Scholarlink

Background <p>Limb-girdle muscular dystrophy R2-dysferlin related (LGMD-R2) is a progressive muscle condition with marked variability in disease course, making prognosis challenging. Quantitative MRI (qMRI) has emerged as a complementary tool that may detect progression earlier and more precisely. Integrating different data modalities is challenging with conventional approaches, and artificial intelligence (AI) can help overcome this. Our aim is to develop robust models capable of predicting clinical progression in LGMD-R2 by incorporating AI-based techniques into the analysis pipeline.</p> Methods <p>Data from 188 COS 1 participants were analysed. Disease progression was assessed using the North Star Assessment for Limb Girdle type Muscular Dystrophies (NSAD). Ambulatory individuals with a maximum NSAD ≥ 20 were included, and progression trajectories were identified through hierarchical clustering. Feature selection was performed using a machine learning pipeline, and top predictors were entered into stepwise logistic regression to build clinical-only and combined clinical-MRI models.</p> Results <p>Two stages of progression were identified, a fast one with a mean three-year loss of 14.4 NSAD points, and a moderate one, with a mean loss of 3.8 NSAD points. The combined model achieved better balanced accuracy than the clinical-only one (83.7% vs 78.7%). Key predictors in the combined model were disease duration and fat content measures in the anterior thigh and gracilis muscle, while the clinical model included disease duration, creatine phosphokinase (CK), and 10 m walk/run test velocity.</p> Conclusions <p>Progression in LGMD-R2 can be grouped into distinct clinical trajectories. Individuals at a faster stage of progression were younger, had shorter disease duration, higher CK, greater weakness, and relatively preserved vastus intermedius and gracilis muscles. AI enabled efficient integration of heterogeneous data, and qMRI biomarkers provided complementary information that improved predictive accuracy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Identification of prognostic biomarkers in a large cohort of patients with LGMD R2

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月26日

查看全文
  • Carla F. Bolano-Diaz,
  • Jose Verdu-Diaz,
  • Dan Hao,
  • Meredith K. James,
  • Laura Rufibach,
  • Andrew Blamire,
  • Harmen Reyngoudt,
  • Pierre G. Carlier,
  • Heather Gordish-Dressman,
  • Heather Hilsden,
  • Simone Spuler,
  • John Day,
  • Kristi J. Jones,
  • Diana Bharucha-Goebel,
  • Alan Pestronk,
  • Maggie C. Walter,
  • Carmen Paradas,
  • Tanya Stojkovic,
  • Madoka Mori-Yoshimura,
  • Elena Bravver,
  • Elena Pegoraro,
  • Jerry Mendell,
  • Adrienne Arrieta,
  • Marni Jacobs,
  • Esther Hwang,
  • Elaine Lee,
  • Isabel Illa,
  • Eduard Gallardo,
  • Izaskun Belmonte Jimeno,
  • Elena Montiel-Morillo,
  • Irene Pedrosa-Hernández,
  • Jaume Llauger Rossello,
  • Bruce Harwick,
  • Jackie Sykes,
  • Susan Sparks,
  • Scott Holsten,
  • Lindsay Alfano,
  • Megan Iammarino,
  • Natalie Reash,
  • Brent Yetter,
  • Mark Smith,
  • Emmanuelle Salort-Campana,
  • Bernard Lapeyssonie,
  • Bruno Vandevelde,
  • David Bendahan,
  • Yann Le Fur,
  • Attarian Shahram,
  • Testot-Ferry Albane,
  • Eva M. Coppenrath,
  • Sabine Krause,
  • Olivia Schreiber-Katz,
  • Simone Thiele,
  • Ursula Moore,
  • Michela Guglieri,
  • Elizabeth Harris,
  • Teresinha Evangelista,
  • Alex Murphy,
  • Michelle Eagle,
  • Robert Muni Lofra,
  • Anna Mayhew,
  • Dionne Moat,
  • Jassi Amritpal Singh Sodhi,
  • Helen Sutherland,
  • Tim Hodgson,
  • Fiona E. Smith,
  • Ian Wilson,
  • Dorothy Wallace,
  • Louise Ward,
  • Debra Galley,
  • Chiara Calore,
  • Claudio Semplicini,
  • Luca Bello,
  • Roberto Stramare,
  • Alessandro Rampado,
  • Suna Turk,
  • Ericky Caldas de Almeida Araujo,
  • Noura Azzabou,
  • Jean Yves Hogrel,
  • Aurélie Canal,
  • Cyrille Theis,
  • Jean-Marc Boisserie,
  • Julien Le Louër,
  • Oumar Diabaté,
  • Matthew Har,
  • Julaine M. Florence,
  • Catherine Siener,
  • Linda Schimmoeller,
  • Glenn Foster,
  • Pilar Carbonell,
  • Macarena Cabrera,
  • Juan Bosco Mendez,
  • Nieves Sánchez-Aguilera Práxedes,
  • Yolanda Morgado,
  • Susana Rico Gala,
  • Jennifer Perez,
  • Anne Marie Sawyer,
  • Carolina Tesi-Rocha,
  • Tina Duong,
  • Richard Gee,
  • Nigel F. Clarke,
  • Sarah Sandaradura,
  • Roula Ghaoui,
  • Kayla Cornett,
  • Claire Miller,
  • Sheryl Foster,
  • Anthony Peduto,
  • Kristy Rose,
  • Noriko Sato,
  • Takeshi Tamaru,
  • Shin’ich Takeda,
  • Ai Ashida,
  • Tatayuki Tateishi,
  • Hiroyuki Yajima,
  • Chikako Sakamoto,
  • Takahiro Nakayama,
  • Kazuhiko Segawa,
  • Makiko Endo,
  • Meganne E. Leach,
  • Nora Brody,
  • Brittney DeWolf,
  • Allyn Toles,
  • Stanley T. Fricke,
  • Hansel J. Otero,
  • Ulrike Grieben,
  • Juliana Prugel,
  • Elke Maron,
  • Linda Pax Lowes,
  • Volker Straub,
  • Jordi Diaz-Manera

摘要

Background

Limb-girdle muscular dystrophy R2-dysferlin related (LGMD-R2) is a progressive muscle condition with marked variability in disease course, making prognosis challenging. Quantitative MRI (qMRI) has emerged as a complementary tool that may detect progression earlier and more precisely. Integrating different data modalities is challenging with conventional approaches, and artificial intelligence (AI) can help overcome this. Our aim is to develop robust models capable of predicting clinical progression in LGMD-R2 by incorporating AI-based techniques into the analysis pipeline.

Methods

Data from 188 COS 1 participants were analysed. Disease progression was assessed using the North Star Assessment for Limb Girdle type Muscular Dystrophies (NSAD). Ambulatory individuals with a maximum NSAD ≥ 20 were included, and progression trajectories were identified through hierarchical clustering. Feature selection was performed using a machine learning pipeline, and top predictors were entered into stepwise logistic regression to build clinical-only and combined clinical-MRI models.

Results

Two stages of progression were identified, a fast one with a mean three-year loss of 14.4 NSAD points, and a moderate one, with a mean loss of 3.8 NSAD points. The combined model achieved better balanced accuracy than the clinical-only one (83.7% vs 78.7%). Key predictors in the combined model were disease duration and fat content measures in the anterior thigh and gracilis muscle, while the clinical model included disease duration, creatine phosphokinase (CK), and 10 m walk/run test velocity.

Conclusions

Progression in LGMD-R2 can be grouped into distinct clinical trajectories. Individuals at a faster stage of progression were younger, had shorter disease duration, higher CK, greater weakness, and relatively preserved vastus intermedius and gracilis muscles. AI enabled efficient integration of heterogeneous data, and qMRI biomarkers provided complementary information that improved predictive accuracy.