BackgroundAngiographic parameters can facilitate the risk stratification of coronary lesions but remain insufficient in the prediction of future myocardial infarction (MI).AIMSWe compared the ability of humans, angiographic parameters and deep learning (DL) to predict the lesion that would be responsible for a future MI in a population of patients with non-significant CAD at baseline.MethodsWe retrospectively included patients who underwent invasive coronary angiography (ICA) for MI, in whom a previous angiogram had been performed within 5 years. The ability of human visual assessment, diameter stenosis, area stenosis, quantitative flow ratio (QFR) and DL to predict the future culprit lesion (FCL) was compared.ResultsIn total, 746 cropped ICA images of FCL and non-culprit lesions (NCL) were analysed. Predictive models for each modality were developed in a training set before validation in a test set. DL exhibited the best predictive performance with an area under the curve of 0.81, compared with diameter stenosis (0.62, p=0.04), area stenosis (0.58, p=0.05) and QFR (0.67, p=0.13). DL exhibited a significant net reclassification improvement (NRI) compared with area stenosis (0.75, p=0.03) and QFR (0.95, p=0.01), and a positive nonsignificant NRI when compared with diameter stenosis. Among all models, DL demonstrated the highest accuracy (0.78) followed by QFR (0.70) and area stenosis (0.68). Predictions based on human visual assessment and diameter stenosis had the lowest accuracy (0.58).ConclusionIn this feasibility study, DL outperformed human visual assessment and established angiographic parameters in the prediction of FCLs. Larger studies are now required to confirm this finding.

A 67-year-old woman underwent a medical check-up by her general practitioner after complaining of atypical pain in the shoulder girdle. Due to the important inflammatory syndrome noticed on blood testing, a polymyalgia rheumatica was suspected and she was started on corticosteroid treatment with good clinical response, but no impact on inflammation. She underwent extensive imaging with a thoraco-abdominal CT scanner that demonstrated a pancreatic mass, then later a PET-CT showed 3 different hyperactive lesions. Biopsies then revealed simultaneous diffuse large B-cell lymphoma (DLBCL), colorectal adenocarcinoma and pancreatic neuroendocrine tumour. She benefited from low rectal endoscopic excision of the colorectal tumour, R-CHOP chemotherapy for DLBCL and laparoscopic left pancreatectomy. Successful treatment required a good multidisciplinary collaboration between the different specialists. The patient made a good recovery and achieved complete remission at 1 year. This an unusual presentation of multiple primary malignancies.

Right ventricular failure (RVF) is often caused by increased afterload and disrupted coupling between the right ventricle (RV) and the pulmonary arteries (PAs). After a phase of adaptive hypertrophy, pressure-overloaded RVs evolve towards maladaptive hypertrophy and finally ventricular dilatation, with reduced stroke volume and systemic congestion. In this article, we review the concept of RV-PA coupling, which depicts the interaction between RV contractility and afterload, as well as the invasive and non-invasive techniques for its assessment. The current principles of RVF management based on pathophysiology and underlying etiology are subsequently discussed. Treatment strategies remain a challenge and range from fluid management and afterload reduction in moderate RVF to vasopressor therapy, inotropic support and, occasionally, mechanical circulatory support in severe RVF.

No abstract