ABSTRACT The organ transplantation process faces significant challenges, resulting in poor patient outcomes, wasted resources, and a growing demand that outpaces the supply. With nearly 120,000 patients on the waitlist and 17 patients dying daily awaiting a donor organ, current organ matching methods are suboptimal and inadequate. Despite the wealth of data available, no comprehensive clinical tools exist to aid transplant centers and Organ Procurement Organizations (OPOs) in making critical, time-sensitive organ allocation decisions. InformAI is developing TransplantAI, an innovative clinical decision support platform that utilizes granular, data-driven insights to assist clinicians in making informed decisions regarding organ use and allocation. This NIH SBIR Fast-Track Phase I/II proposal leverages over 500 relevant data points, including donor-recipient organ size-matching information, to significantly improve organ allocation and utilization, ultimately saving lives and lowering healthcare costs. Phase I builds upon our previous research (2021-2023) in liver and kidney transplantation, expanding our focus to heart and lung transplantation. As of December 2022, 3,300 patients were awaiting a heart transplant and 1,000 patients were awaiting a lung transplant. We will assess the accuracy of machine learning (ML) methods, such as XGBoost, in predicting pre- and post-transplant outcomes for heart and lung transplant patients, and develop deep learning U-Net models for accurate organ segmentation from CT scans. Phase II integrates our previous research and AI models in kidney and liver transplantation with our Phase I results and AI models in heart and lung transplantation into a human-in-the-loop AI system for predicting transplant patient outcomes across all organ types (heart, lung, liver, and kidney). TransplantAI overcomes the constraints of current methods by using advanced machine learning techniques for more precise risk assessments with explainable factors impacting predictions and offers a comprehensive method for accurate organ size matching and improved post-transplant outcomes. Our SBIR project aims to deliver quantitative and validated outcome predictions at the point of care for transplant physicians and clinical care teams to improve solid organ transplantation outcomes. This project addresses critical challenges in organ allocation efficiency and patient outcomes, paving the way for future advancements in solid organ transplantation.