{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T10:13:18Z","timestamp":1792750398781,"version":"4.5.0"},"reference-count":40,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100013654","name":"Deutsche Gesellschaft f\u00fcr Suchtforschung und Suchttherapie","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013654","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J cachexia sarcopenia muscle"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>5q\u2010Spinal muscular atrophy (SMA) is now one of the 5% treatable rare diseases worldwide. As disease\u2010modifying therapies alter disease progression and patient phenotypes, paediatricians and consulting disciplines face new unknowns in their treatment decisions. Conclusions made from historical patient data sets are now mostly limited, and new approaches are needed to ensure our continued best standard\u2010of\u2010care practices for this exceptional patient group. Here, we present a data\u2010driven machine learning approach to a rare disease data set to predict spinal muscular atrophy (SMA)\u2010associated scoliosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected data from 84 genetically confirmed 5q\u2010SMA patients who have received novel SMA therapies. We performed expert domain knowledge\u2010directed feature engineering, correlation and predictive power score (PPS) analyses for feature selection. To test the predictive performance of the selected features, we trained a Random Forest Classifier and evaluated model performance using standard metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The SMA data set consisted of 1304 visits and over 360 variables. We performed feature engineering for variables related to \u2018interventions\u2019, \u2018devices\u2019, \u2018orthosis\u2019, \u2018ventilation\u2019, \u2018muscle contractures\u2019 and \u2018motor milestones\u2019. Through correlation and PPS analysis paired with expert domain knowledge feature selection, we identified relevant features for scoliosis prediction in SMA that included disease progression markers: Hammersmith Functional Motor Scale Expanded \u2018HFMSE\u2019 (PPS\u2009=\u20090.27) and 6\u2010Minute Walk Test \u20186MWT\u2019 scores (PPS\u2009=\u20090.44), \u2018age\u2019 (PPS\u2009=\u20090.41) and \u2018weight\u2019 (PPS\u2009=\u20090.49), \u2018contractures\u2019 (PPS\u2009=\u20090.17), the use of \u2018assistive devices\u2019 (PPS\u2009=\u20090.39, \u2018ventilation\u2019 (PPS\u2009=\u20090.16) and the presence of \u2018gastric tubes\u2019 (PPS\u2009=\u20090.35) in SMA patients. These features were validated using expert domain knowledge and used to train a Random Forest Classifier with an observed accuracy of 0.82 and an average receiver operating characteristic (ROC) area of 0.87.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The introduction of disease\u2010modifying SMA therapies, followed by the implementation of SMA in newborn screenings, has presented physicians with never\u2010seen patients. We used feature engineering tools to overcome one of the main challenges when using data\u2010driven approaches in rare disease data sets. Through predictive modelling of this data, we defined disease progression markers, which are easily assessed during patient visits and can help anticipate scoliosis onset. This highlights the importance of progressive features in the drug\u2010induced revolution of this rare disease and further supports the ongoing efforts to update the SMA classification. We advocate for the consistent documentation of relevant progression markers, which will serve as a basis for data\u2010driven models that physicians can use to update their best standard\u2010of\u2010care practices.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jcsm.13599","type":"journal-article","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T01:48:53Z","timestamp":1733449733000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Feature Engineering for the Prediction of Scoliosis in 5q\u2010Spinal Muscular Atrophy"],"prefix":"10.1002","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9993-6882","authenticated-orcid":false,"given":"Tu\u2010Lan","family":"Vu\u2010Han","sequence":"first","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"},{"name":"Explainable AI for Biology Zuse Institute Berlin  Berlin Germany"},{"name":"Berlin Institute of Health at Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, BIH Biomedical Innovation Academy  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikram","family":"Sunkara","sequence":"additional","affiliation":[{"name":"Explainable AI for Biology Zuse Institute Berlin  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo","family":"Bermudez\u2010Schettino","sequence":"additional","affiliation":[{"name":"Center for Humans and Machines Max\u2010Planck Institute for Human Development  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob","family":"Schwechten","sequence":"additional","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin","family":"Runge","sequence":"additional","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Perka","sequence":"additional","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Winkler","sequence":"additional","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"},{"name":"Berlin Institute of Health at Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, BIH Biomedical Innovation Academy  Berlin Germany"},{"name":"Institute of Health, Berlin Institute of Health Center for Regenerative Therapies  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Pokutta","sequence":"additional","affiliation":[{"name":"Interactive Optimization and Learning Zuse Institute Berlin  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Wei\u00df","sequence":"additional","affiliation":[{"name":"Department of Pediatric Neurology Charit\u00e9\u2010Universit\u00e4tsmedizin Berlin, Berlin, Germany; Center for Chronically Sick Children, Charit\u00e9\u2010Universit\u00e4tsmedizin Berlin  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Pumberger","sequence":"additional","affiliation":[{"name":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt\u2010Universit\u00e4t Zu Berlin, Center for Musculoskeletal Surgery  Berlin Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jval.2015.05.008"},{"issue":"2","key":"e_1_2_11_3_1","first-page":"S38","article-title":"Natural History and Real\u2010World Data in Rare Diseases: Applications, Limitations, and Future Perspectives","volume":"62","author":"Liu J.","year":"2022","journal-title":"Journal of Clinical Pharmacology"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-021-01783-8"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2016.00007"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-genom-102319-103602"},{"key":"e_1_2_11_7_1","unstructured":"U.S. Food and Drug Administration News Release \u201cFDA Approves First Drug for Spinal Muscular Atrophy \u201d In: FDA Press Announcements FDA (2016) accessed January 18 2021 https:\/\/www.fda.gov\/news\u2010events\/press\u2010announcements\/fda\u2010approves\u2010first\u2010drug\u2010spinal\u2010muscular\u2010atrophy."},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2352-4642(21)00287-X"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1177\/2633105520973985"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nmd.2021.03.007"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1097\/GRF.0000000000000654"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0960-8966(93)90061-N"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-020-06564-8"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-020-01356-1"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1097\/BPO.0000000000001473"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4642"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-019-0998-4"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103208"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2008.08.010"},{"key":"e_1_2_11_20_1","volume-title":"Python 3 Reference Manual","author":"Van Rossum G.","year":"2009"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.5604\/15093492.933792"},{"key":"e_1_2_11_22_1","first-page":"410","article-title":"Contractures of the Upper Extremities in Spinal Muscular Atrophy Type II. Descriptive Clinical Study With Retrospective Data Collection","volume":"12","author":"Fujak A.","year":"2010","journal-title":"Ortopedia, Traumatologia, Rehabilitacja"},{"key":"e_1_2_11_23_1","unstructured":"W.McKinney \u201cData Structures for Statistical Computing in Python Pandas \u201d DataFrame.corr. 1.5.3 ed. Pandas (2010) https:\/\/pandas.pydata.org\/docs\/reference\/api\/pandas.DataFrame.corr.html."},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03021"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"e_1_2_11_26_1","unstructured":"F.Wetschoreck T.Krabel andLabs \u201cppscore\u2014A Python implementation of the Predictive Power Score (PPS) \u201d Python (2022) https:\/\/pypi.org\/project\/ppscore\/#about."},{"key":"e_1_2_11_27_1","first-page":"2825","article-title":"Scikit\u2010learn: Machine Learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_28_1","first-page":"113","article-title":"Proximal Spinal Muscular Atrophy: Current Orthopedic Perspective","volume":"6","author":"Haaker G.","year":"2013","journal-title":"The Application of Clinical Genetics"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1177\/0883073811420294"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/mus.25120"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181d3e308"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awac125"},{"key":"e_1_2_11_33_1","unstructured":"H.Xu K. A.Kinfu W.LeVine et\u00a0al. \u201cWhen Are Deep Networks Really Better Than Decision Forests at Small Sample Sizes and How?arXiv (2021)."},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000007742"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.2307\/2985494"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmr.2012.06.009"},{"key":"e_1_2_11_37_1","first-page":"807","article-title":"Contractures in Neuromuscular Disease","volume":"73","author":"Johnson E. R.","year":"1992","journal-title":"Archives of Physical Medicine and Rehabilitation"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.3349\/ymj.2012.53.6.1183"},{"key":"e_1_2_11_39_1","first-page":"7880","article-title":"Automatically Measuring the Cobb Angle and Screening for Scoliosis on Chest Radiograph With a Novel Artificial Intelligence Method","volume":"14","author":"Xie L.","year":"2022","journal-title":"American Journal of Translational Research"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.3348\/jksr.2021.0146"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-018-2389-8"}],"container-title":["Journal of Cachexia, Sarcopenia and Muscle"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcsm.13599","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jcsm.13599","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcsm.13599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T07:32:59Z","timestamp":1775979179000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jcsm.13599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1002\/jcsm.13599"],"URL":"https:\/\/doi.org\/10.1002\/jcsm.13599","archive":["Portico"],"relation":{},"ISSN":["2190-5991","2190-6009"],"issn-type":[{"value":"2190-5991","type":"print"},{"value":"2190-6009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"2023-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e13599"}}