft vasculopathy (CAV). METHODS AND RESULTS: PCAT density, lesion volumes, and total vessel volume-to-myocardial mass ratio (V/M) were retrospectively measured in 126 CCTAs from 94 heart transplant patients [mean age 49 (SD 14.5) years, 40% female] who underwent imaging between 2010 and 2021; age- and sex-matched controls; and patients with atherosclerosis. PCAT density was higher in transplant patients with CAV [n = 40; -73.0 HU (SD 9.3)] than without CAV [n = 86; -77.9 HU (SD 8.2)], and controls [n = 12; -86.2 HU (SD 5.4)], P < 0.01 for both. Unlike patients with atherosclerotic coronary artery disease (n = 32), CAV lesions were predominantly non-calcified and comprised of mostly fibrous or fibrofatty tissue. V/M was lower in patients with CAV than without [32.4 mm3/g (SD 9.7) vs. 41.4 mm3/g (SD 12.3), P < 0.0001]. PCAT density and V/M improved the ability to predict CAV from area under the receiver operating characteristic curve (AUC) 0.75-0.85 when added to donor age and donor hypertension status (P < 0.0001). PCAT density above -66 HU was associated with a greater incidence of all-cause mortality {odds ratio [OR] 18.0 [95% confidence interval (CI) 3.25-99.6], P < 0.01} and the composite endpoint of death, CAV progression, acute rejection, and coronary revascularization [OR 7.47 (95% CI 1.8-31.6), P = 0.01] over 5.3 (SD 2.1) years. CONCLUSION: Heart transplant patients with CAV have higher PCAT density and lower V/M than those without. Increased PCAT density is associated with adverse clinical outcomes. These CCTA metrics could be useful for the diagnosis and monitoring of CAV severity.

Polygenic risk scores in atrial fibrillation: Associations and clinical utility in disease prediction.

Atrial fibrillation (AF) is a common heart arrhythmia and a major cause of cardioembolic stroke. Therefore, accurate prediction is desirable to allow high-risk individuals to be identified early and their risk lowered before complications arise. Polygenic risk scores (PRSs) have become a popular method of quantifying aggregated genetic risk from common variants, but their clinical value in AF remains uncertain. This literature review summarizes the associations between PRS and AF risk and discusses the evidence for the clinical utility of PRS for AF prediction. Stroke risk in patients with AF is also considered. Despite consistent associations between PRS and AF risk, the performance of PRS as a stand-alone tool for AF prediction was poor. However, addition of PRS to the existing AF prediction models commonly improved the predictive performance above that of the clinical models alone, including in cohorts with comorbid cardiovascular disease. Associations between PRS and cardioembolic stroke risk in patients with AF have also been reported, but improvements in stroke prediction models from PRS have been minimal. PRS are likely to add value to the existing clinical AF prediction models; however, standardization of PRS across studies and populations will likely be required before they can be meaningfully adopted into routine clinical practice.

Use of coronarycomputed tomography for cardiovascular risk assessment in immune-mediated inflammatory diseases.

Immune-mediated inflammatory diseases (IMIDs) are recognised risk factors for accelerated atherosclerotic cardiovascular disease (CVD), particularly in younger individuals and women who lack traditional CVD risk factors. Reflective of the critical role that inflammation plays in the formation, progression and rupture of atherosclerotic plaques, research into immune mechanisms of CVD has led to the identification of a range of therapeutic targets that are the subject of ongoing clinical trials. Several key inflammatory pathways implicated in the pathogenesis of atherosclerosis are targeted in people with IMIDs. However, cardiovascular risk continues to be systematically underestimated by conventional risk assessment tools in the IMID population, resulting in considerable excess CVD burden and mortality. Hence, there is a pressing need to improve methods for CVD risk-stratification among patients with IMIDs, to better guide the use of statins and other prognostic interventions. CT coronary angiography (CTCA) is the current first-line investigation for diagnosing and assessing the severity of coronary atherosclerosis in many individuals with suspected angina. Whether CTCA is also useful in the general population for reclassifying asymptomatic individuals and improving long-term prognosis remains unknown. However, in the context of IMIDs, it is conceivable that the information provided by CTCA, including state-of-the-art assessments of coronary plaque, could be an important clinical adjunct in this high-risk patient population. This narrative review discusses the current literature about the use of coronary CT for CVD risk-stratification in three of the most common IMIDs including rheumatoid arthritis, psoriasis and systemic lupus erythematosus.

Common methodological pitfalls in ICI pneumonitis risk prediction studies.

Background: Pneumonitis is one of the most common adverse events induced by the use of immune checkpoint inhibitors (ICI), accounting for a 20% of all ICI-associated deaths. Despite numerous efforts to identify risk factors and develop predictive models, there is no clinically deployed risk prediction model for patient risk stratification or for guiding subsequent monitoring. We believe this is due to systemic suboptimal approaches in study designs and methodologies in the literature. The nature and prevalence of different methodological approaches has not been thoroughly examined in prior systematic reviews. Methods: The PubMed, medRxiv and bioRxiv databases were used to identify studies that aimed at risk factor discovery and/or risk prediction model development for ICI-induced pneumonitis (ICI pneumonitis). Studies were then analysed to identify common methodological pitfalls and their contribution to the risk of bias, assessed using the QUIPS and PROBAST tools. Results: There were 51 manuscripts eligible for the review, with Japan-based studies over-represented, being nearly half (24/51) of all papers considered. Only 2/51 studies had a low risk of bias overall. Common bias-inducing practices included unclear diagnostic method or potential misdiagnosis, lack of multiple testing correction, the use of univariate analysis for selecting features for multivariable analysis, discretization of continuous variables, and inappropriate handling of missing values. Results from the risk model development studies were also likely to have been overoptimistic due to lack of holdout sets. Conclusions: Studies with low risk of bias in their methodology are lacking in the existing literature. High-quality risk factor identification and risk model development studies are urgently required by the community to give the best chance of them progressing into a clinically deployable risk prediction model. Recommendations and alternative approaches for reducing the risk of bias were also discussed to guide future studies.

The impact of imputation quality on machine learning classifiers for datasets with missing values.

BACKGROUND: Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missing values are typically imputed using established methods, followed by classification of the now complete samples. The focus of the machine learning researcher is to optimise the classifier's performance. METHODS: We utilise three simulated and three real-world clinical datasets with different feature types and missingness patterns. Initially, we evaluate how the downstream classifier performance depends on the choice of classifier and imputation methods. We employ ANOVA to quantitatively evaluate how the choice of missingness rate, imputation method, and classifier method influences the performance. Additionally, we compare commonly used methods for assessing imputation quality and introduce a class of discrepancy scores based on the sliced Wasserstein distance. We also assess the stability of the imputations and the interpretability of model built on the imputed data. RESULTS: The performance of the classifier is most affected by the percentage of missingness in the test data, with a considerable performance decline observed as the test missingness rate increases. We also show that the commonly used measures for assessing imputation quality tend to lead to imputed data which poorly matches the underlying data distribution, whereas our new class of discrepancy scores performs much better on this measure. Furthermore, we show that the interpretability of classifier models trained using poorly imputed data is compromised. CONCLUSIONS: It is imperative to consider the quality of the imputation when performing downstream classification as the effects on the classifier can be considerable.

Many artificial intelligence (AI) methods aim to classify samples of data into groups, e.g., patients with disease vs. those without. This often requires datasets to be complete, i.e., that all data has been collected for all samples. However, in clinical practice this is often not the case and some data can be missing. One solution is to 'complete' the dataset using a technique called imputation to replace those missing values. However, assessing how well the imputation method performs is challenging. In this work, we demonstrate why people should care about imputation, develop a new method for assessing imputation quality, and demonstrate that if we build AI models on poorly imputed data, the model can give different results to those we would hope for. Our findings may improve the utility and quality of AI models in the clinic.

Imaging Carotid Plaque Inflammation Using Positron Emission Tomography: Emerging Role in Clinical Stroke Care, Research Applications, and Future Directions.

Atherosclerosis is a chronic systemic inflammatory condition of the vasculature and a leading cause of stroke. Luminal stenosis severity is an important factor in determining vascular risk. Conventional imaging modalities, such as angiography or duplex ultrasonography, are used to quantify stenosis severity and inform clinical care but provide limited information on plaque biology. Inflammatory processes are central to atherosclerotic plaque progression and destabilization. 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is a validated technique for quantifying plaque inflammation. In this review, we discuss the evolution of FDG-PET as an imaging modality to quantify plaque vulnerability, challenges in standardization of image acquisition and analysis, its potential application to routine clinical care after stroke, and the possible role it will play in future drug discovery.

A pipeline to further enhance quality, integrity and reusability of the NCCID clinical data.

The National COVID-19 Chest Imaging Database (NCCID) is a centralized UK database of thoracic imaging and corresponding clinical data. It is made available by the National Health Service Artificial Intelligence (NHS AI) Lab to support the development of machine learning tools focused on Coronavirus Disease 2019 (COVID-19). A bespoke cleaning pipeline for NCCID, developed by the NHSx, was introduced in 2021. We present an extension to the original cleaning pipeline for the clinical data of the database. It has been adjusted to correct additional systematic inconsistencies in the raw data such as patient sex, oxygen levels and date values. The most important changes will be discussed in this paper, whilst the code and further explanations are made publicly available on GitLab. The suggested cleaning will allow global users to work with more consistent data for the development of machine learning tools without being an expert. In addition, it highlights some of the challenges when working with clinical multi-center data and includes recommendations for similar future initiatives.

Coronary Atherosclerotic Plaque Activity and Future Coronary Events.

Importance: Recurrent coronary events in patients with recent myocardial infarction remain a major clinical problem. Noninvasive measures of coronary atherosclerotic disease activity have the potential to identify individuals at greatest risk. Objective: To assess whether coronary atherosclerotic plaque activity as assessed by noninvasive imaging is associated with recurrent coronary events in patients with myocardial infarction. Design, Setting, and Participants: This prospective, longitudinal, international multicenter cohort study recruited participants aged 50 years or older with multivessel coronary artery disease and recent (within 21 days) myocardial infarction between September 2015 and February 2020, with a minimum 2 years' follow-up. Intervention: Coronary 18F-sodium fluoride positron emission tomography and coronary computed tomography angiography. Main Outcomes and Measures: Total coronary atherosclerotic plaque activity was assessed by 18F-sodium fluoride uptake. The primary end point was cardiac death or nonfatal myocardial infarction but was expanded during study conduct to include unscheduled coronary revascularization due to lower than anticipated primary event rates. Results: Among 2684 patients screened, 995 were eligible, 712 attended for imaging, and 704 completed an interpretable scan and comprised the study population. The mean (SD) age of participants was 63.8 (8.2) years, and most were male (601 [85%]). Total coronary atherosclerotic plaque activity was identified in 421 participants (60%). After a median follow-up of 4 years (IQR, 3-5 years), 141 participants (20%) experienced the primary end point: 9 had cardiac death, 49 had nonfatal myocardial infarction, and 83 had unscheduled coronary revascularizations. Increased coronary plaque activity was not associated with the primary end point (hazard ratio [HR], 1.25; 95% CI, 0.89-1.76; P = .20) or unscheduled revascularization (HR, 0.98; 95% CI, 0.64-1.49; P = .91) but was associated with the secondary end point of cardiac death or nonfatal myocardial infarction (47 of 421 patients with high plaque activity [11.2%] vs 19 of 283 with low plaque activity [6.7%]; HR, 1.82; 95% CI, 1.07-3.10; P = .03) and all-cause mortality (30 of 421 patients with high plaque activity [7.1%] vs 9 of 283 with low plaque activity [3.2%]; HR, 2.43; 95% CI, 1.15-5.12; P = .02). After adjustment for differences in baseline clinical characteristics, coronary angiography findings, and Global Registry of Acute Coronary Events score, high coronary plaque activity was associated with cardiac death or nonfatal myocardial infarction (HR, 1.76; 95% CI, 1.00-3.10; P = .05) but not with all-cause mortality (HR, 2.01; 95% CI, 0.90-4.49; P = .09). Conclusions and Relevance: In this cohort study of patients with recent myocardial infarction, coronary atherosclerotic plaque activity was not associated with the primary composite end point. The findings suggest that risk of cardiovascular death or myocardial infarction in patients with elevated plaque activity warrants further research to explore its incremental prognostic implications.

Characteristics of conventional high-risk coronary plaques and a novel CT defined thin-cap fibroatheroma in patients undergoing CCTA with stable chest pain.

BACKGROUND: Coronary computed tomography angiography (CCTA) can identify high-risk coronary plaque types. However, the inter-observer variability for high-risk plaque features, including low attenuation plaque (LAP), positive remodelling (PR), and the Napkin-Ring sign (NRS), may reduce their utility, especially amongst less experienced readers. METHODOLOGY: In a prospective study, we compared the prevalence, location and inter-observer variability of both conventional CT-defined high-risk plaques with a novel index based on quantifying the ratio of necrotic core to fibrous plaque using individualised X-ray attenuation cut-offs (the CT-defined thin-cap fibroatheroma - CT-TCFA) in 100 patients followed-up for 7 years. RESULTS: In total, 346 plaques were identified in all patients. Seventy-two (21%) of all plaques were classified by conventional CT parameters as high-risk (either NRS or PR and LAP combined), and 43 (12%) of plaques were considered high-risk using the novel CT-TCFA definition of (Necrotic Core/fibrous plaque ratio of >0.9). The majority (80%) of the high-risk plaques (LAP&PR, NRS and CT-TCFA) were located in the proximal and mid-LAD and RCA. The kappa co-efficient of inter-observer variability (k) for NRS was 0.4 and for PR and LAP combined 0.4. While the kappa co-efficient of inter-observer variability (k) for the new CT-TCFA definition was 0.7. During follow-up, patients with either conventional high-risk plaques or CT-TCFAs were significantly more likely to have MACE (Major adverse cardiovascular events) compared to patients without coronary plaques (p value 0.03 & 0.03, respectively). CONCLUSION: The novel CT-TCFA is associated with MACE and has improved inter-observer variability compared with current CT-defined high-risk plaques.

Moving from non-emergency bleeps and long-range pagers to a hospital-wide, EHR-integrated secure messaging system: an implementer report.

INTRODUCTION: Obsolete bleep/long-range pager equipment remains firmly embedded in the National Health Service (NHS). OBJECTIVE: To introduce a secure, chart-integrated messaging system (Epic Secure Chat) in a large NHS tertiary referral centre to replace non-emergency bleeps/long-range pagers. METHODS: The system was socialised in the months before go-live. Operational readiness was overseen by an implementation group with stakeholder engagement. Cutover was accompanied by a week of Secure Chat and bleeps running in parallel. RESULTS: Engagement due to socialisation was high with usage stabilising approximately 3 months after go-live. Contact centre internal call activity fell significantly after go-live. No significant patient safety concerns were reported. DISCUSSION: Uptake was excellent with substantial utilisation well before cutover indirectly supporting high levels of engagement. The majority of those who previously carried bleeps were content to use personal devices for messaging because of user convenience after reassurance about privacy. CONCLUSION: An integrated secure messaging system can replace non-emergency bleeps with beneficial impact on service.

National Trends in Coronary Artery Disease Imaging: Associations With Health Care Outcomes and Costs.

BACKGROUND: In 2016, the National Institute for Health and Care Excellence Clinical Guideline Number 95 ("Chest pain of recent onset") (CG95) recommended coronary computed tomography angiography (CCTA) as the first-line test for possible angina. OBJECTIVES: The purpose of this study was to determine the impact of temporal trends in imaging use on outcomes for coronary artery disease (CAD) following the CG95 recommendations. METHODS: Investigations from 2012 to 2018 were extracted from a national database and linked to hospital admission and mortality registries. Growth rates were adjusted for population size, with image modality use, cardiovascular hospital admissions, and mortality compared using Kendall's rank correlation. The impact of CG95 was assessed using an interrupted time-series analysis. RESULTS: A total of 1,909,314 investigations for CAD were performed, with an annualized per capita growth of 4.8%. Costs were £0.35 million/100,000 population/year with an increase of 2.8%/year mirroring inflation (2.5%/year). CG95 was associated with a rise in CCTA (exp[ß]: 1.10; 95% CI: 1.03-1.18), no change in myocardial perfusion imaging, and a potential modest fall (exp[ß]: 0.997; 95% CI: 0.993-1.00]) in invasive coronary angiography. There was an apparent trend between computed tomography angiography growth and invasive catheter angiography reduction across regions (Kendall Tau: -0.19; P = 0.08). CCTA growth was associated with a reduction in cardiovascular mortality (Kendall Tau: -0.21; P = 0.045), and ischemic heart disease deaths (Kendall Tau: -0.22; P = 0.042), with an apparent trend with reduced all-cause mortality (Kendall Tau: -0.19; P = 0.07). CONCLUSIONS: Imaging investigations for CAD are increasing. Greater regional increases in CCTA were associated with fewer hospitalizations for myocardial infarction and a more rapid decline in CAD mortality.

Somatostatin Receptor PET/MR Imaging of Inflammation in Patients With Large Vessel Vasculitis and Atherosclerosis.

BACKGROUND: Assessing inflammatory disease activity in large vessel vasculitis (LVV) can be challenging by conventional measures. OBJECTIVES: We aimed to investigate somatostatin receptor 2 (SST2) as a novel inflammation-specific molecular imaging target in LVV. METHODS: In a prospective, observational cohort study, in vivo arterial SST2 expression was assessed by positron emission tomography/magnetic resonance imaging (PET/MRI) using 68Ga-DOTATATE and 18F-FET-ßAG-TOCA. Ex vivo mapping of the imaging target was performed using immunofluorescence microscopy; imaging mass cytometry; and bulk, single-cell, and single-nucleus RNA sequencing. RESULTS: Sixty-one participants (LVV: n = 27; recent atherosclerotic myocardial infarction of ≤2 weeks: n = 25; control subjects with an oncologic indication for imaging: n = 9) were included. Index vessel SST2 maximum tissue-to-blood ratio was 61.8% (P < 0.0001) higher in active/grumbling LVV than inactive LVV and 34.6% (P = 0.0002) higher than myocardial infarction, with good diagnostic accuracy (area under the curve: ≥0.86; P < 0.001 for both). Arterial SST2 signal was not elevated in any of the control subjects. SST2 PET/MRI was generally consistent with 18F-fluorodeoxyglucose PET/computed tomography imaging in LVV patients with contemporaneous clinical scans but with very low background signal in the brain and heart, allowing for unimpeded assessment of nearby coronary, myocardial, and intracranial artery involvement. Clinically effective treatment for LVV was associated with a 0.49 ± 0.24 (standard error of the mean [SEM]) (P = 0.04; 22.3%) reduction in the SST2 maximum tissue-to-blood ratio after 9.3 ± 3.2 months. SST2 expression was localized to macrophages, pericytes, and perivascular adipocytes in vasculitis specimens, with specific receptor binding confirmed by autoradiography. SSTR2-expressing macrophages coexpressed proinflammatory markers. CONCLUSIONS: SST2 PET/MRI holds major promise for diagnosis and therapeutic monitoring in LVV. (PET Imaging of Giant Cell and Takayasu Arteritis [PITA], NCT04071691; Residual Inflammation and Plaque Progression Long-Term Evaluation [RIPPLE], NCT04073810).

Low-dose interleukin 2 for the reduction of vascular inflammation in acute coronary syndromes (IVORY): protocol and study rationale for a randomised, double-blind, placebo-controlled, phase II clinical trial.

INTRODUCTION: Inflammation plays a critical role in the pathogenesis of atherosclerosis, the leading cause of ischaemic heart disease (IHD). Studies in preclinical models have demonstrated that an increase in regulatory T cells (Tregs), which have a potent immune modulatory action, led to a regression of atherosclerosis. The Low-dose InterLeukin 2 (IL-2) in patients with stable ischaemic heart disease and Acute Coronary Syndromes (LILACS) study, established the safety of low-dose IL-2 and its biological efficacy in IHD. The IVORY trial is designed to assess the effects of low-dose IL-2 on vascular inflammation in patients with acute coronary syndromes (ACS). METHODS AND ANALYSIS: In this study, we hypothesise that low-dose IL-2 will reduce vascular inflammation in patients presenting with ACS. This is a double-blind, randomised, placebo-controlled, phase II clinical trial. Patients will be recruited across two centres, a district general hospital and a tertiary cardiac centre in Cambridge, UK. Sixty patients with ACS (unstable angina, non-ST elevation myocardial infarction or ST elevation myocardial infarction) with high-sensitivity C reactive protein (hsCRP) levels >2 mg/L will be randomised to receive either 1.5×106 IU of low-dose IL-2 or placebo (1:1). Dosing will commence within 14 days of admission. Dosing will comprise of an induction and a maintenance phase. 2-Deoxy-2-[fluorine-18] fluoro-D-glucose (18F-FDG) positron emission tomography/CT (PET/CT) scans will be performed before and after dosing. The primary endpoint is the change in mean maximum target to background ratios (TBRmax) in the index vessel between baseline and follow-up scans. Changes in circulating T-cell subsets will be measured as secondary endpoints of the study. The safety and tolerability of extended dosing with low-dose IL-2 in patients with ACS will be evaluated throughout the study. ETHICS AND DISSEMINATION: The Health Research Authority and Health and Care Research Wales, UK (19/YH/0171), approved the study. Written informed consent is required to participate in the trial. The results will be reported through peer-reviewed journals and conference presentations. TRIAL REGISTRATION NUMBER: NCT04241601.

Aortic stenosis post-COVID-19: a mathematical model on waiting lists and mortality.

OBJECTIVES: To provide estimates for how different treatment pathways for the management of severe aortic stenosis (AS) may affect National Health Service (NHS) England waiting list duration and associated mortality. DESIGN: We constructed a mathematical model of the excess waiting list and found the closed-form analytic solution to that model. From published data, we calculated estimates for how the strategies listed under Interventions may affect the time to clear the backlog of patients waiting for treatment and the associated waiting list mortality. SETTING: The NHS in England. PARTICIPANTS: Estimated patients with AS in England. INTERVENTIONS: (1) Increasing the capacity for the treatment of severe AS, (2) converting proportions of cases from surgery to transcatheter aortic valve implantation and (3) a combination of these two. RESULTS: In a capacitated system, clearing the backlog by returning to pre-COVID-19 capacity is not possible. A conversion rate of 50% would clear the backlog within 666 (533-848) days with 1419 (597-2189) deaths while waiting during this time. A 20% capacity increase would require 535 (434-666) days, with an associated mortality of 1172 (466-1859). A combination of converting 40% cases and increasing capacity by 20% would clear the backlog within a year (343 (281-410) days) with 784 (292-1324) deaths while awaiting treatment. CONCLUSION: A strategy change to the management of severe AS is required to reduce the NHS backlog and waiting list deaths during the post-COVID-19 'recovery' period. However, plausible adaptations will still incur a substantial wait to treatment and many hundreds dying while waiting.