Background: Sepsis is a time-dependent disease: the early recognition of patients at risk for poor outcome is mandatory. Aim: To identify prognostic predictors of the risk of death or admission to intensive care units in a consecutive sample of septic patients, comparing different statistical models and machine learning algorithms. Methods: Retrospective study including 148 patients discharged from an Italian internal medicine unit with a diagnosis of sepsis/septic shock and microbiological identification. Results: Of the total, 37 (25.0%) patients reached the composite outcome. The sequential organ failure assessment (SOFA) score at admission (odds ratio (OR): 1.83; 95% confidence interval (CI): 1.41–2.39; p < 0.001), delta SOFA (OR: 1.64; 95% CI: 1.28–2.10; p < 0.001), and the alert, verbal, pain, unresponsive (AVPU) status (OR: 5.96; 95% CI: 2.13–16.67; p < 0.001) were identified through the multivariable logistic model as independent predictors of the composite outcome. The area under the receiver operating characteristic curve (AUC) was 0.894; 95% CI: 0.840–0.948. In addition, different statistical models and machine learning algorithms identified further predictive variables: delta quick-SOFA, delta-procalcitonin, mortality in emergency department sepsis, mean arterial pressure, and the Glasgow Coma Scale. The cross-validated multivariable logistic model with the least absolute shrinkage and selection operator (LASSO) penalty identified 5 predictors; and recursive partitioning and regression tree (RPART) identified 4 predictors with higher AUC (0.915 and 0.917, respectively); the random forest (RF) approach, including all evaluated variables, obtained the highest AUC (0.978). All models’ results were well calibrated. Conclusions: Although structurally different, each model identified similar predictive covariates. The classical multivariable logistic regression model was the most parsimonious and calibrated one, while RPART was the easiest to interpret clinically. Finally, LASSO and RF were the costliest in terms of number of variables identified.

Takotsubo Syndrome (TTS) is a transient left ventricular systolic dysfunction that mimics acute coronary syndrome (ACS) with unclear pathophysiology. This study aims to evaluate blood cell subtypes in TTS and ACS on admission and their impact on outcome. Admission hemograms of 466 consecutive TTS patients from the German Italian Spanish (GEIST) registry were recorded and, after propensity matching, compared with admission hemograms of 280 ACS patients. Hemogram parameters, including neutrophil lymphocyte ratio (NLR) and lymphocyte monocyte ratio (LMR), were recorded. The primary endpoint was long-term all-cause mortality; the secondary endpoint was in-hospital complications (hemodynamic or electrical instability). Higher monocyte levels and lower LMR were found in TTS compared with ACS patients (0.63 ± 0.3 vs 0.51 ± 0.24 10³/μL, p < 0.001; 2.7 (IQR 1.8-3.9) vs 3.2 (IQR 2.2-4.4), p < 0.01). One hundred thirty-three out of 466 (28.5 %) TTS patients experienced in-hospital complications. In multivariate analysis, LVEF (OR 0.92, 95 %CI 0.90-0.95, p < 0.001), physical triggers (OR 2.59, 95 %CI 1.47-4.55, p < 0.01), and NLR (OR 1.06, 95 %CI 1.03-1.09, p < 0.001) were independently associated with in-hospital complications. At multivariate analysis, including age, gender, physical trigger, admission LVEF, hemoglobin levels and NLR (model 1) or LMR (model 2), NLR (OR 1.02, 95 %CI 1.01-1.03, p < 0.01) or LMR (OR = 0.89, 95 %CI 0.81-0.99, p < 0.04) were independent predictors of long-term mortality. NLR levels above the median value and LMR levels below the median value were associated with poor survival in TTS patients (log-rank p < 0.01). TTS is featured by higher levels of monocytes and lower LMR than ACS during hospital admission. NLR and LMR are independent predictors of long-term mortality in TTS.

Mitral valve prolapse is a common condition. It affects 1–3% of the population. Clinical manifestations range from the absence of symptoms to sudden cardiac death. The arrhythmogenic mechanism is related to fibrotic changes in myocardial posterior caused by valve prolapse. ECG abnormalities indicative of high risk are inverted or biphasic T waves, ST depression, QT prolongation or dispersion, and BEV originating from the left outflow tract or papillary muscles. The echocardiogram allows the identification of mitral prolapse and disjunction of the mitral annulus (MAD), while MRI shows fibrosis. ICD implantation should be considered in high–risk patients with documented ventricular arrhythmias.