PROJECT SUMMARY Loss of functional mobility associated with aging is the leading cause of dangerous falls and loss of living independence. Approximately 60% of community-residing individuals >80 years-old have a gait disorder, and abnormal gait patterns are associated with a greater than two-fold increased risk of institutionalization and death in comparison to age-related adults without gait impairments. Through analysis of temporospatial gait parameters of healthy and pathologic populations, gait function can be measured, quantified, and monitored. Three-dimensional (3D) force plates and motion capture technologies are the current gold standard for analysis, but they are limited by their cost, confinement to laboratory settings, and inability to measure large areas. In-the- field tests of physical performance can be conducted by trained personnel to screen for functional mobility and gait impairments, but the resulting data can only be used in comparison gait lab assessments. Other technologies on the market lack data fidelity and require complicated data analysis, which makes them unacceptable to healthcare providers and patients alike. To solve these problems, Axioforce is developing a noninvasive wearable technology that provides near-real time automated gait insights. Axioforce's 3D-force sensing shoe insole, Axiostride, enables artificial intelligence (AI) empowered at-home gait monitoring for aging individuals at- risk of functional mobility decline. This will be the first product to measure 3D ground reaction forces via a shoe insole that can fit within any normal shoe, making it suitable for long term daily use. It will empower clinicians as an easy tool for early detection of gait disorders and declining functional mobility to help prevent further functional decline, falls, and loss of independence. This transition Fast-Track grant will support the development and testing of the sensing insole prototype and accompanying software. In Phase I, the prototype's circuitry will be custom designed to maximize sampling rate and battery life for continuous at-home use, and the most effective arrangement of the sensors within the insole will be determined and validated against a standard 3D force plate, as well as development and testing of an automated data collection and cloud uploading process. In Phase II, an AI algorithm, trained on collected insole data from normal and pathologic gait cycles in aged individuals, will be used to classify individuals above and below important thresholds in functional mobility tests. Secondly, a one-month pilot study will be performed to determine capabilities of the AI empowered Axiostride for unsupervised classification of functional mobility and analyze the product’s acceptability and adoption. Thus, Axioforce aims to further improve its insole prototype and develop and test the accuracy of the accompanying AI algorithm.