The aim of this study was to address chronic heart failure (HF) diagnosis with the application of machine learning (ML) approaches. In the present study, we simulated the procedure that is followed in clinical practice, as the models we built are based on various combinations of feature categories, e.g., clinical features, echocardiogram, and laboratory findings. We also investigated the incremental value of each feature type. The total number of subjects utilized was 422. An ML approach is proposed, comprising of feature selection, handling class imbalance, and classification steps. The results for HF diagnosis were quite satisfactory with a high accuracy (91.23%), sensitivity (93.83%), and specificity (89.62%) when features from all categories were utilized. The results remained quite high, even in cases where single feature types were employed.

Echocardiographic markers of right ventricular dysfunction or pressure overload (RV_d/PO) have been used in risk assessment of patients with acute pulmonary embolism (APE). Nevertheless, the role of echocardiography in these patients is incompletely determined. We evaluated the right ventricular function using 'non-conventional' markers of RV_d/PO in patients with APE. This was a prospective, single-arm, single-centre study. Consecutive adult patients hospitalised for APE were included. The RV free wall longitudinal strain (RV-FWLS), the fractional area change (FAC), the ratio tricuspid annular plane systolic excursion (TAPSE)/pulmonary arterial systolic pressure (PASP), and the pulmonary vascular resistance (PVR) were evaluated. One hundred patients (mean age 70.0 ± 13.9 years, female 48%) were screened and 73 had adequate RV-FWLS images. The most common abnormal echocardiographic marker was RV-FWLS (44/73; p < 0.001, for all other echocardiographic indices). Thirty-one patients had either PASP ≥ 36 mmHg or PVR > 2 WU (49.2% of the patients with both indices available). There were significant correlations between RV-FWLS, TAPSE/PASP and PVR with both D-Dimers and B-type natriuretic peptide (BNP), and between FAC and BNP. RF-FWLS differed significantly between patients with a simplified pulmonary embolism severity index (sPESI) score 0 and those with a score ≥1 (p < 0.001). RV_d/PO coexists with APE in a large proportion of patients. RV-FWLS is the most abnormal echocardiographic sign and is related to clinical and biochemical prognostic indices.

Pulmonary embolism (PE) is correlated with serious morbidity and mortality. Efforts have been made to establish and validate mortality predictive scores based mainly on clinical parameters. Patients with PE and traditional indices of echocardiographic right ventricular (RV) dysfunction or pressure overload have a higher probability of a worse outcome. During the last two decades, studies regarding the use of two-dimensional speckle-tracking echocardiography (2DSTE) and its derived indices in the setting of acute PE have been conducted. In this comprehensive review of the literature, we aimed to summarize these studies. Safe conclusions and comparisons among the reviewed studies are prone to statistical errors, mainly because the studies published were heterogenous in design, different 2DSTE-derived parameters were tested, and different clinical outcomes were used as endpoints. Nonetheless, RV strain indices and, more commonly, regional longitudinal strain of the RV free wall have shown a promising correlation with mortality, assisting in the differential diagnosis between PE and other acute or chronic disorders.

Maladaptive activation of the immune system plays a key role in the pathogenesis of chronic kidney disease (CKD). Our aim was to investigate differences in circulating immune cells between type 2 cardiorenal syndrome (CRS-2) patients and CKD patients without cardiovascular disease (CVD). CRS-2 patients were prospectively followed up, with the primary endpoint being all-cause and cardiovascular mortality. Method: A total of 39 stable males with CRS-2 and 24 male CKD patients matched for eGFR (CKD-EPI) were enrolled. A selected panel of immune cell subsets was measured by flow cytometry. Results: Compared to CKD patients, CRS-2 patients displayed higher levels of proinflammatory CD14++CD16+ monocytes (p = 0.04) and T regulatory cells (Tregs) (p = 0.03), lower lymphocytes (p = 0.04), and lower natural killer cells (p = 0.001). Decreased lymphocytes, T-lymphocytes, CD4+ T-cells, CD8+ T-cells, Tregs, and increased CD14++CD16+ monocytes were associated with mortality at a median follow-up of 30 months (p < 0.05 for all). In a multivariate model including all six immune cell subsets, only CD4+ T-lymphocytes remained independent predictors of mortality (OR 0.66; 95% CI 0.50–0.87; p = 0.004). Conclusion: Patients with CRS-2 exhibit alterations in immune cell profile compared to CKD patients of similar kidney function but without CVD. In the CRS-2 cohort, CD4+ T-lymphocytes independently predicted fatal cardiovascular events.

Diagnosis of coronary artery disease is mainly based on invasive imaging modalities such as X-ray angiography, intravascular ultrasound (IVUS) and optical coherence tomography (OCT). Computed tomography coronary angiography (CTCA) is also used as a non-invasive imaging alternative. In this work, we present a novel and unique tool for 3D coronary artery reconstruction and plaque characterization using the abovementioned imaging modalities or their combination. In particular, image processing and deep learning algorithms were employed and validated for the lumen and adventitia borders and plaque characterization at the IVUS and OCT frames. Strut detection is also achieved from the OCT images. Quantitative analysis of the X-ray angiography enables the 3D reconstruction of the lumen geometry and arterial centerline extraction. The fusion of the generated centerline with the results of the OCT or IVUS analysis enables hybrid coronary artery 3D reconstruction, including the plaques and the stent geometry. CTCA image processing using a 3D level set approach allows the reconstruction of the coronary arterial tree, the calcified and non-calcified plaques as well as the detection of the stent location. The modules of the tool were evaluated for efficiency with over 90% agreement of the 3D models with the manual annotations, while a usability assessment using external evaluators demonstrated high usability resulting in a mean System Usability Scale (SUS) score equal to 0.89, classifying the tool as “excellent”.

Background/Objectives: Patient care in Cardiac Intensive Care Units (CICU) has evolved but data on patient characteristics and outcomes are sparse. This retrospective observational study aimed to define clinical characteristics and risk factors of CICU patients, their in-hospital and 30-day mortality, and compare it with established risk scores. Methods: Consecutive patients (n = 294, mean age 70 years, 74% males) hospitalized within 15 months were studied; APACHE II, EHMRG, GWTG-HF, and GRACE II were calculated on admission. Results: Most patients were admitted for ACS (48.3%) and acute decompensated heart failure (ADHF) (31.3%). Median duration of hospitalization was 2 days (IQR = 1, 4). In-hospital infection occurred in 20%, 18% needed mechanical ventilation, 10% renal replacement therapy and 4% percutaneous ventricular assist devices (33%, 29%, 20% and 4%, respectively, for ADHF). In-hospital and 30-day mortality was 18% and 11% for all patients (29% and 23%, respectively, for ADHF). Established scores (especially APACHE II) had a good diagnostic accuracy (area under the curve-AUC). In univariate and multivariate analyses in-hospital intubation and infection, history of coronary artery disease, hypotension, uremia and hypoxemia on admission were the most important risk factors. Based on these, a proposed new score showed a diagnostic accuracy of 0.954 (AUC) for in-hospital mortality, outperforming previous scores. Conclusions: Patients are admitted mainly with ACS or ADHF, the latter with worse prognosis. Several patients need advanced support; intubation and infections adversely affect prognosis. Established scores predict mortality satisfactorily, but larger studies are needed to develop CICU-directed scores to identify risk factors, improve prediction, guide treatment and staff training.