Background/Objectives: To assess the association between moderate N-terminal natriuretic peptide (NT-proBNP) and cardiac alterations and prognosis in septuagenarians without heart failure (HF). Methods: From the STROKESTOP II screening study, 230 individuals aged 75/76 years with NT-proBNP < 900 ng/L were randomly selected. Subjects with persistent atrial fibrillation (AF), more than mild valvular disease, or HF were excluded. Echocardiography was performed. NT-proBNP ≥ 125 ng/L and paroxysmal AF (pAF) on thumb ECG were used as grouping variables. Participants were followed up during a median of 5 years for cardiovascular mortality, HF, AF, and cerebrovascular events. Cox regression analysis was employed for prognostic assessment. Results: Three groups were identified: SR ≥ 125 (n = 94, no pAF and NT-proBNP ≥ 125 ng/L), pAF (n = 77, pAF and NT-proBNP ≥ 125 ng/L), and controls (n = 30, no pAF and NT-proBNP < 125 ng/L). NT-proBNP was not associated with structural (left atrial volume and left ventricular (LV) mass) or functional (E/e’, LV strain) alterations in any group (p > 0.05). Cardiovascular risk factors (HR: 4.6; CI = 1.7–12.3; p = 0.002), but not NT-proBNP (HR: 1.9; CI = 0.7–5.1; p = 0.2), entailed a prognostic value for the composite endpoint of HF, AF, and cardiovascular death. Conclusions: In septuagenarians without HF, modest NT-proBNP elevation was not associated with echocardiographic changes or prognosis
Hypertensive disorders of pregnancy (HDP) remain a leading cause of maternal and perinatal morbidity worldwide, and current screening strategies have limited predictive value in low-risk populations especially for late-onset HDP. This study aimed to develop and internally validate an interpretable machine-learning model for predicting HDP using noninvasive parameters of maternal systemic hemodynamics, endothelial function, and utero-placental and feto-placental blood flow measured in mid-pregnancy. In this cross-sectional cohort, 577 normotensive women underwent impedance cardiography and Doppler ultrasonography at 22 + 0 to 23 + 6 weeks’ gestation. The incidence of HDP was 16.6% (96/577) most (87.5%) occurring at term (≥ 37 weeks), including 73 cases of gestational hypertension (12.6%) and 23 cases of pre-eclampsia (4.0%). An optimized predictive model with seven physiological features was developed using Extreme Gradient Boosting (XGBoost). Hyperparameters were optimized using stratified 10-fold cross-validation maximizing average Precision Recall Area Under the Curve (PR–AUC), and the decision threshold was selected by maximizing the geometric mean of sensitivity and specificity on a separate validation set. On an independent test set ( n = 58; 10 HDP), the model achieved an Area Under the Receiver Operating Curve (ROC–AUC) of 0.82 (95% CI 0.65–0.95) and a PR–AUC of 0.57 (95% CI 0.26–0.84). At the optimized operating point, sensitivity was 70% (95% CI 0.40–1.00), specificity 79% (95% CI 0.67–0.90), precision 41% (95% CI 0.18–0.65), and negative predictive value 93% (95% CI 0.84–1.00). This interpretable, non-invasive mid-gestation model demonstrates strong discrimination and excellent negative predictive value, supporting its integration into routine second-trimester screening for risk stratification without reliance on biochemical markers.