PROJECT SUMMARY/ABSTRACTWe propose a better way to diagnose pulmonary embolism (PE) early and save lives. More than 900000 people in theUnited States suffer from acute PE and about 100000 die each year. With 10% of such cases being fatal within the firsthour of the onset of symptoms rapid diagnosis of PE is critical to direct appropriate therapy. Unfortunately clinicalevaluation alone is unreliable and often results in grave diagnostic delays. Furthermore while echocardiography at thepatients bedside can rapidly detect heart dysfunction caused by PE traditional echocardiography performed bycardiology services is not readily available in acute care settings. Thus there is a critical need for use of a rapid non-invasive diagnostic tool at the point-of-care (POC) to accurately assess for PE and direct emergency therapy. The focus ofthis research is to develop innovative artificial intelligence algorithms that can transform the care of patients with PE byenabling non-experts to use echocardiography to detect PE direct emergency therapy and improve survival. Therationale underlying this proposal is that the proposed artificial intelligence technology tools will provide a relativelysimple and time-efficient strategy that can be implemented in most healthcare settings. This will in turn fulfill the overallgoal of creating a positive shift in the management of patients presenting with PE. The proposed specialized artificialintelligence technology would ultimately be applicable to early detection of a wide variety of diseases. The long-termgoal of our research is to develop and implement effective automated ultrasound tools that would significantly impact thediagnosis and treatment of different life-threatening conditions. The objective of this proposal is to develop and validate aprototype mobile artificial intelligence enabled-software platform that can accurately detect echocardiographic signs ofPE. The hypothesis is that artificial intelligence algorithms will achieve levels of diagnostic accuracy equivalent to expertphysician sonographers in detecting PE. This hypothesis will be tested by pursuing two specific aims: 1) Develop amachine learning algorithm for the detection of PE that can be extended to detect other cardiopulmonary conditions usingexplicit echocardiographic signs of PE and implicit image content representations. 2) Validate the accuracy of themachine learning algorithm to detect PE on echocardiographic images using explicit sonographic signs. Innovativereinforcement learning techniques will be utilized to accomplish the specific aims. The proposed research is significantbecause it will transform the care of patients with PE by enabling non-experts to use POC echocardiography. It will alsohave an immediate positive impact because it will help lower morbidity mortality improve quality of life and decreasehealthcare costs by expediting diagnosis and therapeutic interventions. The proximate expected outcome of this work isimprovement in the evaluation of patients with life-threatening PE by inexperienced healthcare providers which willresult in more accurate and rapid identification of cases that require emergency treatment. Our proposal aligns with theNIBIBs overall mission to advance healthcare through innovative engineering and more specifically its emphasis ondevelopment of transformative unsupervised and semi-supervised machine learning technologies to enhance analysis ofcomplex medical images and data for diagnosing and treating a wide range of diseases and health conditions.