Abstract

Introduction: Stroke survivors experience high levels of social isolation which hinder their rehabilitation and well-being. A gap in the field that impedes intervention development is a lack of real-time social interaction measurement tailored for this population. In response, we developed SocialBit, a smartwatch-based machine learning algorithm to discreetly and passively detect social interactions through privacy-preserving acoustic analysis. In this observational study, we estimated the accuracy of SocialBit to detect social interactions compared to human observers in stroke survivors.
Methods: SocialBit was built as a neural network machine learning algorithm using features from YAMNet and a Transformer classifier. It was then trained and tested in stroke survivors for up to 8 days in hospital. Independently, human observers tallied the presence or absence of social interactions every minute to establish the ground …

Date

January 1, 1970

Authors

Oluwamayomikun Adeboye, Grace Cooke, Kelly White, Samuel Tate, Ross Zafonte, Shrikanth Narayanan, Matthias Mehl, Min Shin, Amar Dhand

Journal

Stroke

Volume

55

Issue

Suppl_1

Pages

ATP14-ATP14

Publisher

Lippincott Williams & Wilkins