Citations

Background: Cardiogenic shock (CS) is a life-threatening complication of ST-elevation myocardial infarction (STEMI) and remains the leading cause of in-hospital mortality, with rates ranging from 5 to 10% despite advances in reperfusion strategies. Early identification and timely intervention are critical for improving outcomes. This study investigates the utility of machine learning (ML) models for predicting the risk of CS during the early phases of care—prehospital, emergency department (ED), and cardiology-on-call—with a focus on accurate triage and prioritization for urgent angiography. Results: In the prehospital phase, the Extra Trees classifier demonstrated the highest overall performance. It achieved an accuracy (ACC) of 0.9062, precision of 0.9078, recall of 0.9062, F1-score of 0.9061, and Matthews correlation coefficient (MCC) of 0.8140, indicating both high predictive power and strong generalization. In the ED phase, the support vector machine model outperformed others with an ACC of 78.12%. During the cardiology-on-call phase, Random Forest showed the best performance with an ACC of 81.25% and consistent values across other metrics. Quadratic discriminant analysis showed consistent and generalizable performance across all early care stages. Key predictive features included the Killip class, ECG rhythm, creatinine, potassium, and markers of renal dysfunction—parameters readily available in routine emergency settings. The greatest clinical utility was observed in prehospital and ED phases, where ML models could support the early identification of critically ill patients and could prioritize coronary catheterization, especially important for centers with limited capacity for angiography. Conclusions: Machine learning-based predictive models offer a valuable tool for early risk stratification in STEMI patients at risk for cardiogenic shock. These findings support the implementation of ML-driven tools in early STEMI care pathways, potentially improving survival through faster and more accurate decision-making, especially in time-sensitive clinical environments.

Objective: Four hypertension-mediated left ventricular hypertrophy (LVH) phenotypes have been reported using cardiac magnetic resonance (CMR): normal LV, LV remodelling, eccentric and concentric LVH, with varying prognostic implications. The electrocardiogram (ECG) is routinely used to detect LVH; however, its capacity to differentiate between LVH phenotypes is unknown. This study aimed to classify hypertension-mediated LVH from the ECG using machine learning and test for associations of ECG-predicted phenotypes with incident cardiovascular outcomes. Methods: ECG biomarkers were extracted from the 12-lead ECG of 20 439 hypertensive patients in UK Biobank (UKB). Classification models integrating ECG and clinical variables were built using logistic regression, support vector machine (SVM), and random forest. The models were trained in 80% of the participants, and the remaining 20% formed the test set. External validation was sought in 877 hypertensive participants from the Study of Health in Pomerania (SHIP). In the UKB test set, we tested for associations between ECG-predicted LVH phenotypes and incident major adverse cardiovascular events (MACE) and heart failure. Results: Among UKB participants 19 408 had normal LV, 758 LV remodelling, 181 eccentric and 92 concentric LVH. Classification performance of the three models was comparable in UKB. SVM (accuracy 0.79, sensitivity 0.59, specificity 0.87, AUC 0.69) was taken forward for external validation with similar results in SHIP. There was superior prediction of eccentric LVH in both cohorts. In the UKB test set, ECG-predicted eccentric LVH was associated with heart failure (hazard ratio 3.42, 95% CI 1.06–9.86). Conclusion: ECG-based ML classifiers represent a potentially accessible screening strategy for the early detection of hypertension-mediated LVH phenotypes.

Background Right ventricular (RV) maladaptation to elevated pulmonary afterload is the primary determinant of outcomes in pulmonary artery (PA) hypertension; however, the pathobiological mechanisms underlying RV decompensation remain poorly understood. Methods We performed global untargeted metabolomics on plasma from 55 patients who underwent gold‐standard RV‐PA coupling measurements using multibeat pressure volume loop assessment in a single‐center cohort and from 1027 patients with coupling surrogate measurements in a larger multicenter cohort, the PVDOMICS (Pulmonary Vascular Disease Phenomics) study. Age and sex‐adjusted linear regression was performed to identify associations between metabolites and coupling metrics. Additionally, we performed a metabolic flux analysis using gene expression data from RV tissue in an independent cohort of 32 patients. Partial least squares–discriminant analysis was used to identify metabolites and reactions characteristic of the decompensated RV. Results RV‐PA coupling was negatively associated with tricarboxylic acid (TCA) cycle intermediate levels. Specifically, plasma α‐ketoglutarate and fumarate were significantly associated with all coupling metrics in both cohorts. Metabolic flux analysis indicated that decompensated RVs exhibited aberrant TCA cycle activity, including reduced acetyl coenzyme A entry and increased lactate elimination, suggesting a shift from the TCA cycle toward glycolysis at the RV tissue level. Conclusions We identify an association between circulating TCA cycle intermediate levels and RV‐PA uncoupling in 2 independent cohorts, and dysregulated TCA cycle metabolism in decompensated PA hypertension RVs, suggesting that aberrant TCA cycle metabolism could represent a hallmark of RV maladaptation in PA hypertension. Further study of this pathway is warranted to develop novel biomarkers of RV function or RV‐targeted therapies.

Background Low-dose colchicine (0.5 mg once daily) reduces the risk of major cardiovascular events in coronary disease, but its mechanism of action is not yet fully understood. We investigated whether low-dose colchicine is associated with changes in pericoronary inflammation and plaque composition in patients with chronic coronary disease. Methods We performed a cross-sectional, nationwide, subanalysis of the Low-Dose Colchicine 2 Trial (LoDoCo2, n=5522). CT angiography studies were performed in 151 participants randomised to colchicine or placebo after a median treatment duration of 28.2 months. Pericoronary adipose tissue (PCAT) attenuation measurements around proximal coronary artery segments and quantitative plaque analysis for the entire coronary tree were performed using artificial intelligence-enabled plaque analysis software. Results Median PCAT attenuation was not significantly different between the two groups (−79.5 Hounsfield units (HU) for colchicine versus −78.7 HU for placebo, p=0.236). Participants assigned to colchicine had a higher volume (169.6 mm 3 vs 113.1 mm 3 , p=0.041) and burden (9.6% vs 7.0%, p=0.035) of calcified plaque, and higher volume of dense calcified plaque (192.8 mm 3 vs 144.3 mm 3 , p=0.048) compared with placebo, independent of statin therapy. Colchicine treatment was associated with a lower burden of low-attenuation plaque in participants on a low-intensity statin, but not in those on a high-intensity statin (p interaction =0.037). Conclusions Pericoronary inflammation did not differ among participants who received low-dose colchicine compared with placebo. Low-dose colchicine was associated with a higher volume of calcified plaque, particularly dense calcified plaque, which is considered a feature of plaque stability.

Cardiovascular disease is the global #1 cause of mortality and morbidity. The majority of cardiovascular diseases is caused by atherosclerosis, a lipid-driven, inflammatory disease of the middle- and large-sized arteries. The disease is characterized by the formation of atherosclerotic plaques throughout the arterial tree. Over the years, insights into the pathogenesis of atherosclerosis have shifted from a ‘lipid-driven’ model to a ‘response-to-injury’ perspective, and more recently to a ‘lipid-driven inflammatory disease’ viewpoint. We are now aware that a network of multiple immune cell-types and -subsets of the innate and adaptive immune system inhabit our arteries. Intricate interactions between these immune cellsubsets, non-immune cells, and local environmental substances such as lipids, cell debris and calcium cause a fluidic balance of pro-inflammatory and regulatory responses. A dysregulation of this balance towards a pro-inflammatory milieu drives atherosclerotic disease progression. Although we have acknowledged that atherosclerosis is an inflammatory disease, state-of-theart treatments are still based on lipid lowering, anti-hypertensive and lifestyle-changing strategies. In the past decade, clinical phase I, II and III trials targeting the immune system revealed that patients tolerate immunotherapy, show decreased inflammation and/or had a reduction in cardiovascular endpoints. However, the search for novel immunotherapeutic targets and treatment regimens as well as stratification of patients who would benefit from such treatments to combat atherosclerotic cardiovascular disease is only just beginning. In this review article, we will highlight the newest insights on the different cell subsets and components of the immune system in atherosclerosis and elaborate on current and future immunotherapeutics to treat atherosclerotic cardiovascular disease.

ABSTRACT Introduction Chronic back/neck pain costs the United States around 250 billion dollars annually. Treatment strategies include medication, physical therapy, and specialized procedures. This study aimed to investigate the trends in procedural frequency and Medicare reimbursement rates for common back pain procedures. Methods Data from 2000 to 2020 were extracted from Medicare Part B National Summary Data files, using Current Procedural Terminology (CPT) codes to identify reimbursement for cervical/thoracic and lumbar/sacral epidural injections, radiofrequency ablation, facet joint injections, and spinal cord stimulators (both percutaneous and paddle). Key metrics included annual total physician charges, reimbursements, and the number of procedures performed. Results From 2000 to 2020, 53,208,205 pain procedures were performed. The most common was lumbar/sacral epidural injections, followed by facet joint injections and radiofrequency ablations. Paddle SCS placement was the least common. Percutaneous SCS had the greatest volume growth, increasing from 3595 to 111,172 [+2992%], followed by lumbar/sacral epidural injections with 118,884 to 1,965,445 [+1553%], and cervical/thoracic epidural injections, 22,480–348,642 [+1451%]. All procedures saw a significant increase in volume except for facet joint injections. Inflation‐adjusted reimbursement per service also increased, with paddle SCS demonstrating the largest increase ($618–$2960 [+379.0%]), followed by percutaneous SCS ($353–$1428 [+304.5%]) and cervical/thoracic epidural injections ($128–$153 [+19.5%]). Conclusions Pain management procedures have increased in volume and reimbursement over the last 20 years. This increased reimbursement may allow for broader access to these procedures compared to prior decades and support a shift from traditional and more invasive surgical procedures to minimally invasive treatments for chronic pain patients.

Background: While early risk stratification in STEMI is essential, the threat of cardiogenic shock (CS) persists after revascularization due to reperfusion injury and evolving instability. However, risk prediction in later phases—after revascularization—is less explored, despite its importance in guiding intensive care decisions. This study evaluates machine learning (ML) models for dynamic risk assessment in interventional cardiology and cardiac intensive care unit (CICU) phases, where timely detection of deterioration can guide treatment escalation. Methods: We retrospectively analyzed clinical and procedural data from 158 patients diagnosed with STEMI complicated by cardiogenic shock, treated between 2019 and 2022 at the Cardiology Department of the University Emergency Hospital of Bucharest, Romania. Machine learning models—Random Forest (RF), and Quadratic Discriminant Analysis (QDA)—were developed and tested specifically for the interventional cardiology and CICU phases. Model performance was evaluated using area under the receiver operating characteristic curve (ROC-AUC), accuracy (ACC), sensitivity, specificity, and F1-score. Results: In the interventional phase, RF and QDA achieved the highest accuracy, both reaching 87.50%. In the CICU, RF and QDA demonstrate the best performance, reaching ACCs of 0.843. QDA maintained consistent performance across phases. Relevant predictors included reperfusion strategy, TIMI flow before percutaneous coronary intervention (PCI), Killip class, creatinine, and Creatine Kinase Index (CKI)—all parameters routinely assessed in STEMI patients. These models effectively identified patients at risk for post-reperfusion complications and hemodynamic decline, supporting decisions regarding extended monitoring and ICU-level care. Conclusions: Predictive models implemented in advanced STEMI phases can contribute to dynamic, phase-specific risk reassessment and optimize CICU resource allocation. These findings support the integration of ML-based tools into post-PCI workflows, enabling earlier detection of clinical decline and more efficient deployment of intensive care resources. When combined with earlier-stage models, the inclusion of interventional and CICU phases forms a dynamic, end-to-end risk assessment framework. With further refinement, this system could be implemented as a mobile application to support clinical decisions throughout the STEMI care continuum.

Background Secondary aortoenteric fistulas (SAEF) following endovascular aortic repair (EVAR) is an extremely rare event but life threatening. Our review offers comprehensive knowledge on pathophysiology, clinical presentation, diagnosis, and treatment options. Aim To summarize the current literature regarding pathophysiology, clinical, diagnostic and therapeutic approach of aortoenteric fistulas secondary to EVAR. Methods We performed a literature search in Pubmed/MEDLINE to identify the literature published about SAEF after EVAR. Cases were summarized in a table and prevalences. Other relevant literature was included in the results sections. Results A total of 35 reports (single cases and small series) with 45 patients were included. SAEF after EVAR can result from infection, inflammation, or mechanical factors. Clinical presentation is often non-specific, ranging from a gastrointestinal herald bleed to hemorrhagic shock, or malaise and general infection-related symptoms. Cross-sectional imaging plays a critical role in diagnosing SAEF. The treatment approach involves a multidisciplinary team approach and requires broad-spectrum intravenous antibiotics, endovascular intervention for urgent hemorrhage control, and open surgical intervention for definitive repair. Long-term antimicrobial therapy is essential to avoid reinfection. Conclusions SAEF following EVAR represents a complex, life-threatening condition with limited evidence-based management strategies. Given the growing prevalence of endovascular procedures, comprehensive knowledge of SAEF is crucial for all health care providers to improve early diagnosis and outcomes.