TY  - JOUR
AU  - Pontillo, Giuseppe
AU  - Penna, Simone
AU  - Arrigoni, Filippo
AU  - Bender, Benjamin
AU  - Boesch, Sylvia
AU  - Brunetti, Arturo
AU  - Cendes, Fernando
AU  - Chopra, Sidhant
AU  - Corben, Louise A
AU  - Deistung, Andreas
AU  - Delatycki, Martin B
AU  - Diciotti, Stefano
AU  - Dogan, Imis
AU  - Egan, Gary F
AU  - França, Marcondes C
AU  - Georgiou-Karistianis, Nellie
AU  - Göricke, Sophia L
AU  - Henry, Pierre-Gilles
AU  - Hernandez-Castillo, Carlos R
AU  - Hutter, Diane
AU  - Joers, James M
AU  - Lenglet, Christophe
AU  - Lindig, Tobias
AU  - Lodi, Raffaele
AU  - Manners, David N
AU  - Martinez, Alberto R M
AU  - Martinuzzi, Andrea
AU  - Marzi, Chiara
AU  - Mascalchi, Mario
AU  - Nachbauer, Wolfgang
AU  - Pane, Chiara
AU  - Peruzzo, Denis
AU  - Pishardy, Pramod K
AU  - Reetz, Kathrin
AU  - Rezende, Thiago J R
AU  - Romanzetti, Sandro
AU  - Saccà, Francesco
AU  - Schoels, Ludger
AU  - Schulz, Jorg B
AU  - Stefani, Ambra
AU  - Synofzik, Matthis
AU  - Thomopoulos, Sophia I
AU  - Thompson, Paul M
AU  - Timmann, Dagmar
AU  - Tonon, Caterina
AU  - Vavla, Marinela
AU  - Harding, Ian H
AU  - Cocozza, Sirio
TI  - Identification of Biological Subtypes of Friedreich Ataxia with Structural MRI-based Machine Learning.
JO  - Radiology
VL  - 318
IS  - 3
SN  - 0033-8419
CY  - Oak Brook, Ill.
PB  - Soc.
M1  - DZNE-2026-00272
SP  - e251386
PY  - 2026
AB  - Background Friedreich ataxia (FRDA) is an inherited, progressive neurodegenerative disease. Interindividual heterogeneity in the rate and phenotypic profile of disease progression indicates a biologic variability in the pattern and spatial evolution of underlying changes, but the occurrence of possible FRDA subgroups, which could aid in clinical trial design and treatment, are still unknown. Purpose To obtain a structural MRI-based stratification of participants with FRDA using the Subtype and Stage Inference (SuStaIn) algorithm and determine whether these subgroups are biologically meaningful and clinically relevant. Materials and Methods This multicenter secondary analysis of prospectively acquired data included structural MRI and clinical-demographic data from participants from the ENIGMA-Ataxia working group. MRI biomarkers were analyzed using the SuStaIn algorithm to identify subgroups with distinct patterns and disease stages. The clinical and genetic relevance of these subgroups were assessed within a linear model framework. Results This study included 565 participants (mean age, 32 years ± 13.1 [SD]; 286 women; 275 participants with FRDA and 290 healthy controls). SuStaIn identified three subtypes: (a) a classical subtype (66.5
KW  - Humans
KW  - Friedreich Ataxia: diagnostic imaging
KW  - Friedreich Ataxia: classification
KW  - Friedreich Ataxia: pathology
KW  - Magnetic Resonance Imaging: methods
KW  - Female
KW  - Male
KW  - Adult
KW  - Machine Learning
KW  - Prospective Studies
KW  - Brain: diagnostic imaging
KW  - Brain: pathology
KW  - Middle Aged
KW  - Disease Progression
KW  - Young Adult
LB  - PUB:(DE-HGF)16
C6  - pmid:41805414
DO  - DOI:10.1148/radiol.251386
UR  - https://pub.dzne.de/record/285633
ER  -