{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:32:42Z","timestamp":1760149962242,"version":"build-2065373602"},"reference-count":50,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>This study aims to compare the variable selection strategies of different machine learning (ML) and statistical algorithms in the prognosis of neck pain (NP) recovery. A total of 3001 participants with NP were included. Three dichotomous outcomes of an improvement in NP, arm pain (AP), and disability at 3 months follow-up were used. Twenty-five variables (twenty-eight parameters) were included as predictors. There were more parameters than variables, as some categorical variables had &gt;2 levels. Eight modelling techniques were compared: stepwise regression based on unadjusted p values (stepP), on adjusted p values (stepPAdj), on Akaike information criterion (stepAIC), best subset regression (BestSubset) least absolute shrinkage and selection operator [LASSO], Minimax concave penalty (MCP), model-based boosting (mboost), and multivariate adaptive regression splines (MuARS). The algorithm that selected the fewest predictors was stepPAdj (number of predictors, p = 4 to 8). MuARS was the algorithm with the second fewest predictors selected (p = 9 to 14). The predictor selected by all algorithms with the largest coefficient magnitude was \u201chaving undergone a neuroreflexotherapy intervention\u201d for NP (\u03b2 = from 1.987 to 2.296) and AP (\u03b2 = from 2.639 to 3.554), and \u201cImaging findings: spinal stenosis\u201d (\u03b2 = from \u22121.331 to \u22121.763) for disability. Stepwise regression based on adjusted p-values resulted in the sparsest models, which enhanced clinical interpretability. MuARS appears to provide the optimal balance between model sparsity whilst retaining high predictive performance across outcomes. Different algorithms produced similar performances but resulted in a different number of variables selected. Rather than relying on any single algorithm, confidence in the variable selection may be increased by using multiple algorithms.<\/jats:p>","DOI":"10.3390\/jcm12196232","type":"journal-article","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T01:51:14Z","timestamp":1695865874000},"page":"6232","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Variable Selection Algorithms in Prognostic Factor Research in Neck Pain"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7057-7548","authenticated-orcid":false,"given":"Bernard X. W.","family":"Liew","sequence":"first","affiliation":[{"name":"School of Sport, Rehabilitation and Exercise Sciences, University of Essex, Colchester CO4 3SQ, Essex, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2984-4800","authenticated-orcid":false,"given":"Francisco M.","family":"Kovacs","sequence":"additional","affiliation":[{"name":"Unidad de la Espalda Kovacs, HLA-Moncloa University Hospital, 28008 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"R\u00fcgamer","sequence":"additional","affiliation":[{"name":"Department of Statistics, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, 80539 Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1665-081X","authenticated-orcid":false,"given":"Ana","family":"Royuela","sequence":"additional","affiliation":[{"name":"Biostatistics Unit, Hospital Puerta de Hierro, Instituto Investigaci\u00f3n Sanitaria Puerta de Hierro-Segovia de Arana, Consorcio de Investigaci\u00f3n Biom\u00e9dica en Red de Epidemiolog\u00eda y Salud P\u00fablica, Red Espa\u00f1ola de Investigadores en Dolencias de la Espalda, 28222 Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"m791","DOI":"10.1136\/bmj.m791","article-title":"Global, regional, and national burden of neck pain in the general population, 1990-2017: Systematic analysis of the Global Burden of Disease Study 2017","volume":"368","author":"Safiri","year":"2020","journal-title":"BMJ"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/S0304-3959(98)00268-1","article-title":"Cost-of-illness of neck pain in The Netherlands in 1996","volume":"80","author":"Borghouts","year":"1999","journal-title":"Pain"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"309","DOI":"10.2519\/jospt.2009.0113","article-title":"Neck Pain: Much More Than a Psychosocial Condition","volume":"39","author":"Sterling","year":"2009","journal-title":"J. Orthop. Sports Phys. Ther."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Riley, R.D., Hayden, J.A., Steyerberg, E.W., Moons, K.G., Abrams, K., Kyzas, P.A., Malats, N., Briggs, A., Schroter, S., and Altman, D.G. (2013). Prognosis Research Strategy (PROGRESS) 2: Prognostic factor research. PLoS Med., 10.","DOI":"10.1371\/journal.pmed.1001380"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"101660","DOI":"10.1016\/j.rehab.2022.101660","article-title":"Modifiable lifestyle-related prognostic factors for the onset of chronic spinal pain: A systematic review of longitudinal studies","volume":"65","author":"Manderlier","year":"2022","journal-title":"Ann. Phys. Rehabil. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.msksp.2019.03.009","article-title":"Prognostic factors for persistent pain after a first episode of nonspecific idiopathic, non-traumatic neck pain: A systematic review","volume":"42","author":"Verwoerd","year":"2019","journal-title":"Musculoskelet Sci. Pr."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1097\/j.pain.0000000000000117","article-title":"Prognostic factors of complaints of arm, neck, and\/or shoulder: A systematic review of prospective cohort studies","volume":"156","author":"Bruls","year":"2015","journal-title":"Pain"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kovacs, F.M., Seco-Calvo, J., Fern\u00e1ndez-F\u00e9lix, B.M., Zamora, J., Royuela, A., and Muriel, A. (2019). Predicting the evolution of neck pain episodes in routine clinical practice. BMC Musculoskelet. Disord., 20.","DOI":"10.1186\/s12891-019-2962-9"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1097\/AJP.0000000000000727","article-title":"Trajectories of Pain Intensity Over 1 Year in Adults With Disabling Subacute or Chronic Neck Pain","volume":"35","author":"Jensen","year":"2019","journal-title":"Clin. J. Pain"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e000262","DOI":"10.1136\/fmch-2019-000262","article-title":"Variable selection strategies and its importance in clinical prediction modelling","volume":"8","author":"Chowdhury","year":"2020","journal-title":"Fam. Med. Community Health"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/s10654-019-00529-y","article-title":"A descriptive review of variable selection methods in four epidemiologic journals: There is still room for improvement","volume":"34","author":"Talbot","year":"2019","journal-title":"Eur. J. Epidemiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s10654-009-9411-2","article-title":"Variable selection: Current practice in epidemiological studies","volume":"24","author":"Walter","year":"2009","journal-title":"Eur. J. Epidemiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2021.07.006","article-title":"Variable selection methods were poorly reported but rarely misused in major medical journals: Literature review","volume":"139","author":"Jouffroy","year":"2021","journal-title":"J. Clin. Epidemiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s40537-018-0143-6","article-title":"Step away from stepwise","volume":"5","author":"Smith","year":"2018","journal-title":"J. Big Data"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1097\/j.pain.0000000000001118","article-title":"Machine learning in pain research","volume":"159","author":"Ultsch","year":"2018","journal-title":"Pain"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/s41746-020-0303-x","article-title":"Artificial intelligence to improve back pain outcomes and lessons learnt from clinical classification approaches: Three systematic reviews","volume":"3","author":"Tagliaferri","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.cjca.2021.09.004","article-title":"Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology","volume":"38","author":"Petch","year":"2022","journal-title":"Can. J. Cardiol."},{"key":"ref_18","first-page":"477","article-title":"Boosting Algorithms: Regularization, Prediction and Model Fitting","volume":"22","author":"Buhlmann","year":"2007","journal-title":"Stat. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Society. Ser. B (Methodol.)"},{"key":"ref_20","first-page":"1","article-title":"Multivariate Adaptive Regression Splines","volume":"19","author":"Friedman","year":"1991","journal-title":"Ann. Statist."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1016\/j.scitotenv.2017.12.152","article-title":"Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods","volume":"624","author":"Mendes","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1007\/s00586-022-07188-w","article-title":"Machine learning versus logistic regression for prognostic modelling in individuals with non-specific neck pain","volume":"31","author":"Liew","year":"2022","journal-title":"Eur. Spine J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.jclinepi.2015.10.002","article-title":"A tutorial on variable selection for clinical prediction models: Feature selection methods in data mining could improve the results","volume":"71","author":"Ramezankhani","year":"2016","journal-title":"J. Clin. Epidemiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M14-0698","article-title":"Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and Elaboration","volume":"162","author":"Moons","year":"2015","journal-title":"Ann. Intern. Med."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Harrell, F. (2001). Regression Modeling Strategies with Applications to Linear Models, Logistics Regression, and Survival Analysis, Springer.","DOI":"10.1007\/978-1-4757-3462-1"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kovacs, F.M., Bag\u00f3, J., Royuela, A., Seco, J., Gim\u00e9nez, S., Muriel, A., Abraira, V., Mart\u00edn, J.L., Pe\u00f1a, J.L., and Gestoso, M. (2008). Psychometric characteristics of the Spanish version of instruments to measure neck pain disability. BMC Musculoskelet. Disord., 9.","DOI":"10.1186\/1471-2474-9-42"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1097\/AJP.0000000000000147","article-title":"Patients with neck pain are less likely to improve if they experience poor sleep quality: A prospective study in routine practice","volume":"31","author":"Kovacs","year":"2015","journal-title":"Clin. J. Pain"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1016\/j.spinee.2013.09.039","article-title":"Predicting outcomes of neuroreflexotherapy in patients with subacute or chronic neck or low back pain","volume":"14","author":"Royuela","year":"2014","journal-title":"Spine J."},{"key":"ref_29","first-page":"1","article-title":"mice: Multivariate Imputation by Chained Equations in R","volume":"45","year":"2011","journal-title":"J. Stat. Softw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e210","DOI":"10.1002\/sta4.210","article-title":"Consistent significance controlled variable selection in high-dimensional regression","volume":"7","author":"Zambom","year":"2018","journal-title":"Stat"},{"key":"ref_31","first-page":"1165","article-title":"The control of the false discovery rate in multiple testing under dependency","volume":"29","author":"Yoav","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical model identification","volume":"19","author":"Akaike","year":"1974","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_33","unstructured":"Zhu, J., Hu, L., Huang, J., Jiang, K., Zhang, Y., Lin, S., Zhu, J., and Wang, X. (2021). abess: A Fast Best Subset Selection Library in Python and R. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2504","DOI":"10.1016\/j.apmr.2018.04.026","article-title":"Development of a Multivariate Prognostic Model for Pain and Activity Limitation in People With Low Back Disorders Receiving Physiotherapy","volume":"99","author":"Ford","year":"2018","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1111\/j.1526-4637.2008.00456.x","article-title":"Clinical course and prognostic factors in acute neck pain: An inception cohort study in general practice","volume":"9","author":"Vos","year":"2008","journal-title":"Pain Med."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"16782","DOI":"10.1038\/s41598-020-73740-7","article-title":"Clinical predictive modelling of post-surgical recovery in individuals with cervical radiculopathy: A machine learning approach","volume":"10","author":"Liew","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"33117","DOI":"10.1073\/pnas.2014241117","article-title":"A polynomial algorithm for best-subset selection problem","volume":"117","author":"Zhu","year":"2020","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Desboulets, L.D.D. (2018). A Review on Variable Selection in Regression Analysis. Econometrics, 6.","DOI":"10.3390\/econometrics6040045"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.ijmedinf.2018.05.006","article-title":"Comparison of variable selection methods for clinical predictive modeling","volume":"116","author":"Venable","year":"2018","journal-title":"Int. J. Med. Inf."},{"key":"ref_40","first-page":"579","article-title":"Best Subset, Forward Stepwise or Lasso? Analysis and Recommendations Based on Extensive Comparisons","volume":"35","author":"Hastie","year":"2020","journal-title":"Stat. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1002\/bimj.201700067","article-title":"Variable selection\u2014A review and recommendations for the practicing statistician","volume":"60","author":"Heinze","year":"2018","journal-title":"Biom. J."},{"key":"ref_42","first-page":"513","article-title":"Comment: Boosting Algorithms: Regularization, Prediction and Model Fitting","volume":"22","author":"Trevor","year":"2007","journal-title":"Stat. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Hofner, B., Boccuto, L., and G\u00f6ker, M. (2015). Controlling false discoveries in high-dimensional situations: Boosting with stability selection. BMC Bioinform., 16.","DOI":"10.1186\/s12859-015-0575-3"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.inffus.2018.11.008","article-title":"Ensembles for feature selection: A review and future trends","volume":"52","year":"2019","journal-title":"Inf. Fusion."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1007\/s10994-017-5633-9","article-title":"Optimal classification trees","volume":"106","author":"Bertsimas","year":"2017","journal-title":"Mach. Learn."},{"key":"ref_46","unstructured":"Klusowski, J.M. (2019). Analyzing cart. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1214\/12-AOS1077","article-title":"Valid post-selection inference","volume":"41","author":"Berk","year":"2013","journal-title":"Ann. Stat."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.spl.2018.04.010","article-title":"Selective inference after likelihood- or test-based model selection in linear models","volume":"140","author":"Greven","year":"2018","journal-title":"Stat. Probab. Lett."},{"key":"ref_49","first-page":"894","article-title":"Nearly unbiased variable selection under minimax concave penalty","volume":"38","year":"2010","journal-title":"Ann Stat."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1214\/10-AOAS388","article-title":"Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection","volume":"5","author":"Breheny","year":"2011","journal-title":"Ann. Appl. Stat."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/19\/6232\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:59:52Z","timestamp":1760129992000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/12\/19\/6232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,27]]},"references-count":50,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["jcm12196232"],"URL":"https:\/\/doi.org\/10.3390\/jcm12196232","relation":{},"ISSN":["2077-0383"],"issn-type":[{"type":"electronic","value":"2077-0383"}],"subject":[],"published":{"date-parts":[[2023,9,27]]}}}