PROJECT SUMMARY The primary focus of this research proposal is the refinement and advanced optimization of the Non-Invasive Venous waveform Analysis for Heart Failure (NIVAHF) device, building upon the foundational achievements made under R01HL148244. This device represents a pioneering stride in the field of cardiology, offering the potential for accurate, non-invasive monitoring of volume status, which is paramount for heart failure patients. The advancements made in recent years have rendered a significant shift in our understanding of venous waveforms, leading to the development of this revolutionary monitoring tool--NIVAHF. This tool, at its core, employs an AI neural network algorithm to generate a NIVA Score, a pulmonary capillary wedge pressure (PCWP) equivalent value. This renewal looks to investigate and confront three major limitations found with venous waveform analysis in heart failure patients: tricuspid regurgitation (TR), those having undergone orthotopic heart transplantation (OHT), and those supported by a left ventricular assist device (LVAD). The prevalence of TR in heart failure patients, due to hemodynamic changes, makes it an essential marker of disease severity. Heart transplant recipients are particularly vulnerable, requiring continuous monitoring to detect early signs of graft dysfunction or rejection. Similarly, for LVAD-supported patients, consistent PCWP monitoring becomes a cornerstone for optimal care, as it helps in reducing complications and enhancing overall health outcomes. To address the complex challenges associated with venous waveform analysis, our research advances a multifaceted approach. Initially, we will delve into characterizing the intricate relationship between TR severity and the NIVA Score by harnessing an expansive database and analysis plan. This endeavor aims to recalibrate the device's precision for patients exhibiting different stages of TR. Concurrently, understanding the criticality of post-transplant surveillance, we will lay the groundwork for an OHT specific NIVAHF algorithm. This innovation will be pivotal in the early detection of graft anomalies, potentially amplifying survival rates and uplifting health trajectories for OHT beneficiaries. Lastly, as LVADs, especially the HeartMate 3, become indispensable in heart failure management, our focus sharpens on crafting an AI-driven neural network algorithm tailored for HM3 LVAD patients. The culmination of these targeted efforts will be to furnish a dependable, non-invasive PCWP monitoring device with NIVAHF to these vulnerable heart failure patients.