MMAI-MS

Multi-Modal Analysis and Integration of MS Patient Data

Started
September 1, 2022
Status
Completed
Share this project

Abstract

This project aims to create computational models for predicting the course of the Multiple Sclerosis (MS) disease and stratifying for treatment responses to support clinicians. Based on an already collected data corpus and ongoing data collection, we will adapt and develop novel machine learning methods to exploit the variety of data modalities focusing on disease state characterization and disease progression modeling. This includes natural language processing (NLP) for feature extraction from clinical data, automatic feature detection in magnetic resonance images (MRI), models for longer-term temporal data, and integrative models that combine information from different data sources. Together, these models will allow generating reports for longitudinal comparisons of MS patients to support patient care.

This project is co-funded by PHRT.

People

Collaborators

SDSC Team:
Firat Ozdemir
Luis Salamanca
Ekaterina Krymova
Fernando Perez-Cruz

PI | Partners:

ETH Zurich, Department of Computer Science

  • Prof. Dr. Christian Holz
  • Prof. Dr. Gunnar Rätsch
  • Dr. Cristóbal Esteban
  • Dr. Martina Baumann
  • Dr. Rita Kuznetsova
  • Dr. Neda Davoudi
  • Dr. Shkurta Gashi
  • Dr. Liliana Barrios
  • Max Möbus

More info: siplab.org | bmi.inf.ethz.ch

University Hospital Zurich, Neuroimmunology Department:

  • Prof. Dr. med. Roland Martin
  • Prof. Dr. Andreas Lutteroti
  • Dr. med. Dr. sc. nat. Veronika Kana
  • Dr. med. univ. Marc Hilty
  • Prof. Dr. med. Patrick Roth

More info

description

Motivation

Multiple Sclerosis presents with a wide range of symptoms, imaging findings, and underlying mechanisms of inflammation and nerve damage. Among these, fatigue and poor sleep quality are particularly common and significantly impact patients’ quality of life and long-term outcomes. As a result, accurately assessing disease activity and progression in individual patients remains a major challenge that requires a deep understanding of the key drivers of the disease and how they evolve over time

Proposed Approach / Solution

Data preprocessing and feature extraction from mobile and wearable devices was performed and integrated with other data from the patients. Interpretable statistical and machine learning methods were developed to determine the ability of derived features to distinguish people with MS from healthy controls, recognize MS disability and fatigue levels, and to quantify the effect of sleep quality.

Impact

The proposed analysis demonstrates a potential of using the collected physiological signals from wearables to monitor different aspects of multiple sclerosis status and progression.

Gallery

Annexe

Cover image source: Getty Images

Additional resources

Bibliography

Publications

Moebus, Max; Gashi, Shkurta; Hilty, Marc; Oldrati, Pietro; Holz, Christian; PHRT Consortium, "Meaningful digital biomarkers derived from wearable sensors to predict daily fatigue in multiple sclerosis patients and healthy controls" iScience 27 2 108965 2024 View publication
Moebus, M.; Hilty, M.; Oldrati, P.; Barrios, L.; PHRT Author Consortium; Holz, C. "Assessing the Role of the Autonomic Nervous System as a Driver of Sleep Quality in Patients With Multiple Sclerosis: Observation Study" JMIR Neurotechnology 3 e48148 2024 View publication
Gashi, S.; Oldrati, P.; Moebus, M.; Hilty, M.; Barrios, L.; Ozdemir, F.; Kana, V.; Lutterotti, A.; Rätsch, G.; Holz, C. "Modeling multiple sclerosis using mobile and wearable sensor data" npj Digital Medicine 7 1 64 2024 View publication

Related Pages

More projects

MAGNIFY

In Progress
Machine learning Assisted larGe scale quaNtIfication of building energy FlexibilitY
Energy, Climate & Environment

SPI-GreenFjord

In Progress
Energy, Climate & Environment

SPI-PAMIR

In Progress
Energy, Climate & Environment

TREMA

Completed
Transforming real estate management with AI
Engineering

News

Latest news

First National Calls: 50 selected projects to start in 2025
March 12, 2025

First National Calls: 50 selected projects to start in 2025

First National Calls: 50 selected projects to start in 2025

50 proposals were selected through the review processes of the SDSC's first National Calls.
AIXD | Generative AI toolbox for architects and engineers
January 22, 2025

AIXD | Generative AI toolbox for architects and engineers

AIXD | Generative AI toolbox for architects and engineers

Introducing AIXD (AI-eXtended Design), a toolbox for forward and inverse modeling for exhaustive design exploration.
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
May 1, 2024

Smartair | An active learning algorithm for real-time acquisition and regression of flow field data

Smartair | An active learning algorithm for real-time acquisition and regression of flow field data

We’ve developed a smart solution for wind tunnel testing that learns as it works, providing accurate results faster. It provides an accurate mean flow field and turbulence field reconstruction while shortening the sampling time.

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!