The Project

Virtual Sensors for Anomaly detection in people with Multiple Sclerosis (Ref. PID2020-112667RB-I00)

Abstract

Multiple Sclerosis (MS) is a neurological disorder that affects more than 40,000 people in Spain. Currently, it is one of the diseases with higher impact in society, due to its low average incidence age (30 years, 2/3 women), degenerative nature, variability on its symptoms and evolution, and the nonexistence of a cure. Typical treatment of MS involves a combination of pharmacological and rehabilitation approaches. In particular, recent studies have demonstrated that an appropriate rehabilitation therapy can moderate the sequels of MS, and reduce the physical and neurological degeneration. However, as the disease can present different symptoms in each patient, therapy personalization is mandatory to ensure its efficiency.

 

Adapting the rehabilitation therapy to the particular state of each patient is a complex task, as first this state has to be defined. This is typically carried out using clinical scales, which have high granularity and do not take into account the existing variability (not only from one patient to the other, but also within the same patient, whose state may change through the day). In addition, patient evaluation is typically carried out in a clinically controlled environment, with low periodicity and without considering the impacts of the activities of the daily living.

 

Hence, in this project, a set of Virtual Sensors to detect anomalies in the state of people with MS are developed. These sensors use the personalized model of each patient to characterize his/her current state, and use this model as a reference to detect changes in the state of the patient. The Virtual Sensors are fed with the information obtained by monitoring devices, that can be carried out by patients in their daily life in a noninvasive way.

 

In order to carry out this development, two study cases that have not previously been analyzed in the literature have been considered:

1) People with MS that require the use of canes/crutches to walk;

2) people with MS that require the use of wheelchairs to move. Both study cases will share the same methodology, but obviously will require to consider their particularities and will face different challenges.

 

A multi and interdisciplinary team has been composed, which combines technical and clinical know-how. In addition, the project is backed by ADEMBI, the MS patients association from Biscay, which will take part into the required clinical trials.

Objectives

The main challenge of this approach is to characterize the state of the patient in a given time, so that the Virtual Sensor is able to detect slight variations in this state. The final goal is to provide therapists with information that allows them to adapt easily the rehabilitation therapies, so that their efficiency is maximized, which will impact on the quality of life of patients.

 

 

Achievements

The expected contributions of this project are:

1) the development of monitoring sensors (a sensorized tip and a sensorized wheelchair);

2) a set of low-level Virtual Sensors that allow to estimate relevant variables to define the state of the patient;

3) the design of Virtual Sensors to detect anomalies in the state of a patient using Machine Learning approaches;

4) the validation of the proposed approaches with people with MS.

 

Acknowledgements

This project is funded by FEDER/Ministry of Science and Innovation - State Research Agency/Project Project PID2020-112667RBI00, funded by MCIN/AEI/10.13039/501100011033.

 

Software

Patente 1: Dispositivo Sensor para monitorización postural de sedestación de un usuario.

Inventores: I. Cabanes, A. Mancisidor, P. Vermander, N. Pérez, A. Brull, E. Pérez, A. Zubizarreta, C. Pérez

Nº de solicitud: P202130502    País de prioridad: España          Fecha de prioridad: 2-Junio-2021

Tramitada su ampliación al ámbito Europeo:

Nº de Solicitud Europea: EP22177087   País de prioridad: Europa          Fecha de prioridad: 2-Junio-2022

Entidad titular: UPV/EHU

 

Patente 2: Dispositivo Sensor para monitorizar la marcha.

Inventores: A. Rodriguez-Larrad, A. Zubizarreta, I. Cabanes, A. Brull, I. Sesar, J. Torres–Unda, E. Portillo, A. Espin, L. Santisteban

Nº de solicitud: P202130682.   País de prioridad: España          Fecha de prioridad: 16-Julio-2021

Entidad titular: UPV/EHU

Tramitada su ampliación al ámbito Europeo:

Nº de Solicitud Europea: EP22185211   País de prioridad: Europa          Fecha de prioridad: 15-Julio-2022

Entidad titular: UPV/EHU

 

back