Project Methods for A Machine-learning Approach To Derive Biology-driven Parkinson's Disease Subtypes And Predict Longitudinal Clinical Outcomes Across Multiple Cohorts
This document summarizes the theoretical rationale and methods for “A Machine Learning Approach to Derive Biology Driven Parkinson’s Disease Subtypes and Predict Longitudinal Clinical Outcomes Across Multiple Cohorts.” This project was funded by the Michael J. Fox Foundation in 2023 through the Data Driven Subtyping and Stratification Program, Grant ID MJFF 023158. This technical brief is intended to help researchers understand and use the resources produced by this project in an open science context.
Authors
- Christian Mattjie (ORCID: https://orcid.org/0000-0002-3745-8686)
- Eduardo Rigon Zimmer (ORCID: https://orcid.org/0000-0002-5349-0053)
- Rafaela Ravazio (ORCID: https://orcid.org/0000-0003-4729-4993)
- Rodrigo C. Barros (ORCID: https://orcid.org/0000-0002-0782-9482)
- Lucas Silveira Kupssinskü (ORCID: https://orcid.org/0000-0003-2580-3996)
- Marco Antônio De Bastiani (ORCID: https://orcid.org/0000-0003-3924-5278)
- Artur Francisco Schumacher Schuh (ORCID: https://orcid.org/0000-0002-8722-0908)
- Andrei Bieger (ORCID: https://orcid.org/0000-0002-6669-2834)
- Daniel Teixeira dos Santos (ORCID: https://orcid.org/0000-0003-0182-424X)
Institutions
- Universidade Federal do Rio Grande do Sul (BR)
- Hospital de Clínicas de Porto Alegre (BR)
- Zimmerman Associates (United States) (US)
- Pontifícia Universidade Católica do Rio Grande do Sul (BR)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-06-26
- DOI
- https://doi.org/10.5281/zenodo.20931762
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00