DCCAT: Dual-Coordinate Cross-Attention Transformer for thrombus segmentation on coronary OCT.

Acute coronary syndromes (ACS) are one of the leading causes of mortality worldwide, with atherosclerotic plaque rupture and subsequent thrombus formation as the main underlying substrate. Thrombus burden evaluation is important for tailoring treatment therapy and predicting prognosis. Coronary optical coherence tomography (OCT) enables in-vivo visualization of thrombus that cannot otherwise be achieved by other image modalities. However, automatic quantification of thrombus on OCT has not been implemented. The main challenges are due to the variation in location, size and irregularities of thrombus in addition to the small data set. In this paper, we propose a novel dual-coordinate cross-attention transformer network, termed DCCAT, to overcome the above challenges and achieve the first automatic segmentation of thrombus on OCT. Imaging features from both Cartesian and polar coordinates are encoded and fused based on long-range correspondence via multi-head cross-attention mechanism. The dual-coordinate cross-attention block is hierarchically stacked amid convolutional layers at multiple levels, allowing comprehensive feature enhancement. The model was developed based on 5,649 OCT frames from 339 patients and tested using independent external OCT data from 548 frames of 52 patients. DCCAT achieved Dice similarity score (DSC) of 0.706 in segmenting thrombus, which is significantly higher than the CNN-based (0.656) and Transformer-based (0.584) models. We prove that the additional input of polar image not only leverages discriminative features from another coordinate but also improves model robustness for geometrical transformation.Experiment results show that DCCAT achieves competitive performance with only 10% of the total data, highlighting its data efficiency. The proposed dual-coordinate cross-attention design can be easily integrated into other developed Transformer models to boost performance.

Cardiovascular Magnetic Resonance Before Invasive Coronary Angiography in Suspected Non-ST-Segment Elevation Myocardial Infarction.

BACKGROUND: In suspected non-ST-segment elevation myocardial infarction (NSTEMI), this presumed diagnosis may not hold true in all cases, particularly in patients with nonobstructive coronary arteries (NOCA). Additionally, in multivessel coronary artery disease, the presumed infarct-related artery may be incorrect. OBJECTIVES: This study sought to assess the diagnostic utility of cardiac magnetic resonance (CMR) before invasive coronary angiogram (ICA) in suspected NSTEMI. METHODS: A total of 100 consecutive stable patients with suspected acute NSTEMI (70% male, age 62 ± 11 years) prospectively underwent CMR pre-ICA to assess cardiac function (cine), edema (T2-weighted imaging, T1 mapping), and necrosis/scar (late gadolinium enhancement). CMR images were interpreted blinded to ICA findings. The clinical care and ICA teams were blinded to CMR findings until post-ICA. RESULTS: Early CMR (median 33 hours postadmission and 4 hours pre-ICA) confirmed only 52% (52 of 100) of patients had subendocardial infarction, 15% transmural infarction, 18% nonischemic pathologies (myocarditis, Takotsubo and other forms of cardiomyopathies), and 11% normal CMR; 4% were nondiagnostic. Subanalyses according to ICA findings showed that, in patients with obstructive coronary artery disease (73 of 100), CMR confirmed only 84% (61 of 73) had MI, 10% (7 of 73) nonischemic pathologies, and 5% (4 of 73) normal. In patients with NOCA (27 of 100), CMR found MI in only 22% (6 of 27 true MI with NOCA), and reclassified the presumed diagnosis of NSTEMI in 67% (18 of 27: 11 nonischemic pathologies, 7 normal). In patients with CMR-MI and obstructive coronary artery disease (61 of 100), CMR identified a different infarct-related artery in 11% (7 of 61). CONCLUSIONS: In patients presenting with suspected NSTEMI, a CMR-first strategy identified MI in 67%, nonischemic pathologies in 18%, and normal findings in 11%. Accordingly, CMR has the potential to affect at least 50% of all patients by reclassifying their diagnosis or altering their potential management.

Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: the ORFAN multicentre, longitudinal cohort study.

BACKGROUND: Coronary computed tomography angiography (CCTA) is the first line investigation for chest pain, and it is used to guide revascularisation. However, the widespread adoption of CCTA has revealed a large group of individuals without obstructive coronary artery disease (CAD), with unclear prognosis and management. Measurement of coronary inflammation from CCTA using the perivascular fat attenuation index (FAI) Score could enable cardiovascular risk prediction and guide the management of individuals without obstructive CAD. The Oxford Risk Factors And Non-invasive imaging (ORFAN) study aimed to evaluate the risk profile and event rates among patients undergoing CCTA as part of routine clinical care in the UK National Health Service (NHS); to test the hypothesis that coronary arterial inflammation drives cardiac mortality or major adverse cardiac events (MACE) in patients with or without CAD; and to externally validate the performance of the previously trained artificial intelligence (AI)-Risk prognostic algorithm and the related AI-Risk classification system in a UK population. METHODS: This multicentre, longitudinal cohort study included 40 091 consecutive patients undergoing clinically indicated CCTA in eight UK hospitals, who were followed up for MACE (ie, myocardial infarction, new onset heart failure, or cardiac death) for a median of 2·7 years (IQR 1·4-5·3). The prognostic value of FAI Score in the presence and absence of obstructive CAD was evaluated in 3393 consecutive patients from the two hospitals with the longest follow-up (7·7 years [6·4-9·1]). An AI-enhanced cardiac risk prediction algorithm, which integrates FAI Score, coronary plaque metrics, and clinical risk factors, was then evaluated in this population. FINDINGS: In the 2·7 year median follow-up period, patients without obstructive CAD (32 533 [81·1%] of 40 091) accounted for 2857 (66·3%) of the 4307 total MACE and 1118 (63·7%) of the 1754 total cardiac deaths in the whole of Cohort A. Increased FAI Score in all the three coronary arteries had an additive impact on the risk for cardiac mortality (hazard ratio [HR] 29·8 [95% CI 13·9-63·9], p<0·001) or MACE (12·6 [8·5-18·6], p<0·001) comparing three vessels with an FAI Score in the top versus bottom quartile for each artery. FAI Score in any coronary artery predicted cardiac mortality and MACE independently from cardiovascular risk factors and the presence or extent of CAD. The AI-Risk classification was positively associated with cardiac mortality (6·75 [5·17-8·82], p<0·001, for very high risk vs low or medium risk) and MACE (4·68 [3·93-5·57], p<0·001 for very high risk vs low or medium risk). Finally, the AI-Risk model was well calibrated against true events. INTERPRETATION: The FAI Score captures inflammatory risk beyond the current clinical risk stratification and CCTA interpretation, particularly among patients without obstructive CAD. The AI-Risk integrates this information in a prognostic algorithm, which could be used as an alternative to traditional risk factor-based risk calculators. FUNDING: British Heart Foundation, NHS-AI award, Innovate UK, National Institute for Health and Care Research, and the Oxford Biomedical Research Centre.

Treatment and Care of Patients with ST-Segment Elevation Myocardial Infarction-What Challenges Remain after Three Decades of Primary Percutaneous Coronary Intervention?

Primary percutaneous coronary intervention (pPCI) has revolutionized the prognosis of ST-segment elevation myocardial infarction (STEMI) and is the gold standard treatment. As a result of its success, the number of pPCI centres has expanded worldwide. Despite decades of advancements, clinical outcomes in STEMI patients have plateaued. Out-of-hospital cardiac arrest and cardiogenic shock remain a major cause of high in-hospital mortality, whilst the growing burden of heart failure in long-term STEMI survivors presents a growing problem. Many elements aiming to optimize STEMI treatment are still subject to debate or lack sufficient evidence. This review provides an overview of the most contentious current issues in pPCI in STEMI patients, with an emphasis on unresolved questions and persistent challenges.

Comparison of troponin and natriuretic peptides in Takotsubo syndrome and acute coronary syndrome: a meta-analysis.

OBJECTIVE: Takotsubo syndrome (TTS) is an acute heart failure syndrome which resembles acute coronary syndrome (ACS) at presentation. Differentiation requires coronary angiography, but where this does not occur immediately, cardiac biomarkers may provide additional utility. We performed a meta-analysis to compare troponin and natriuretic peptides (NPs) in TTS and ACS to determine if differences in biomarker profile can aid diagnosis. METHODS: We searched five literature databases for studies reporting NPs (Brain NP (BNP)/NT-pro-BNP) or troponin I/T in TTS and ACS, identifying 28 studies for troponin/NPs (5618 and 1145 patients, respectively). RESULTS: Troponin was significantly lower in TTS than ACS (standardised mean difference (SMD) -0.86; 95% CI, -1.08 to -0.64; p<0.00001), with an absolute difference of 75 times the upper limit of normal (×ULN) higher in ACS than TTS. Conversely, NPs were significantly higher in TTS (SMD 0.62; 95% CI, 0.44 to 0.80; p<0.00001) and 5.8×ULN greater absolutely. Area under the curve (AUC) for troponin in ACS versus TTS was 0.82 (95% CI, 0.70 to 0.93), and 0.92 (95% CI, 0.80 to 1.00) for ST-segment elevation myocardial infarction versus TTS. For NPs, AUC was 0.69 (95% CI, 0.48 to 0.89). Combination of troponin and NPs with logistic regression did not improve AUC. Recursive Partitioning and Regression Tree analysis calculated a troponin threshold ≥26×ULN that identified 95% cases as ACS where and specificity for ACS were 85.71% and 53.57%, respectively, with 94.32% positive predictive value and 29.40% negative predictive value. CONCLUSIONS: Troponin is lower and NPs higher in TTS versus ACS. Troponin had greater power than NPs at discriminating TTS and ACS, and with troponin ≥26×ULN patients are far more likely to have ACS.

Comparison of bolus versus continuous thermodilution derived indices of microvascular dysfunction in revascularized coronary syndromes.

Background: The assessment of coronary microvascular dysfunction (CMD) using invasive methods is a field of growing interest, however the preferred method remains debated. Bolus and continuous thermodilution are commonly used methods, but weak agreement has been observed in patients with angina with non-obstructive coronary arteries (ANOCA). This study examined their agreement in revascularized acute coronary syndromes (ACS) and chronic coronary syndromes (CCS) patients. Objective: To compare bolus thermodilution and continuous thermodilution indices of CMD in revascularized ACS and CCS patients and assess their diagnostic agreement at pre-defined cut-off points. Methods: Patients from two centers underwent paired bolus and continuous thermodilution assessments after revascularization. CMD indices were compared between the two methods and their agreements at binary cut-off points were assessed. Results: Ninety-six patients and 116 vessels were included. The mean age was 64 ± 11 years, and 20 (21 %) were female. Overall, weak correlations were observed between the Index of Microcirculatory Resistance (IMR) and continuous thermodilution microvascular resistance (Rµ) (rho = 0.30p = 0.001). The median coronary flow reserve (CFR) from continuous thermodilution (CFRcont) and bolus thermodilution (CFRbolus) were 2.19 (1.76-2.67) and 2.55 (1.50-3.58), respectively (p < 0.001). Weak correlation and agreement were observed between CFRcont and CFRbolus (rho = 0.37, p < 0.001, ICC 0.228 [0.055-0.389]). When assessed at CFR cut-off values of 2.0 and 2.5, the methods disagreed in 41 (35 %) and 45 (39 %) of cases, respectively. Conclusions: There is a significant difference and weak agreement between bolus and continuous thermodilution-derived indices, which must be considered when diagnosing CMD in ACS and CCS patients.

Angiography-Derived Index of Microcirculatory Resistance to Define the Risk of Early Discharge in STEMI.

BACKGROUND: Patients with ST-segment-elevation myocardial infarction but no coronary microvascular injury are at low risk of early cardiovascular complications (ECC). We aim to assess whether nonhyperemic angiography-derived index of microcirculatory resistance (NH-IMRangio) could be a user-friendly tool to identify patients at low risk of ECC, potentially candidates for expedited care pathway and early hospital discharge. METHODS: Retrospective analysis of 2 independent, international, prospective, observational cohorts included 568 patients with ST-segment-elevation myocardial infarction. NH-IMRangio was calculated based on standard coronary angiographic views with 3-dimensional-modeling and computational analysis of the coronary flow. RESULTS: Overall, ECC (a composite of cardiovascular death, cardiogenic shock, acute heart failure, life-threatening arrhythmias, resuscitated cardiac arrest, left ventricular thrombus, post-ST-segment-elevation myocardial infarction mechanical complications, and rehospitalization for acute heart failure or acute myocardial infarction at 30 days follow-up), occurred in 54 (9.3%) patients. NH-IMRangio was significantly correlated with pressure/thermodilution-based index of microcirculatory resistance (r=0.607; P<0.0001) and demonstrated good accuracy in predicting ECC (area under the curve, 0.766 [95% CI, 0.706-0.827]; P<0.0001). Importantly, ECC occurred more frequently in patients with NH-IMRangio ≥40 units (18.1% versus 1.4%; P<0.0001). At multivariable analysis, NH-IMRangio provided incremental prognostic value to conventional clinical, angiographic, and echocardiographic features (adjusted-odds ratio, 14.861 [95% CI, 5.177-42.661]; P<0.0001). NH-IMRangio<40 units showed an excellent negative predictive value (98.6%) in ruling out ECC. Discharging patients with NH-IMRangio<40 units at 48 hours after admission would reduce the total in-hospital stay by 943 days (median 2 [1-4] days per patient). CONCLUSIONS: NH-IMRangio is a valuable risk-stratification tool in patients with ST-segment-elevation myocardial infarction. NH-IMRangio guided strategies to early discharge may contribute to safely shorten hospital stay, optimizing resources utilization.

Why percutaneous revascularisation might not reduce the risk of myocardial infarction and mortality in patients with stable CAD?

Percutaneous coronary intervention (PCI) is widely adopted to treat chronic coronary artery disease. Numerous randomised trials have been conducted to test whether PCI may provide any prognostic advantage over oral medical therapy (OMT) alone, without definitive results. This has maintained the paradigm of OMT as the first-line standard of care for patients, reserving PCI for symptom control. In this review, we discuss the current evidence in favour and against PCI in stable coronary syndromes and highlight the pitfalls of the available studies. We offer a critical appraisal of the possible reasons why the existing data does not provide evidence supporting the role of PCI in improving clinical outcomes in patients with stable coronary syndromes.

Periprocedural antithrombotic strategies in acute coronary syndromes undergoing percutaneous coronary intervention: Have we discarded bivalirudin too soon?

BACKGROUND: Publication of the BRIGHT-4 trial results has restimulated discussion about the optimal periprocedural antithrombotic strategy for patients undergoing percutaneous coronary intervention (PCI) with acute coronary syndromes (ACS). It is possible that variation in the infusion duration, may contribute to observed differences in safety-efficacy profiles of bivalirudin in this clinical setting. METHODS: Up to December 2022, randomized controlled trials (RCTs) comparing bivalirudin (either administered peri-procedurally or accompanied by postprocedural infusion) and heparin, both with or without GPI, were searched and entered in a frequentist network meta-analysis. Co-primary endpoints were trial-defined major adverse composite events (MACE) and major bleeding. Incident rate ratios (IRR) and 95 % confidence intervals (CI) were estimated. RESULTS: 10 RCTs (N = 57,137 patients/month) were included. As compared to heparin, prolonged bivalirudin infusion resulted in lower rates of major bleeding (IRR 0.58, 95 % CI 0.36-0.91), but there was no differences in MACE rates between these strategies. With regard to NACE, prolonged bivalirudin infusion yielded lower risk (IRR 0.86, 95 % CI 0.77-0.96), whereas both bivalirudin and heparin increased risk when coupled with GPI (IRR 1.24, 95 % CI 1.01-1.51 and IRR 1.24, 95 % CI 1.06-1.44, respectively). Both these combination strategies also increased minor bleeding rates (IRR 1.49, 95 % CI 1.16-1.93 and IRR 1.58, 95 % CI 1.29-1.95, respectively, for bivalirudin and heparin). Results were consistent across several sensitivity analyses. CONCLUSION: In patients with ACS undergoing PCI, procedural bivalirudin administration followed by prolonged infusion results in lower major bleeding rates, but there does not appear to be a difference in observed MACE.

The role of invasive and non-invasive imaging technologies and calcium modification therapies in the evaluation and management of coronary artery calcifications.

The treatment of coronary artery disease (CAD) has advanced significantly in recent years due to improvements in medical therapy and percutaneous or surgical revascularization. However, a persistent obstacle in the percutaneous management of CAD is coronary artery calcification (CAC), which portends to higher rates of procedural challenges, post-intervention complications, and overall poor prognosis. With the advent of novel multimodality imaging technologies spanning from intravascular ultrasound to optical coherence tomography to coronary computed tomography angiography combined with advances in calcium debulking and modification techniques, CACs are now targets for intervention with growing success. This review will summarize the most recent developments in the diagnosis and characterization of CAC, offer a comparison of the aforementioned imaging technologies including which ones are most suitable for specific clinical presentations, and review the CAC modifying therapies currently available.

Acute changes in myocardial tissue characteristics during hospitalization in patients with COVID-19.

Background: Patients with a history of COVID-19 infection are reported to have cardiac abnormalities on cardiovascular magnetic resonance (CMR) during convalescence. However, it is unclear whether these abnormalities were present during the acute COVID-19 illness and how they may evolve over time. Methods: We prospectively recruited unvaccinated patients hospitalized with acute COVID-19 (n = 23), and compared them with matched outpatient controls without COVID-19 (n = 19) between May 2020 and May 2021. Only those without a past history of cardiac disease were recruited. We performed in-hospital CMR at a median of 3 days (IQR 1-7 days) after admission, and assessed cardiac function, edema and necrosis/fibrosis, using left and right ventricular ejection fraction (LVEF, RVEF), T1-mapping, T2 signal intensity ratio (T2SI), late gadolinium enhancement (LGE) and extracellular volume (ECV). Acute COVID-19 patients were invited for follow-up CMR and blood tests at 6 months. Results: The two cohorts were well matched in baseline clinical characteristics. Both had normal LVEF (62 ± 7 vs. 65 ± 6%), RVEF (60 ± 6 vs. 58 ± 6%), ECV (31 ± 3 vs. 31 ± 4%), and similar frequency of LGE abnormalities (16 vs. 14%; all p > 0.05). However, measures of acute myocardial edema (T1 and T2SI) were significantly higher in patients with acute COVID-19 when compared to controls (T1 = 1,217 ± 41 ms vs. 1,183 ± 22 ms; p = 0.002; T2SI = 1.48 ± 0.36 vs. 1.13 ± 0.09; p < 0.001). All COVID-19 patients who returned for follow up (n = 12) at 6 months had normal biventricular function, T1 and T2SI. Conclusion: Unvaccinated patients hospitalized for acute COVID-19 demonstrated CMR imaging evidence of acute myocardial edema, which normalized at 6 months, while biventricular function and scar burden were similar when compared to controls. Acute COVID-19 appears to induce acute myocardial edema in some patients, which resolves in convalescence, without significant impact on biventricular structure and function in the acute and short-term. Further studies with larger numbers are needed to confirm these findings.

Rationale and Design of a Randomized Controlled Pilot Trial to Assess Stent Retriever Thrombectomy for Thrombus Burden Reduction in Patients with Acute Myocardial Infarction: The RETRIEVE-AMI Study.

BACKGROUND: ST-elevation myocardial infarction (STEMI) is typically caused by thrombotic occlusion of a coronary artery with subsequent hypoperfusion and myocardial necrosis. In approximately half of patients with STEMI, despite successful restoration of epicardial coronary patency, downstream myocardium perfusion remains impeded. Coronary microvascular injury is one of the key mechanisms behind suboptimal myocardial perfusion and it is primarily, yet not exclusively, related to distal embolization of atherothrombotic material following recanalization of the culprit artery. Routine manual thrombus-aspiration has failed to show clinical efficacy in this scenario. This could be related with limitations in technology adopted as well as patients' selection. To this end, we set out to explore the efficacy and safety of stent retriever-assisted thrombectomy based on clot-removal device routinely used in stroke intervention. STUDY DESIGN AND OBJECTIVES: The stent RETRIEVEr thrombectomy for thrombus burden reduction in patients with Acute Myocardial Infarction (RETRIEVE-AMI) study has been designed to establish whether stent retriever-based thrombectomy is safe and more efficacious in thrombus modification than the current standard of care: manual thrombus aspiration or stenting. The RETRIEVE-AMI trial will enrol 81 participants admitted for primary PCI for inferior STEMI. Participants will be 1:1:1 randomised to receive either standalone PCI, thrombus aspiration and PCI, or retriever-based thrombectomy and PCI. Change in thrombus burden will be assessed via optical coherence tomography imaging. A telephone follow-up at 6 months will be arranged. CONCLUSIONS: It is anticipated by the investigators that stent retriever thrombectomy will more effectively reduce the thrombotic burden compared to current standard of care whilst being clinically safe.

Acute Response in the Noninfarcted Myocardium Predicts Long-Term Major Adverse Cardiac Events After STEMI.

BACKGROUND: Acute ST-segment elevation myocardial infarction (STEMI) has effects on the myocardium beyond the immediate infarcted territory. However, pathophysiologic changes in the noninfarcted myocardium and their prognostic implications remain unclear. OBJECTIVES: The purpose of this study was to evaluate the long-term prognostic value of acute changes in both infarcted and noninfarcted myocardium post-STEMI. METHODS: Patients with acute STEMI undergoing primary percutaneous coronary intervention underwent evaluation with blood biomarkers and cardiac magnetic resonance (CMR) at 2 days and 6 months, with long-term follow-up for major adverse cardiac events (MACE). A comprehensive CMR protocol included cine, T2-weighted, T2∗, T1-mapping, and late gadolinium enhancement (LGE) imaging. Areas without LGE were defined as noninfarcted myocardium. MACE was a composite of cardiac death, sustained ventricular arrhythmia, and new-onset heart failure. RESULTS: Twenty-two of 219 patients (10%) experienced an MACE at a median of 4 years (IQR: 2.5-6.0 years); 152 patients returned for the 6-month visit. High T1 (>1250 ms) in the noninfarcted myocardium was associated with lower left ventricular ejection fraction (LVEF) (51% ± 8% vs 55% ± 9%; P = 0.002) and higher NT-pro-BNP levels (290 pg/L [IQR: 103-523 pg/L] vs 170 pg/L [IQR: 61-312 pg/L]; P = 0.008) at 6 months and a 2.5-fold (IQR: 1.03-6.20) increased risk of MACE (2.53 [IQR: 1.03-6.22]), compared with patients with normal T1 in the noninfarcted myocardium (P = 0.042). A lower T1 (<1,300 ms) in the infarcted myocardium was associated with increased MACE (3.11 [IQR: 1.19-8.13]; P = 0.020). Both noninfarct and infarct T1 were independent predictors of MACE (both P = 0.001) and significantly improved risk prediction beyond LVEF, infarct size, and microvascular obstruction (C-statistic: 0.67 ± 0.07 vs 0.76 ± 0.06, net-reclassification index: 40% [IQR: 12%-64%]; P = 0.007). CONCLUSIONS: The acute responses post-STEMI in both infarcted and noninfarcted myocardium are independent incremental predictors of long-term MACE. These insights may provide new opportunities for treatment and risk stratification in STEMI.

The association between cancer diagnosis, care, and outcomes in 1 million patients hospitalized for acute pulmonary embolism.

OBJECTIVES: To evaluate the clinical care provided to cancer patients hospitalized for acute pulmonary embolism (PE), as well as the association between type of cancer, in-hospital care, and clinical outcomes. METHODS: This study examined the in-hospital care (systemic thrombolysis, catheter-directed thrombolysis, and surgical thrombectomy/embolectomy) and clinical outcomes (mortality, major bleeding, and hemorrhagic stroke) among adults hospitalized due to acute PE between October 2015 to December 2018 using the National Inpatient Sample (NIS). Multivariable logistic regression analysis was used to determine adjusted odds ratios (aOR) with 95% confidence interval (95% CI). RESULTS: Of 1,090,130 hospital records included in the analysis, 216,825 (19.9%) had current cancer diagnoses, including lung (4.7%), hematological (2.5%), colorectal (1.6%), breast (1.3%), prostate (0.8%), and 'other' cancer (9.0%). Cancer patients had lower adjusted odds of receiving systemic thrombolysis, catheter-directed therapy, and surgical thrombectomy/embolectomy compared with their non-cancer counterparts (P < 0.001), except for systemic thrombolysis (aOR 0.96, 95% CI 0.85-1.09, P = 0.553) and catheter-directed therapy (aOR 0.82, 95% CI 0.67-1.00, P = 0.053) for prostate cancer. Cancer patients had greater odds of mortality (P < 0.05). Lung cancer patients had the highest odds of mortality (aOR 2.68, 95% CI 2.61-2.76, P < 0.001) and hemorrhagic stroke (aOR 1.75, 95% CI 1.61-1.90, P < 0.001), while colorectal cancer patients had the greatest odds of bleeding (aOR 2.04, 95% CI 1.94-2.15, P < 0.001). CONCLUSION: Among those hospitalized for PE, cancer diagnoses were associated with lower odds of invasive management and poorer in-hospital outcomes, with metastatic status being an especially important determinant. Appropriateness of care could not be assessed in this study.

Machine learning assisted reflectance spectral characterisation of coronary thrombi correlates with microvascular injury in patients with ST-segment elevation acute coronary syndrome.

Aims: We set out to further develop reflectance spectroscopy for the characterisation and quantification of coronary thrombi. Additionally, we explore the potential of our approach for use as a risk stratification tool by exploring the relation of reflectance spectra to indices of coronary microvascular injury. Methods and results: We performed hyperspectral imaging of coronary thrombi aspirated from 306 patients presenting with ST-segment elevation acute coronary syndrome (STEACS). Spatially resolved reflected light spectra were analysed using unsupervised machine learning approaches. Invasive [index of coronary microvascular resistance (IMR)] and non-invasive [microvascular obstruction (MVO) at cardiac magnetic resonance imaging] indices of coronary microvascular injury were measured in a sub-cohort of 36 patients. The derived spectral signatures of coronary thrombi were correlated with both invasive and non-invasive indices of coronary microvascular injury. Successful machine-learning-based classification of the various thrombus image components, including differentiation between blood and thrombus, was achieved when classifying the pixel spectra into 11 groups. Fitting of the spectra to basis spectra recorded for separated blood components confirmed excellent correlation with visually inspected thrombi. In the 36 patients who underwent successful thrombectomy, spectral signatures were found to correlate well with the index of microcirculatory resistance and microvascular obstruction; R 2: 0.80, p < 0.0001, n = 21 and R 2: 0.64, p = 0.02, n = 17, respectively. Conclusion: Machine learning assisted reflectance spectral analysis can provide a measure of thrombus composition and evaluate coronary microvascular injury in patients with STEACS. Future work will further validate its deployment as a point-of-care diagnostic and risk stratification tool for STEACS care.

Constructing custom-made radiotranscriptomic signatures of vascular inflammation from routine CT angiograms: a prospective outcomes validation study in COVID-19.

BACKGROUND: Direct evaluation of vascular inflammation in patients with COVID-19 would facilitate more efficient trials of new treatments and identify patients at risk of long-term complications who might respond to treatment. We aimed to develop a novel artificial intelligence (AI)-assisted image analysis platform that quantifies cytokine-driven vascular inflammation from routine CT angiograms, and sought to validate its prognostic value in COVID-19. METHODS: For this prospective outcomes validation study, we developed a radiotranscriptomic platform that uses RNA sequencing data from human internal mammary artery biopsies to develop novel radiomic signatures of vascular inflammation from CT angiography images. We then used this platform to train a radiotranscriptomic signature (C19-RS), derived from the perivascular space around the aorta and the internal mammary artery, to best describe cytokine-driven vascular inflammation. The prognostic value of C19-RS was validated externally in 435 patients (331 from study arm 3 and 104 from study arm 4) admitted to hospital with or without COVID-19, undergoing clinically indicated pulmonary CT angiography, in three UK National Health Service (NHS) trusts (Oxford, Leicester, and Bath). We evaluated the diagnostic and prognostic value of C19-RS for death in hospital due to COVID-19, did sensitivity analyses based on dexamethasone treatment, and investigated the correlation of C19-RS with systemic transcriptomic changes. FINDINGS: Patients with COVID-19 had higher C19-RS than those without (adjusted odds ratio [OR] 2·97 [95% CI 1·43-6·27], p=0·0038), and those infected with the B.1.1.7 (alpha) SARS-CoV-2 variant had higher C19-RS values than those infected with the wild-type SARS-CoV-2 variant (adjusted OR 1·89 [95% CI 1·17-3·20] per SD, p=0·012). C19-RS had prognostic value for in-hospital mortality in COVID-19 in two testing cohorts (high [≥6·99] vs low [<6·99] C19-RS; hazard ratio [HR] 3·31 [95% CI 1·49-7·33], p=0·0033; and 2·58 [1·10-6·05], p=0·028), adjusted for clinical factors, biochemical biomarkers of inflammation and myocardial injury, and technical parameters. The adjusted HR for in-hospital mortality was 8·24 (95% CI 2·16-31·36, p=0·0019) in patients who received no dexamethasone treatment, but 2·27 (0·69-7·55, p=0·18) in those who received dexamethasone after the scan, suggesting that vascular inflammation might have been a therapeutic target of dexamethasone in COVID-19. Finally, C19-RS was strongly associated (r=0·61, p=0·00031) with a whole blood transcriptional module representing dysregulation of coagulation and platelet aggregation pathways. INTERPRETATION: Radiotranscriptomic analysis of CT angiography scans introduces a potentially powerful new platform for the development of non-invasive imaging biomarkers. Application of this platform in routine CT pulmonary angiography scans done in patients with COVID-19 produced the radiotranscriptomic signature C19-RS, a marker of cytokine-driven inflammation driving systemic activation of coagulation and responsible for adverse clinical outcomes, which predicts in-hospital mortality and might allow targeted therapy. FUNDING: Engineering and Physical Sciences Research Council, British Heart Foundation, Oxford BHF Centre of Research Excellence, Innovate UK, NIHR Oxford Biomedical Research Centre, Wellcome Trust, Onassis Foundation.