RESUMEN
Background: Advances in computational methodologies have enabled processing of large datasets originating from imaging studies. However, most imaging biomarkers suffer from a lack of direct links with underlying biology, as they are only observationally correlated with pathophysiology. Purpose(s): To develop and validate a novel AI-assisted image analysis platform, by applying quantitative radiotranscriptomics that quantifies cytokinedriven vascular inflammation from routine CT angiograms (CTA) performed as part of clinical care in COVID-19. Method(s): We used this platform to train the radiotranscriptomic signature C19-RS, derived from the perivascular space around the aorta and the internal mammary artery in routine chest CTAs, to best describe cytokinedriven vascular inflammation, defined using transcriptomic profiles from RNA sequencing data from human arterial biopsies (A). This signature was validated externally in 358 clinically indicated CT pulmonary angiograms from patients with or without COVID-19 from 3 different geographical regions. Result(s): First, 22 patients who had a CTA before the pandemic underwent repeat CTA <6 months post COVID-19 infection (B). Compared with 22 controls (matched for age, gender, and BMI) C19-RS was increased only in the COVID-19 group (C). Next, C19-RS was calculated in a cohort of 331 patients hospitalised during the pandemic, and was higher in COVID-19 positives (adjusted OR=2.97 [95% CI: 1.43-6.27], p=0.004, D). C19-RS had prognostic value for in-hospital mortality in COVID-19, with HR=3.31 ([95% CI: 1.49-7.33], p=0.003) and 2.58 ([95% CI: 1.10-6.05], p=0.028) in two testing cohorts respectively (E, F), adjusted for clinical factors and biochemical biomarkers of inflammation and myocardial injury. The corrected HR for in-hospital mortality was 8.24 [95% CI: 2.16-31.36], p=0.002 for those who received no treatment with dexamethasone, but only 2.27 [95% CI: 0.69-7.55], p=0.18 in those who received dexamethasone subsequently to the C19-RS based image analysis, suggesting that vascular inflammation may have been a therapeutic target of dexamethasone in COVID-19. Finally, C19-RS was strongly associated (r=0.61, p=0.0003) with a whole blood transcriptional module representing dysregulation of coagulation and platelet aggregation pathways. Conclusion(s): We present the first proof of concept study that combines transcriptomics with radiomics to provide a platform for the development of machine learning derived radiotranscriptomics analysis of routine clinical CT scans for the development of non-invasive imaging biomarkers. Application in COVID-19 produced C19-RS, a marker of cytokine-driven inflammation driving systemic activation of coagulation, that predicts inhospital mortality and identifies people who will have better response to anti-inflammatory treatments, allowing targeted therapy. This AI-assisted image analysis platform may have applications across a wide range of vascular diseases, from infections to autoimmune diseases.
RESUMEN
Background: Quality indicators (QIs) have been increasingly used as tools to assess and improve the quality of care for acute myocardial infarction (AMI). However, it is not known if it is feasible to use the 2020 iteration of international AMI QIs using routinely collected data and, if so, whether higher performance is associated with improved outcomes. Objective: To investigate if routine data are available to measure care quality against the 2020 European Society of Cardiology (ESC) Association for Acute Cardiovascular Care (ACVC) QIs for AMI, investigate whether higher performance is associated with reduced mortality, and to report quality of care during the COVID-19 pandemic. Methods: Cohort study of linked data from the AMI and percutaneous coronary intervention (PCI) registries in England and Wales with outcome data from the Civil Registration of Deaths Register between 2017 and 2020 (representing 236 743 patients from 186 hospitals). Baseline ischaemic risk was estimated using the Global Registry of Acute Coronary Events (GRACE) risk score. The likelihood of attainment for each QI based on GRACE risk was quantified using logistic regression and the association with mortality at 30 days, 6 months, 1 year and long-term (maximum 1243 days) was obtained from Cox proportional hazard models. Results: Of 26 QIs, 17 (65.3%) could be directly measured using nationwide registry data and were each inversely associated with risk-adjusted 1-year and long-term mortality. At 30 days, the measured QIs with exception of early invasive coronary angiography for non-ST elevation myocardial infarction, were associated with improved survival, and the QIs that had the greatest magnitude for a reduction in mortality were the prescription of secondary prevention medications at discharge;hazard ratio 0.13 (95% CI 0.12-0.14) for statins, 0.16 (95% CI 0.15-0.18) for adequate P2Y12 inhibition, and 0.18 (95% CI 0.17-0.20) for dual antiplatelet therapy (Figure 1). The magnitude of association between the composite QI (CQI) and survival attenuated over time, with greater long-term survival gains observed for the high GRACE risk compared with low- and intermediate-risk (Figure 2). During the first UK lockdown there was an improvement in the attainment for 62.5% of the measured QIs compared with before the COVID-19 pandemic, with a higher attainment for the CQI (43.8% to 45.2%, odds ratio 1.06, 95% CI 1.02-1.10). Conclusion: Care quality for AMI may be evaluated using routinely collected clinical data from the national registries, whereby higher performance is associated with reduced mortality. Such QIs will have a role in monitoring hospital care as demonstrated for COVID-19.
RESUMEN
Background Evidence suggests that adverse outcomes in COVID-19 may be driven by a cytokine-induced vascular inflammatory response, caused by SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2). Aim We aimed to develop a non-invasive method for quantifying cytokine-driven vascular inflammation in patients with acute COVID-19 infection that could allow risk stratification. Methods We developed a platform for rapid development of novel imaging biomarkers of vascular inflammation, by applying quantitative radiotranscriptomics to images from standard Computed Tomography Angiography (CTA). We used this platform to train a radiotranscriptomic signature (C19-RS) from the perivascular space around the aorta and the internal mammary artery, visualized in routine chest CTAs, to best describe cytokine-driven vascular inflammation, defined using transcriptomic profiles from RNA sequencing data from human arterial biopsies. This signature was tested externally in 435 clinically indicated CT pulmonary angiograms (CTPAs) from patients with or without COVID-19 from 3 different geographical regions. Results COVID-19 patients were characterised by significantly higher C19-RS values (adjusted odds ratio of 2.97 [95%CI: 1.43-6.27], p=0.004), while patients infected with the new B.1.1.7 variant (“UK variant”) were also found to have higher C19-RS values compared to those with the original variant, evidence suggestive of higher degrees of vascular inflammation. C19-RS had prognostic value for in-hospital mortality in COVID-19, with hazard ratios of 3.31 ([95%CI: 1.49-7.33], p=0.003) and 2.58 ([95%CI: 1.10-6.05], p=0.028) in two external testing cohorts respectively, after correction for clinical factors and biochemical biomarkers of inflammation (WBC, CRP) and myocardial injury (troponin). Importantly, the corrected HR for in-hospital mortality was 8.24[95%CI: 2.16- 31.36], P=0.002 for those who received no treatment with dexamethasone, but only 2.27[95%CI: 0.69-7.55], p=0.18 in those who received dexamethasone after the test, suggesting that anti-inflammatory treatment may be modifying the natural history of COVID-19 infection by improving outcomes specifically in those patients with high vascular inflammation. Conclusions Our study introduces a new radiotranscriptomic signature, C19-RS, extracted from routine CTPAs, trained to detect cytokine-driven arterial inflammation, and demonstrates that vascular inflammation determined in this way has prognostic value in patients with COVID-19. The “UK variant” leads to higher vascular inflammation measured in this way, and the risk associated with COVID-19 arteritis is modifiable by dexamethasone.