Deep-PIRA: Deep learning to predict progression independent of relapse activity at a first demyelinating event.
02/02/2026
2602024435905

About the work

With this project we proposed an artificial intelligence model (based on deep learning), based solely on magnetic resonance imaging (MRI) raw data, able to predict, at the time of the first demyelinating attack, the probability of developing a first episode of progression independent of relapse activity (PIRA) at the individual level and at each one of the following 10 years. This prognostic model, called Deep PIRA, has been successfully validated in an external cohort and has an eminent translational purpose.

Software and Database designs
susana otero
carmen tur
mar tintoré
xavier montalban

Copyright registered declarations

FH
Fundació Hospital Universitari Vall d’Hebron - Institut de Recerca
All exploitation rights
Consolidated inscription:
Attached documents:
0
Copyright infringement notifications:
0
Contact
CT
Carmen Tur
Author - 25%
Consolidated inscription:
Attached documents:
0
Copyright infringement notifications:
0
Contact
SO
Susana Otero
Author - 25%
Consolidated inscription:
Attached documents:
0
Copyright infringement notifications:
0
Contact
XM
Xavier Montalban
Author - 25%
Consolidated inscription:
Attached documents:
0
Copyright infringement notifications:
0
Contact
MT
Mar Tintoré
Author - 25%
Consolidated inscription:
Attached documents:
0
Copyright infringement notifications:
0
Contact

Notify irregularities in this registration

AI Availability Declaration

This work cannot be made available to AI systems.

Print work information
Work information

Title Deep-PIRA: Deep learning to predict progression independent of relapse activity at a first demyelinating event.
With this project we proposed an artificial intelligence model (based on deep learning), based solely on magnetic resonance imaging (MRI) raw data, able to predict, at the time of the first demyelinating attack, the probability of developing a first episode of progression independent of relapse activity (PIRA) at the individual level and at each one of the following 10 years. This prognostic model, called Deep PIRA, has been successfully validated in an external cohort and has an eminent translational purpose.
Work type Software and Database designs
Tags susana otero, carmen tur, mar tintoré, xavier montalban

-------------------------

Registry info in Safe Creative

Identifier 2602024435905
Entry date Feb 2, 2026, 7:55 AM UTC
License All rights reserved

-------------------------

Copyright registered declarations

All exploitation rights 100.00 %. Holder Fundació Hospital Universitari Vall d’Hebron - Institut de Recerca. Date Feb 2, 2026.
Author 25.00 %. Holder Carmen Tur. Date Feb 2, 2026.
Author 25.00 %. Holder Susana Otero. Date Feb 2, 2026.
Author 25.00 %. Holder Xavier Montalban. Date Feb 2, 2026.
Author 25.00 %. Holder Mar Tintoré. Date Feb 2, 2026.


Information available at https://www.safecreative.org/work/2602024435905-deep-pira-deep-learning-to-predict-progression-independent-of-relapse-activity-at-a-first-demyelinating-event-
© 2026 Safe Creative