Stroke Clinical Trials

Major oncological surgery is among the most complex procedures, involving patients with a combination of high-risk factors that can significantly influence immediate postoperative outcomes and quality of life. The intraoperative hemodynamic management of these patients represents a crucial challenge: maintaining cardiovascular stability and fluid balance during the surgery is associated with reduced complications, including acute kidney injury, myocardial ischemia, and sepsis. Literature has shown that intraoperative fluid administration guided by specific algorithms can reduce complications and improve patient outcomes. In recent years, innovations in artificial intelligence (AI) have profoundly changed how hemodynamic variables are managed during surgery. AI enables real-time clinical data processing and offers the possibility to predict imminent hypotension episodes, allowing the medical team to intervene proactively. An example of such technologies is the Hypotension Prediction Index (HPI), which uses a machine learning algorithm to analyze hemodynamic data and predict the risk of hypotension with up to 80% accuracy, up to 10 minutes before it occurs. Therefore, softwares that integrate fluid administration volumes with parameters derived from pulse contour systems are used currently, enabling an analysis of the efficacy of administration of fluid boluses. For example, the Assisted Fluid Management (AFM) software helps the clinician in choosing the timing of fluid administration, determining its effectiveness in terms of fluid responsiveness. This allows to reduce complications related to improper intraoperative fluid management, such as organ damage, and optimize the use of fluids and vasopressor drugs. Despite the growing use of AI in surgery, the clinical and economic impact of such technologies is still under study. Advanced intraoperative hemodynamic management tools have been shown to reduce the duration of hypotensive episodes and improve hemodynamic stability. The clinical impact of such monitoring, in terms of complications and length of postoperative stay, could be crucial to recommend their use in high-risk patient cohorts. This aligns with medical literature showing that postoperative complications increase patient-related hospitalization costs. This study aims to explore the utility of combining a Goal-Directed Hemodynamic Therapy (GDHT) protocol with AI software in three different scenarios. The primary objective of the study is to evaluate if there is a significant difference in intraoperative fluid administration volumes across three different protocols of GDHT supported by AI, in patients undergoing major abdominal oncological surgery. The study's secondary objectives include: * Assess the rate of hypotensive episodes in terms of Time-Weighted Average Hypotension (TWAH) across the three groups. * Analyze the rate of postoperative complications and hospital mortality across the three groups. * Evaluate the total hospital stay duration and/or the number of days spent in intensive care across the three groups. The study aims to provide evidence on the clinical efficacy of haemodynamic monitoring technologies currently present in daily practice. The results will allow us to define an optimization of intraoperative haemodynamic management, improving clinical outcomes and optimizing the use of healthcare resources.