%0 Journal Article
%A Pontillo, Giuseppe
%A Penna, Simone
%A Arrigoni, Filippo
%A Bender, Benjamin
%A Boesch, Sylvia
%A Brunetti, Arturo
%A Cendes, Fernando
%A Chopra, Sidhant
%A Corben, Louise A
%A Deistung, Andreas
%A Delatycki, Martin B
%A Diciotti, Stefano
%A Dogan, Imis
%A Egan, Gary F
%A França, Marcondes C
%A Georgiou-Karistianis, Nellie
%A Göricke, Sophia L
%A Henry, Pierre-Gilles
%A Hernandez-Castillo, Carlos R
%A Hutter, Diane
%A Joers, James M
%A Lenglet, Christophe
%A Lindig, Tobias
%A Lodi, Raffaele
%A Manners, David N
%A Martinez, Alberto R M
%A Martinuzzi, Andrea
%A Marzi, Chiara
%A Mascalchi, Mario
%A Nachbauer, Wolfgang
%A Pane, Chiara
%A Peruzzo, Denis
%A Pishardy, Pramod K
%A Reetz, Kathrin
%A Rezende, Thiago J R
%A Romanzetti, Sandro
%A Saccà, Francesco
%A Schoels, Ludger
%A Schulz, Jorg B
%A Stefani, Ambra
%A Synofzik, Matthis
%A Thomopoulos, Sophia I
%A Thompson, Paul M
%A Timmann, Dagmar
%A Tonon, Caterina
%A Vavla, Marinela
%A Harding, Ian H
%A Cocozza, Sirio
%T Identification of Biological Subtypes of Friedreich Ataxia with Structural MRI-based Machine Learning.
%J Radiology
%V 318
%N 3
%@ 0033-8419
%C Oak Brook, Ill.
%I Soc.
%M DZNE-2026-00272
%P e251386
%D 2026
%X 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
%K Humans
%K Friedreich Ataxia: diagnostic imaging
%K Friedreich Ataxia: classification
%K Friedreich Ataxia: pathology
%K Magnetic Resonance Imaging: methods
%K Female
%K Male
%K Adult
%K Machine Learning
%K Prospective Studies
%K Brain: diagnostic imaging
%K Brain: pathology
%K Middle Aged
%K Disease Progression
%K Young Adult
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:41805414
%R 10.1148/radiol.251386
%U https://pub.dzne.de/record/285633