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 Authors, "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.; Consortium, P. A.; 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

LUCID National Data Stream

In Progress
Low Value of Care in Medical Hospitalized Patients - a National Data Stream on Quality of Care in Swiss University Hospitals
Health & Biomedical

Syngenta: Steam consumption optimization

Completed
Reliable strategies to save energy in Syngenta’s Kaisten plant
Energy & Sustainability
Private sector

Pilot project ENERBAT

Completed
Data-Driven Pathways to Net Zero for the Canton of Vaud’s Building Portfolio
Energy & Sustainability
Climate & Environment
Public sector

EKZ: Synthetic Load Profile Generation

Completed
Reliable electricity load monitoring for non-metered nodes
Energy & Sustainability
Public sector

News

Latest news

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland
May 7, 2026

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Held at the SDSC headquarters at Biopôle, the Energy Data Hackdays gather 100 experts to tackle 5 energy and grid challenges.
Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués
April 30, 2026

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Le SDSC et le Canton de Vaud ont retenu quatre projets parmi les 57 soumissions reçues lors de leur deuxième appel à projets.
Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne
March 12, 2026

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le SDSC inaugure aujourd'hui son siège au campus Biopôle de Lausanne, dans le cadre d'un partenariat stratégique avec l'État de Vaud.

Contact us

Let’s talk Data Science

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