Developing a new tool for scoliosis screening in a tertiary specialistic setting using artificial intelligence: a retrospective study on 10,813 patients: 2023 SOSORT award winner.
Adolescent idiopathic scoliosis
Machine learning
Prediction model
Journal
European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society
ISSN: 1432-0932
Titre abrégé: Eur Spine J
Pays: Germany
ID NLM: 9301980
Informations de publication
Date de publication:
11 2023
11 2023
Historique:
received:
01
08
2023
accepted:
06
08
2023
revised:
01
08
2023
medline:
31
10
2023
pubmed:
31
8
2023
entrez:
31
8
2023
Statut:
ppublish
Résumé
The study aims to assess if the angle of trunk rotation (ATR) in combination with other readily measurable clinical parameters allows for effective non-invasive scoliosis screening. We analysed 10,813 patients (4-18 years old) who underwent clinical and radiological evaluation for scoliosis in a tertiary clinic specialised in spinal deformities. We considered as predictors ATR, Prominence (mm), visible asymmetry of the waist, scapulae and shoulders, familiarity, sex, BMI, age, menarche, and localisation of the curve. We implemented a Logistic Regression model to classify the Cobb angle of the major curve according to thresholds of 15, 20, 25, 30, and 40 degrees, by randomly splitting the dataset into 80-20% for training and testing, respectively. The model showed accuracies of 74, 81, 79, 79, and 84% for 15-, 20-, 25-, 30- and 40-degrees thresholds, respectively. For all the thresholds ATR, Prominence, and visible asymmetry of the waist were the top five most important variables for the prediction. Samples that were wrongly classified as negatives had always statistically significant (p ≪ 0.01) lower values of ATR and Prominence. This confirmed that these two parameters were very important for the correct classification of the Cobb angle. The model showed better performances than using the 5 and 7 degrees ATR thresholds to prescribe a radiological examination. Machine-learning-based classification models have the potential to effectively improve the non-invasive screening for AIS. The results of the study constitute the basis for the development of easy-to-use tools enabling physicians to decide whether to prescribe radiographic imaging.
Identifiants
pubmed: 37650978
doi: 10.1007/s00586-023-07892-1
pii: 10.1007/s00586-023-07892-1
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
3836-3845Informations de copyright
© 2023. The Author(s).
Références
Konieczny MR, Senyurt H, Krauspe R (2013) Epidemiology of adolescent idiopathic scoliosis. J Child Orthop 7:3–9. https://doi.org/10.1007/s11832-012-0457-4
doi: 10.1007/s11832-012-0457-4
pubmed: 24432052
Brooks HL, Azen SP, Gerberg E et al (1975) Scoliosis: a prospective epidemiological study. J Bone Joint Surg Am 57:968–972
doi: 10.2106/00004623-197557070-00015
pubmed: 1194304
Huang SC (1997) Cut-off point of the Scoliometer in school scoliosis screening. Spine (Phila Pa 1976) 22:1985–1989. https://doi.org/10.1097/00007632-199709010-00007
doi: 10.1097/00007632-199709010-00007
pubmed: 9306527
Wong H-K, Hui JHP, Rajan U, Chia H-P (2005) Idiopathic scoliosis in Singapore schoolchildren: a prevalence study 15 years into the screening program. Spine (Phila Pa 1976) 30:1188–1196. https://doi.org/10.1097/01.brs.0000162280.95076.bb
doi: 10.1097/01.brs.0000162280.95076.bb
pubmed: 15897834
Parent S, Newton PO, Wenger DR (2005) Adolescent idiopathic scoliosis: etiology, anatomy, natural history, and bracing. Instr Course Lect 54:529–536
pubmed: 15948477
Lonstein JE (2006) Scoliosis: surgical versus nonsurgical treatment. Clin Orthop Relat Res 443:248–259. https://doi.org/10.1097/01.blo.0000198725.54891.73
doi: 10.1097/01.blo.0000198725.54891.73
pubmed: 16462448
Weinstein SL, Dolan LA, Wright JG, Dobbs MB (2013) Effects of bracing in adolescents with idiopathic scoliosis. N Engl J Med 369:1512–1521. https://doi.org/10.1056/NEJMoa1307337
doi: 10.1056/NEJMoa1307337
pubmed: 24047455
pmcid: 3913566
Negrini S, Donzelli S, Aulisa AG et al (2018) 2016 SOSORT guidelines: orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth. Scoliosis Spinal Disord 13. https://doi.org/10.1186/s13013-017-0145-8
Negrini S, Grivas TB (2005) Why do we treat adolescent idiopathic scoliosis? What we want to obtain and to avoid for our patients. SOSORT 2005 Consensus paper. Scoliosis 1:4. https://doi.org/10.1186/1748-7161-1-4
doi: 10.1186/1748-7161-1-4
Altaf F, Drinkwater J, Phan K, Cree AK (2017) Systematic review of school scoliosis screening. Spine Deform 5:303–309. https://doi.org/10.1016/j.jspd.2017.03.009
doi: 10.1016/j.jspd.2017.03.009
pubmed: 28882347
Montgomery F, Willner S (1993) Screening for idiopathic scoliosis. Comparison of 90 cases shows less surgery by early diagnosis. Acta Orthop Scand 64:456–458. https://doi.org/10.3109/17453679308993666
doi: 10.3109/17453679308993666
pubmed: 8213127
Berg AO (1993) Screening for adolescent idiopathic scoliosis: a report from the United States preventive services task force. J Am Board Fam Pract 6:497–501
pubmed: 8213240
Ferraro C, Venturin A, Ferraro M et al (2017) Hump height in idiopathic scoliosis measured using a humpmeter in growing subjects: relationship between the hump height and the Cobb angle and the effect of age on the hump height. Eur J Phys Rehabil Med 53:377–389. https://doi.org/10.23736/S1973-9087.16.04227-1
Bunnell WP (1993) Outcome of spinal screening. Spine (Phila Pa 1976) 18:1572–1580
doi: 10.1097/00007632-199309000-00001
pubmed: 8235833
Bunnell WP (1984) An objective criterion for scoliosis screening. J Bone Joint Surg Am 66:1381–1387
doi: 10.2106/00004623-198466090-00010
pubmed: 6501335
Grosso C, Negrini S, Boniolo A, Negrini A (2002) The validity of clinical examination in adolescent spinal deformities. Stud Health Technol Inform 91:123–125
pubmed: 15462010
Ron E (2003) Cancer risks from medical radiation. Health Phys 85:47–59. https://doi.org/10.1097/00004032-200307000-00011
doi: 10.1097/00004032-200307000-00011
pubmed: 12852471
Applebaum A, Ference R, Cho W (2020) Evaluating the role of surface topography in the surveillance of scoliosis. Spine Deform 8:397–404. https://doi.org/10.1007/s43390-019-00001-7
doi: 10.1007/s43390-019-00001-7
pubmed: 31965557
von Elm E, Altman DG, Egger M et al (2007) The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Lancet 370:1453–1457. https://doi.org/10.1016/S0140-6736(07)61602-X
doi: 10.1016/S0140-6736(07)61602-X
Negrini S, Donzelli S, Di Felice F et al (2020) Construct validity of the Trunk Aesthetic Clinical Evaluation (TRACE) in young people with idiopathic scoliosis. Ann Phys Rehabil Med 63:216–221. https://doi.org/10.1016/j.rehab.2019.10.008
doi: 10.1016/j.rehab.2019.10.008
pubmed: 31816447
Ruopp MD, Perkins NJ, Whitcomb BW, Schisterman EF (2008) Youden Index and optimal cut-point estimated from observations affected by a lower limit of detection. Biom J 50:419–430. https://doi.org/10.1002/bimj.200710415
doi: 10.1002/bimj.200710415
pubmed: 18435502
pmcid: 2515362
Ashworth MA, Hancock JA, Ashworth L, Tessier KA (1988) Scoliosis screening. An approach to cost/benefit analysis. Spine (Phila Pa 1976) 13:1187–1188. https://doi.org/10.1097/00007632-198810000-00024
doi: 10.1097/00007632-198810000-00024
pubmed: 3144755
Yawn BP, Yawn RA, Hodge D et al (1999) A population-based study of school scoliosis screening. JAMA 282:1427–1432. https://doi.org/10.1001/jama.282.15.1427
doi: 10.1001/jama.282.15.1427
pubmed: 10535432
Dunn J, Henrikson NB, Morrison CC et al (2018) Screening for adolescent idiopathic scoliosis: evidence report and systematic review for the US preventive services task force. JAMA 319:173–187. https://doi.org/10.1001/jama.2017.11669
doi: 10.1001/jama.2017.11669
pubmed: 29318283
Aulisa L, Papaleo P, Pola E et al (2007) Association between IL-6 and MMP-3 gene polymorphisms and adolescent idiopathic scoliosis: a case-control study. Spine 32:2700–2702. https://doi.org/10.1097/BRS.0b013e31815a5943
doi: 10.1097/BRS.0b013e31815a5943
pubmed: 18007247
Ren G, Yu K, Xie Z et al (2022) Current applications of machine learning in spine: from clinical view. Global Spine J 12:1827–1840. https://doi.org/10.1177/21925682211035363
doi: 10.1177/21925682211035363
pubmed: 34628966
Tajdari M, Pawar A, Li H et al (2021) Image-based modelling for Adolescent Idiopathic Scoliosis: Mechanistic machine learning analysis and prediction. Comp Methods Appl Mech Eng 374:113590. https://doi.org/10.1016/j.cma.2020.113590
Pasha S, Shah S, Newton P, Harms Study Group (2021) Machine learning predicts the 3D outcomes of adolescent idiopathic scoliosis surgery using patient-surgeon specific parameters. Spine (Phila Pa 1976) 46:579–587. https://doi.org/10.1097/BRS.0000000000003795
doi: 10.1097/BRS.0000000000003795
pubmed: 33821816