Progress assessment of Stroke patients in robotic rehabilitation treatments

• Grant number: 18/26493-7
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: February 01, 2019
• End date: January 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Alexandre Cláudio Botazzo Delbem
• Grantee: Caio Benatti Moretti
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID
• Associated scholarship(s): 19/06551-5 - Machine-learning-based biomarkers towards customization of robotic rehabilitation treatments, BE.EP.DR

Abstract

Coupled with sensors, robotic devices for Stroke rehabilitation describe the motor behavior of patients as kinematic and dynamic data, which are underexplored in the machine learning context, due to the time-consuming task of pursuing enough data volume. Moreover, the establishment of means for a quantitative assessment of patient progress, as well as whether data volume is large enough for solid learning guarantees remain unclear. Pondered by premises from Statistical Learning Theory, this research project proposes means for assessing the patient progress during the treatment. The uncertainty in binary classification between left and right hemiparesis are to be exploited, towards grounds for the assumption that pathological features in data attenuate over time, as an evidence of patient recovery. (AU)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

MORETTI, Caio Benatti. Machine-learning-based biomarkers towards customization of robotic rehabilitation treatments for stroke patients. 2021. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.