Machine learning predicts treatment response to nusinersen in non-sitter spinal muscular atrophy (SMA).
8 affiliations
- 1Dubowitz Neuromuscular Centre, UCL Great Ormond Street Institute of Child Health, London, UK.
- 2Health and Medical Science Programme, The Alan Turing Institute, London, UK.
- 3NIHR Great Ormond Street Hospital Biomedical Research Centre, UCL Great Ormond Street Institute of Child Health, London, UK.
- 4Paediatric Neurology Unit, Catholic University, Rome, Italy.
- 5Centro Clinico Nemo, U.O.C. Neuropsichiatria Infantile Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
- 6Population, Policy & Practice Department, UCL Great Ormond Street Institute of Child Health, London, UK.
- 7UCL Cancer Institute and Dept of Medical Physics & Biomedical Engineering, UCL, London, UK.
- 8Department of Statistical Science, UCL.
Abstract
BackgroundNusinersen has substantially increased survival and improved disease progression in Spinal Muscular Atrophy (SMA) patients. However, treatment response is heterogeneous, with some patients gaining the ability to sit and walk whilst others display less obvious changes.MethodFrom the SMA Reach UK and the Italian Telethon Network, 124 non-sitter SMA patients treated with nusinersen under 4 years were included and randomly allocated to training and testing (80/20%). Tree and regression-based machine learning for survival outcomes were compared, and oblique random forests were selected, with a testing C-Index of 0.74. The features were selected from items of the CHOP-INTEND and HINE-2 motor function assessments, respiratory and swallowing status using mutual information.FindingsSixty-two patients (50%) achieved sitting, at a median age of 2.4 years. The predicted median time-to-sitting in those requiring tube feeding at treatment initiation was 4-months later than those without, and this was the most influential factor. Specific motor function features, including the ability to kick in supine, were strongly associated with a higher likelihood of sitting.InterpretationThis work provides a framework for predicting nusinersen-response and represents the first stage in personalised counselling on treatment plans for SMA.FundingSupport for SMA Reach is provided by Biogen, Roche and Novartis, and historically the NIHR BRC, SMA Trust, the MRC Translational Research Centre and MD UK. Support for the Italian network is provided by Famiglie SMA, Telethon (GSP 13002), and ASAMSI.
Related
- Myostatin/Smad3 in Spinal Muscular Atrophy: Biomarkers of Disease Severity and Treatment Response
- Habitat informed 3D deep learning predicts immunochemotherapy response in esophageal squamous cell carcinoma
- Mammography based delta radiomics with machine learning predicts pathologic complete response after neoadjuvant chemotherapy in breast cancer
- Multi-task deep learning integrating pretreatment MRI and whole slide images predicts induction chemotherapy response and survival in locally advanced nasopharyngeal carcinoma
- Response to the Letter Regarding "If Becker Muscular Dystrophy Initially Manifests with Heart Disease and Rhabdomyolysis, Neurological Work-up Is Imperative"
BibTeX
@article{stimpson2026machine,
title = {{Machine learning predicts treatment response to nusinersen in non-sitter spinal muscular atrophy (SMA).}},
author = {Georgia Stimpson and Emer O'Reilly and Giorgia Coratti and Deborah Ridout and Tapabrata Chakraborti and Robin Mitra and Roberto de Sanctis and Marika Pane and Mariacristina Scoto and Eugenio Mercuri and Francesco Muntoni and Giovanni Baranello and International SMA Consortium},
journal = {Journal of neuromuscular diseases},
year = {2026},
month = oct,
doi = {10.1177/22143602261496327},
url = {https://europepmc.org/article/MED/42900957},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning predicts treatment response to nusinersen in non-sitter spinal muscular atrophy (SMA).
AU - Georgia Stimpson
AU - Emer O'Reilly
AU - Giorgia Coratti
AU - Deborah Ridout
AU - Tapabrata Chakraborti
AU - Robin Mitra
AU - Roberto de Sanctis
AU - Marika Pane
AU - Mariacristina Scoto
AU - Eugenio Mercuri
AU - Francesco Muntoni
AU - Giovanni Baranello
AU - International SMA Consortium
PY - 2026
DA - 2026/10/20
JO - Journal of neuromuscular diseases
DO - 10.1177/22143602261496327
UR - https://europepmc.org/article/MED/42900957
AB - BackgroundNusinersen has substantially increased survival and improved disease progression in Spinal Muscular Atrophy (SMA) patients. However, treatment response is heterogeneous, with some patients gaining the ability to sit and walk whilst others display less obvious changes.MethodFrom the SMA Reach UK and the Italian Telethon Network, 124 non-sitter SMA patients treated with nusinersen under 4 years were included and randomly allocated to training and testing (80/20%). Tree and regression-based machine learning for survival outcomes were compared, and oblique random forests were selected, with a testing C-Index of 0.74. The features were selected from items of the CHOP-INTEND and HINE-2 motor function assessments, respiratory and swallowing status using mutual information.FindingsSixty-two patients (50%) achieved sitting, at a median age of 2.4 years. The predicted median time-to-sitting in those requiring tube feeding at treatment initiation was 4-months later than those without, and this was the most influential factor. Specific motor function features, including the ability to kick in supine, were strongly associated with a higher likelihood of sitting.InterpretationThis work provides a framework for predicting nusinersen-response and represents the first stage in personalised counselling on treatment plans for SMA.FundingSupport for SMA Reach is provided by Biogen, Roche and Novartis, and historically the NIHR BRC, SMA Trust, the MRC Translational Research Centre and MD UK. Support for the Italian network is provided by Famiglie SMA, Telethon (GSP 13002), and ASAMSI.
SN - 2214-3599
SN - 2214-3602
ER -