Meeting Banner
Abstract #0753

Using Machine Learning to study knee Osteoarthritis: the path towards OA Precision Medicine

Valentina Pedoia1, Jenny Haefeli 1, Kazuhito Morioka1, Hsiang-Ling Tang1, Lorenzo Nardo2, Richard B Suoza1, Adam R Ferguson1, and Sharmila Majumdar1

1University Of California, San Francisco, San Francisco, CA, United States, 2Memorial Sloan Kettering Cancer Center, New York, New York, NY, United States

In this study we describe the analysis of a dataset including 178 subjects with and without Osteoarthritis using Topological data analysis (TDA), a machine-learning tool that involves projecting individual patients into the ‘syndromic space’ defined by all outcome variables simultaneously. Demographics, patient reported outcomes Kellgren-Lawrence grading, MRI WORMS morphological grading, cartilage relaxation times, gait kinematics and kinetics during walking were simultaneously considered to define the data topology. TDA shows the presence of subgroups characterized by a strong biochemical signature, showing how this new technique could be used to extract insight from complex data, allowing for more personalized characterization of each individual.

This abstract and the presentation materials are available to members only; a login is required.

Join Here