The correct recognition of the etiology of ischemic stroke (IS) allows tempestive interventions in therapy with the aim of treating the cause and preventing a new cerebral ischemic event. Nevertheless, the identification of the cause is often challenging and is based on clinical features and data obtained by imaging techniques and other diagnostic exams. TOAST classification system describes the different etiologies of ischemic stroke and includes five subtypes: LAAS (large-artery atherosclerosis), CEI (cardio embolism), SVD (small vessel disease), ODE (stroke of other determined etiology), and UDE (stroke of undetermined etiology). AI models, providing computational methodologies for quantitative and objective evaluations, seem to increase the sensitivity of main IS causes, such as tomographic diagnosis of carotid stenosis, electrocardiographic recognition of atrial fibrillation, and identification of small vessel disease in magnetic resonance images. The aim of this review is to provide overall knowledge about the most effective AI models used in the differential diagnosis of ischemic stroke etiology according to the TOAST classification. According to our results, AI has proven to be a useful tool for identifying predictive factors capable of subtyping acute stroke patients in large heterogeneous populations and, in particular, clarifying the etiology of UDE IS especially detecting cardioembolic sources.

Peripheral artery disease (PAD) is a clinical manifestation of atherosclerotic disease with a large-scale impact on the economy and global health. Despite the role played by platelets in the process of atherogenesis being well recognized, evidence has been increasing on the contribution of the coagulation system to the atherosclerosis formation and PAD development, with important repercussions for the therapeutic approach. Histopathological analysis and some clinical studies conducted on atherosclerotic plaques testify to the existence of different types of plaques. Likely, the role of coagulation in each specific type of plaque can be an important determinant in the histopathological composition of atherosclerosis and in its future stability. In this review, we analyze the molecular contribution of inflammation and the coagulation system on PAD pathogenesis, focusing on molecular similarities and differences between atherogenesis in PAD and coronary artery disease (CAD) and discussing the possible implications for current therapeutic strategies and future perspectives accounting for molecular inflammatory and coagulation targets. Understanding the role of cross-talking between coagulation and inflammation in atherosclerosis genesis and progression could help in choosing the right patients for future dual pathway inhibition strategies, where an antiplatelet agent is combined with an anticoagulant, whose role, despite pathophysiological premises and trials’ results, is still under debate.

Introduction: Autonomic nervous system activity in cirrhotic portal hypertension is linked to hyperdynamic circulation. Heart rate variability (HRV) is a validated noninvasive method to assess the sympathovagal balance. To investigate the correlation between HRV parameters and degree of portal hypertension, we studied a cohort of patients with cirrhosis accounting for etiology and treatments. Patients and Methods: In this cross-sectional, observational cohort study, 157 outpatients of both sex with nonalcoholic cirrhosis were assessed by upper gastrointestinal endoscopy to search for esophagogastric varices. Twenty-four-hour electrocardiogram Holter monitoring with 3 HRV parameters measurement [SD of the NN intervals, root mean square successive difference of NN intervals, and SD of the averages of NN intervals (SDANN)] according to time-domain analysis were performed in all patients. Sixteen patients with large esophagogastric varices underwent measurements of the HVPG and assessment of HRV parameters at baseline and after 45 days on carvedilol. Results: The liver dysfunction, expressed by Child-Pugh class or MELD score, was directly related to root mean square successive difference of NN intervals and inversely related to SDANN. Presence of ascites was inversely related to SDANN and to SD of the NN intervals. Treatment with carvedilol had an inverse relation with SDANN. Presence and size of esophagogastric varices had an inverse relation to SDANN and SD of the NN intervals. Upon multivariate analysis the associations between SDANN and Child-Pugh class, size of varices and ascites were confirmed. In the subgroup of 16 patients undergoing HVPG measurement, pressure gradient was unrelated to heart rate and HRV parameters. Conclusions: Time-domain HRV parameters in patients with cirrhosis, confirm the autonomic nervous system alteration, and their correlation to the degree of portal hypertension suggesting a role of the ANS in hepatic decompensation.