PROJECT SUMMARY/ABSTRACT An aortic aneurysm carries increasing risk of rupture with growing aneurysm diameter. This condition is typically asymptomatic, so screening and surveillance are essential. Ultrasound and other imaging methods are employed for such monitoring at high accuracy. However, these methods require an expert-operator and are expensive, and aortic aneurysms are considerably underdetected at present and may become even more underdetected in the future as the disease prevalence increases with societal aging. The broad goal is to establish a point-of-care device that is convenient in use and cost (e.g., in a smartphone form factor) for aortic aneurysm screening and surveillance. The underlying hypothesis is that arterial waveforms, which can be obtained with such a device, constitute a non- imaging solution for indicating aneurysm size. This new hypothesis will be efficiently and effectively tested by leveraging a wealth of existing patient data. These data include high-fidelity, non-invasive waveforms from four arterial sites and reference imaging measurements of aneurysm size from at least 217 patients and 217 matchable controls. The specific aims are to develop and validate (1) physics-based methods and (2) machine learning methods for predicting aneurysm size from arterial waveforms. The physics-based methods will fit tube-load models of arterial wave transmission and reflection to the waveforms to estimate parameters indicative of aneurysm size. The machine learning methods will employ linear regression or a neural network and take inputs comprising waveform features such as pulse wave velocity, which decreases with increasing aneurysm diameter as predicted by the well-known Moens-Korteweg equation, and number of local waveform maxima, which may increase with enhanced negative wave reflection induced by aneurysm growth, as well as confounding factors such as blood pressure and age, which also alter pulse wave velocity, to predict aneurysm diameter. These methods will be optimized using a portion of the patient data for application to various combinations of the arterial waveforms (e.g., proximal and distal waveforms or single waveforms). The developed methods will then be tested using the remaining data, while blinded to the reference aneurysm measurements, in terms of their ability to track aneurysm diameter and classify patients versus controls and patients before versus after endovascular repair. The final method will be chosen as the one that best balances accuracy of aneurysm monitoring with convenience of arterial waveform measurements. Successful completion of this project will guide the design and justify the development of a point-of-care device that may ultimately help mitigate aortic aneurysm mortality.