Machine learning predicts emergency physician specialties from treatment strategies for patients suspected of myocardial infarction.

BACKGROUND: Our investigation aimed to determine how the diverse backgrounds and medical specialties of emergency physicians (Eps) influence the accuracy of diagnoses and the subsequent treatment pathways for patients presenting preclinically with MI symptoms. By scrutinizing the relationships between EPs' specialties and their approaches to patient care, we aimed to unveil potential variances in diagnostic accuracy and treatment choices. METHODS: In this retrospective, monocenter cohort study, we leveraged machine learning techniques to analyze a comprehensive dataset of 2328 patients with suspected MI, encompassing preclinical diagnoses, electrocardiogram (ECG) interpretations, and subsequent treatment strategies by attending EPs. RESULTS: We demonstrated that diagnosis and treatment patterns of different specialties were distinct enough, that machine learning (ML) was able to differentiate between specialties (maximum area under the receiver operating characteristic = 0.80 for general medicine and 0.80 for surgery). In our study, internist demonstrated the highest accuracy for preclinical identification of STEMI (0.96) whereas surgeons showed the highest accuracy for identifying NSTEMI. Our findings highlight significant correlations between EP specialties and the accuracy of both preclinical diagnoses and subsequent treatment pathways for patients with suspected MI. CONCLUSIONS: Our results offer valuable insights into how the diverse backgrounds and specialties of EPs can influence the optimization of patient care in emergency settings. Understanding these patterns can help in the development of tailored training programs and protocols to enhance diagnostic accuracy and treatment efficacy in emergency cardiac care, ultimately optimizing patient treatment and improving outcomes.

Preclinical identification of acute coronary syndrome without high sensitivity troponin assays using machine learning algorithms.

Preclinical management of patients with acute chest pain and their identification as candidates for urgent coronary revascularization without the use of high sensitivity troponin essays remains a critical challenge in emergency medicine. We enrolled 2760 patients (average age 70 years, 58.6% male) with chest pain and suspected ACS, who were admitted to the Emergency Department of the University Hospital Tübingen, Germany, between August 2016 and October 2020. Using 26 features, eight Machine learning models (non-deep learning models) were trained with data from the preclinical rescue protocol and compared to the "TropOut" score (a modified version of the "preHEART" score which consists of history, ECG, age and cardiac risk but without troponin analysis) to predict major adverse cardiac event (MACE) and acute coronary artery occlusion (ACAO). In our study population MACE occurred in 823 (29.8%) patients and ACAO occurred in 480 patients (17.4%). Interestingly, we found that all machine learning models outperformed the "TropOut" score. The VC and the LR models showed the highest area under the receiver operating characteristic (AUROC) for predicting MACE (AUROC = 0.78) and the VC showed the highest AUROC for predicting ACAO (AUROC = 0.81). A SHapley Additive exPlanations (SHAP) analyses based on the XGB model showed that presence of ST-elevations in the electrocardiogram (ECG) were the most important features to predict both endpoints.

Machine learning insights into thrombo-ischemic risks and bleeding events through platelet lysophospholipids and acylcarnitine species.

Coronary artery disease (CAD) often leads to adverse events resulting in significant disease burdens. Underlying risk factors often remain inapparent prior to disease incidence and the cardiovascular (CV) risk is not exclusively explained by traditional risk factors. Platelets inherently promote atheroprogression and enhanced platelet functions and distinct platelet lipid species are associated with disease severity in patients with CAD. Lipidomics data were acquired using mass spectrometry and processed alongside clinical data applying machine learning to model estimates of an increased CV risk in a consecutive CAD cohort (n = 595). By training machine learning models on CV risk measurements, stratification of CAD patients resulted in a phenotyping of risk groups. We found that distinct platelet lipids are associated with an increased CV or bleeding risk and independently predict adverse events. Notably, the addition of platelet lipids to conventional risk factors resulted in an increased diagnostic accuracy of patients with adverse CV events. Thus, patients with aberrant platelet lipid signatures and platelet functions are at elevated risk to develop adverse CV events. Machine learning combining platelet lipidome data and common clinical parameters demonstrated an increased diagnostic value in patients with CAD and might improve early risk discrimination and classification for CV events.

Thrombus architecture is influenced by the antiplatelet loading treatment in patients with acute myocardial infarction.

BACKGROUND: Intracoronary thrombus formation is a main cause of acute myocardial infarction triggered by platelet activation. However, there are no data on the impact of different treatment strategies with antiplatelet agents before percutaneous coronary intervention (PCI) on histological characteristics of thrombus formation. OBJECTIVE: In this study, we investigate the impact of preinterventional administration of the P2Y12-inhibitors clopidogrel and prasugrel on thrombus composition, highlighting significant changes associated with the antiplatelet pre-treatment. METHODS: We prospectively enrolled 104 consecutive patients with ST-segment elevation myocardial infarction (STEMI) undergoing immediate PCI and thrombus aspiration by immunohistochemical staining along with RNA-sequencing employing Nanostring analysis. Fifty-two patients were treated with either prasugrel loading (60 mg) or clopidogrel loading (600 mg) prior to PCI, respectively. RESULTS: In Patients with STEMI, intracoronary thrombus architecture was significantly altered between patients pre-treated with prasugrel when compared to clopidogrel. Fibrin content of thrombi was significantly decreased (41.8 % versus 66.7 %, p = 0.009) after pre-treatment with prasugrel compared to clopidogrel. Furthermore, levels of MPO positive cells in intracoronary thrombi were significantly decreased in patients with prasugrel pre-treatment (90.5 versus 201.1, p = 0.014) indicating an association of antiplatelet pre-treatment and the inflammatory responses during thrombus formation. Most strikingly, we observed significant differences among both pre-treatment groups regarding altered RNA expression and signaling pathways of thrombo-inflammatory processes within the thrombotic material, which were independently associated with antiplatelet strategies. CONCLUSIONS: Our study elucidates the impact of antiplatelet pre-treatment on thrombus remodeling and architecture, thereby lowering the risk of recurrent adverse cardiovascular events in prasugrel-treated patients.

The Subtilisin-Like Protease Furin Regulates Hemin-Dependent Ectodomain Shedding of Glycoprotein VI.

INTRODUCTION: Hemolysis results in release of free hemoglobin and hemin liberation from erythrocytes. Hemin has been described to induce platelet activation and to trigger thrombosis. METHODS: We evaluated the effect of hemin on platelet function and surface expression of the platelet collagen receptor glycoprotein VI (GPVI). Isolated platelets were stimulated with increasing concentrations of hemin. RESULTS: We found that hemin strongly enhanced platelet activation, aggregation, and aggregate formation on immobilized collagen under flow. In contrast, we found that surface expression of GPVI was significantly reduced upon hemin stimulation with high hemin concentrations indicating that hemin-induced loss of surface GPVI does not hinder platelet aggregation. Loss of hemin-induced surface expression of GPVI was caused by shedding of the ectodomain of GPVI as verified by immunoblotting and is independent of the GPVI or CLEC-2 mediated ITAM (immunoreceptor-tyrosine-based-activation-motif) signaling pathway as inhibitor studies revealed. Hemin-induced GPVI shedding was independent of metalloproteinases such as ADAM10 or ADAM17, which were previously described to regulate GPVI degradation. Similarly, concentration-dependent shedding of CD62P was also induced by hemin. Unexpectedly, we found that the subtilisin-like proprotein convertase furin controls hemin-dependent GPVI shedding as shown by inhibitor studies using the specific furin inhibitors SSM3 and Hexa-D-arginine. In the presence of SSM3 and Hexa-D-arginine, hemin-associated GPVI degradation was substantially reduced. Further, SSM3 inhibited hemin-induced but not CRP-XL-induced platelet aggregation and thrombus formation, indicating that furin controls specifically hemin-associated platelet functions. CONCLUSION: In summary, we describe a novel mechanism of hemin-dependent GPVI shedding and platelet function mediated by furin.

ACKR3 regulates platelet activation and ischemia-reperfusion tissue injury.

Platelet activation plays a critical role in thrombosis. Inhibition of platelet activation is a cornerstone in treatment of acute organ ischemia. Platelet ACKR3 surface expression is independently associated with all-cause mortality in CAD patients. In a novel genetic mouse strain, we show that megakaryocyte/platelet-specific deletion of ACKR3 results in enhanced platelet activation and thrombosis in vitro and in vivo. Further, we performed ischemia/reperfusion experiments (transient LAD-ligation and tMCAO) in mice to assess the impact of genetic ACKR3 deficiency in platelets on tissue injury in ischemic myocardium and brain. Loss of platelet ACKR3 enhances tissue injury in ischemic myocardium and brain and aggravates tissue inflammation. Activation of platelet-ACKR3 via specific ACKR3 agonists inhibits platelet activation and thrombus formation and attenuates tissue injury in ischemic myocardium and brain. Here we demonstrate that ACKR3 is a critical regulator of platelet activation, thrombus formation and organ injury following ischemia/reperfusion.

Platelet-Derived PCSK9 Is Associated with LDL Metabolism and Modulates Atherothrombotic Mechanisms in Coronary Artery Disease.

Platelets play a significant role in atherothrombosis. Proprotein convertase subtilisin/kexin type 9 (PCSK9) is critically involved in the regulation of LDL metabolism and interacts with platelet function. The effect of PCSK9 in platelet function is poorly understood. The authors of this article sought to characterize platelets as a major source of PCSK9 and PCSK9's role in atherothrombosis. In a large cohort of patients with coronary artery disease (CAD), platelet count, platelet reactivity, and platelet-derived PCSK9 release were analyzed. The role of platelet PCSK9 on platelet and monocyte function was investigated in vitro. Platelet count and hyper-reactivity correlated with plasma LDL in CAD. The circulating platelets express on their surface and release substantial amounts of PCSK9. Release of PCSK9 augmented platelet-dependent thrombosis, monocyte migration, and differentiation into macrophages/foam cells. Platelets and PCSK9 accumulated in tissue derived from atherosclerotic carotid arteries in areas of macrophages. PCSK9 inhibition reduced platelet activation and platelet-dependent thrombo-inflammation. The authors identified platelets as a source of PCSK9 in CAD, which may have an impact on LDL metabolism. Furthermore, platelet-derived PCSK9 contributes to atherothrombosis, and inhibition of PCSK9 attenuates thrombo-inflammation, which may contribute to the reported beneficial clinical effects.

Massive haemoptysis in an intravenous drug user with infective tricuspid valve endocarditis.

Major causes of morbidity in intravenous drug users are infections. In infective endocarditis, the tricuspid valve is mainly involved. Masses can cause septic embolisms and, in rare cases, they are associated with mycotic aneurysms of pulmonary arteries that lead to severe haemorrhage. We report the case of a young woman with a history of intravenous drug abuse and prolonged infective tricuspid valve endocarditis. Initially, echocardiography showed large masses on the anterior leaflet of the tricuspid valve and severe tricuspid regurgitation; blood cultures revealed staphylococcus and streptococcus species. Eight months after initial diagnosis, she presented with severe haemoptysis and fever. CT revealed a ruptured mycotic aneurysm of the right pulmonary artery. Lobectomy was performed immediately. Postoperatively, the patient fully recovered. After continued antibiotic treatment, follow-up examinations showed negative echocardiographic findings and blood cultures results.