{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T02:51:15Z","timestamp":1789440675926,"version":"build-2803163510"},"reference-count":66,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:00:00Z","timestamp":1778716800000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Palmer College Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Characterise longitudinal patterns of chiropractic visits for neck pain or low back pain by using machine learning (ML) methods and explainable models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Data and Methods<\/jats:title>\n                    <jats:p>Using de-identified claims data from 2016 to 2023 for adults from the Optum Labs Data Warehouse, we applied spectral clustering (SC) to identify novel patient clusters. Then we used explainable boosting machines (EBM) for feature ranking followed by hierarchical group lasso regression for feature selection. A logistic regression model used for parameter estimates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>SC identified 3 clusters\u2014low, moderate and high dose\u2014based on their pattern of chiropractic visits. An interesting finding was a small cluster where patients received persistently higher care for several months. Age, gender and number of prior visits to a chiropractor, primary care provider, or physical therapist emerged as strong indicators for provider type and frequency of visits.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Patients receiving spinal manipulative therapy sorted into 3 markedly different trajectories of utilisation. This unexpected variation mandates further investigation to identify optimal dose based on patient and provider characteristics. We also present EBM, a robust alternative to computationally heavy feature selection methods, to identify features necessary for predictive models. This approach obviates the need for opaque feature selection methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Results show the use of advanced, explainable methods to discover knowledge that can be missed by other methods. We present an approach to identify hidden patterns in large data that can guide hypothesis driven research. Our work can identify factors that drive high utilisation of services and inform practice guidelines.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooag035","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T12:44:17Z","timestamp":1774442657000},"source":"Crossref","is-referenced-by-count":1,"title":["Spectral clustering identifies patterns of chiropractic care in a national longitudinal cohort"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9340-4415","authenticated-orcid":false,"given":"Monika","family":"Ray","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, University of California Davis , CA, Sacramento, California, 95817,","place":["United States"]},{"name":"Center for Healthcare Policy and Research, University of California Davis , CA, Sacramento, California, 95817,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-You","family":"Fang","sequence":"additional","affiliation":[{"name":"Center for Healthcare Policy and Research, University of California Davis , CA, Sacramento, California, 95817,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony J","family":"Lisi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, Yale School of Medicine , New Haven, Connecticut, 06520,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick S","family":"Romano","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, University of California Davis , CA, Sacramento, California, 95817,","place":["United States"]},{"name":"Center for Healthcare Policy and Research, University of California Davis , CA, Sacramento, California, 95817,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"2026051413304001900_ooag035-B1","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1002\/ejp.1679","article-title":"Evidence-based treatment recommendations for neck and low back pain across Europe: a systematic review of guidelines","volume":"25","author":"Corp","year":"2021","journal-title":"Eur J Pain"},{"key":"2026051413304001900_ooag035-B2","doi-asserted-by":"publisher","first-page":"e028633","DOI":"10.1136\/bmjopen-2018-028633corr1","article-title":"Observational retrospective study of the association of initial healthcare provider for new-onset low back pain with early and long-term opioid use","volume":"9","author":"Kazis","year":"2019","journal-title":"BMJ Open"},{"key":"2026051413304001900_ooag035-B3","first-page":"1409","article-title":"Longitudinal care patterns and utilization among patients with new-onset neck pain by initial provider specialty","volume":"20","author":"Fenton","year":"2025","journal-title":"Spine (Phila Pa 1976)"},{"key":"2026051413304001900_ooag035-B4","doi-asserted-by":"crossref","first-page":"e180105","DOI":"10.1001\/jamanetworkopen.2018.0105","article-title":"Effect of usual medical care plus chiropractic care vs usual medical care alone on pain and disability among US service members with low back pain: a comparative effectiveness clinical trial","volume":"1","author":"Goertz","year":"2018","journal-title":"JAMA Netw Open"},{"key":"2026051413304001900_ooag035-B5","first-page":"E61","article-title":"Visit frequency and outcomes for patients using ongoing chiropractic care for chronic low-back and neck pain: an observational longitudinal study","volume":"24","author":"Herman","year":"2021","journal-title":"Pain Physician"},{"key":"2026051413304001900_ooag035-B6","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s12998-023-00507-y","article-title":"Clinical indicators for recommending continued care to patients with neck pain in chiropractic practice: a cohort study","volume":"31","author":"Myhrvold","year":"2023","journal-title":"Chiropr Man Therap"},{"key":"2026051413304001900_ooag035-B7","doi-asserted-by":"crossref","first-page":"e0000785","DOI":"10.1371\/journal.pdig.0000785","article-title":"Unsupervised machine learning identifies opioid taper reversal patterns in a longitudinal cohort (2008-2018)","volume":"4","author":"Ray","year":"2025","journal-title":"PLOS Digit Health"},{"key":"2026051413304001900_ooag035-B8","first-page":"496","author":"Doyle","year":"2008"},{"key":"2026051413304001900_ooag035-B9","doi-asserted-by":"crossref","first-page":"4896","DOI":"10.1038\/s41598-017-05275-3","article-title":"Spectral clustering using Nystr\u00f6m approximation for the accurate identification of cancer molecular subtypes","volume":"7","author":"Shi","year":"2017","journal-title":"Sci Rep"},{"key":"2026051413304001900_ooag035-B10","doi-asserted-by":"publisher","author":"Chander","DOI":"10.1016\/B978-0-12-820601-0.00002-1"},{"key":"2026051413304001900_ooag035-B11","doi-asserted-by":"crossref","first-page":"842306","DOI":"10.3389\/frai.2022.842306","article-title":"Phenotype clustering in health care: a narrative review for clinicians","volume":"5","author":"Loftus","year":"2022","journal-title":"Front Artif Intell"},{"key":"2026051413304001900_ooag035-B12","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1080\/10618600.2014.938812","article-title":"Learning interactions via hierarchical group-lasso regularization","volume":"24","author":"Lim","year":"2015","journal-title":"J Comput Graph Stat"},{"key":"2026051413304001900_ooag035-B13","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1186\/s12913-023-10423-9","article-title":"Improving hospital quality risk-adjustment models using interactions identified by hierarchical group lasso regularisation","volume":"23","author":"Ray","year":"2023","journal-title":"BMC Health Serv Res"},{"key":"2026051413304001900_ooag035-B14","volume-title":"The Elements of Statistical Learning. Springer Series in Statistics","author":"Friedman","year":"2009"},{"key":"2026051413304001900_ooag035-B15","doi-asserted-by":"crossref","first-page":"13892","DOI":"10.1073\/pnas.1518285112","article-title":"Why significant variables aren\u2019t automatically good predictors","volume":"112","author":"Lo","year":"2015","journal-title":"Proc Natl Acad Sci"},{"key":"2026051413304001900_ooag035-B16","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.tins.2019.02.001","article-title":"Exploration, inference, and prediction in neuroscience and biomedicine","volume":"42","author":"Bzdok","year":"2019","journal-title":"Trends Neurosci"},{"key":"2026051413304001900_ooag035-B17","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1080\/00031305.2016.1154108","article-title":"The ASA statement on p-values: context, process, and purpose","volume":"70","author":"Wasserstein","year":"2016","journal-title":"Am Stat"},{"key":"2026051413304001900_ooag035-B18","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1111\/1467-9574.00084","article-title":"Extracting information from mega-panels and high-frequency data","volume":"52","author":"Granger","year":"1998","journal-title":"Stat Neerl"},{"key":"2026051413304001900_ooag035-B19","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1287\/isre.2013.0480","article-title":"Too big to fail: large samples and the p-value problem","volume":"24","author":"Lin","year":"2013","journal-title":"Inform Syst Res"},{"key":"2026051413304001900_ooag035-B20","first-page":"1721","author":"Caruana","year":"2015"},{"key":"2026051413304001900_ooag035-B21","volume-title":"Optum Labs and Optum Labs Data Warehouse (OLDW) Descriptions and Citation","author":"Optum Labs","year":"2023"},{"key":"2026051413304001900_ooag035-B22","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1097\/MLR.0000000000000735","article-title":"Identifying increased risk of readmission and in-hospital mortality using hospital administrative data: the AHRQ Elixhauser Comorbidity Index","volume":"55","author":"Moore","year":"2017","journal-title":"Med Care"},{"key":"2026051413304001900_ooag035-B23","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1093\/bioinformatics\/btz704","article-title":"Spectrum: fast density-aware spectral clustering for single and multi-omic data","volume":"36","author":"John","year":"2019","journal-title":"Bioinformatics"},{"key":"2026051413304001900_ooag035-B24","author":"John","year":"2025"},{"key":"2026051413304001900_ooag035-B25","volume-title":"Spectral Graph Theory. CBMS Regional Conference Series in Mathematics","author":"Chung","year":"1997","edition":"2nd ed."},{"key":"2026051413304001900_ooag035-B26","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/0097-3165(78)90067-5","article-title":"Matrix tree theorems","volume":"24","author":"Chaiken","year":"1978","journal-title":"J Comb Theory Ser A"},{"key":"2026051413304001900_ooag035-B27","author":"Meila"},{"key":"2026051413304001900_ooag035-B28","volume-title":"Advances in Neural Information Processing Systems","author":"Cristianini"},{"key":"2026051413304001900_ooag035-B29","volume-title":"On Spectral Clustering: analysis and an Algorithm"},{"key":"2026051413304001900_ooag035-B30","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","article-title":"A tutorial on spectral clustering","volume":"17","author":"von Luxburg","year":"2007","journal-title":"Stat Comput"},{"key":"2026051413304001900_ooag035-B31","first-page":"1","article-title":"Path-based spectral clustering: guarantees, robustness to outliers, and fast algorithms","volume":"21","author":"Little","year":"2020","journal-title":"J Mach Learn Res"},{"key":"2026051413304001900_ooag035-B32","first-page":"doi: 10.1109\/ICCV.1999.790354","volume":"2","author":"Weiss","year":"1999"},{"key":"2026051413304001900_ooag035-B33","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1214\/11-EJS651","article-title":"Spectral clustering based on local linear approximations","volume":"5","author":"Arias-Castro","year":"2011","journal-title":"Electron J Stat"},{"key":"2026051413304001900_ooag035-B34","doi-asserted-by":"publisher","first-page":"497\u2013515","DOI":"10.1145\/990308.990313","article-title":"On clusterings-good, bad and spectral","author":"Kannan"},{"key":"2026051413304001900_ooag035-B35","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/S0167-9473(02)00179-2","article-title":"Latent class models for classification","volume":"41","author":"Vermunt","year":"2003","journal-title":"Comput Stat Data Anal"},{"key":"2026051413304001900_ooag035-B36","author":"Orduz","year":"2020"},{"key":"2026051413304001900_ooag035-B37","first-page":"1820","article-title":"Discussion of coauthorship and citation networks for statisticians","volume":"10","author":"Song","year":"2016","journal-title":"Ann Appl Stat"},{"key":"2026051413304001900_ooag035-B38","first-page":"297","article-title":"Generalized additive models","volume":"1","author":"Hastie","year":"1986","journal-title":"Stat Sci"},{"key":"2026051413304001900_ooag035-B39","doi-asserted-by":"crossref","DOI":"10.1201\/9781315370279","volume-title":"Generalized Additive Models: An Introduction with R","author":"Wood","year":"2017","edition":"2nd ed."},{"key":"2026051413304001900_ooag035-B40","doi-asserted-by":"crossref","first-page":"370","DOI":"10.2307\/2344614","article-title":"Generalized linear models","volume":"135","author":"Nelder","year":"1972","journal-title":"J R Stat Soc Ser A (Gen)"},{"key":"2026051413304001900_ooag035-B41","author":"InterpretML","year":"2023"},{"key":"2026051413304001900_ooag035-B42","first-page":"4132","author":"Wang","year":"2022"},{"key":"2026051413304001900_ooag035-B43","author":"InterpretML","year":"2023"},{"key":"2026051413304001900_ooag035-B44","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1080\/00401706.1991.10484873","article-title":"Prediction error and its estimation for subset-selected models","volume":"33","author":"Roecker","year":"1991","journal-title":"Technometrics"},{"key":"2026051413304001900_ooag035-B45","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1080\/00031305.1990.10475722","article-title":"The impact of model selection on inference in linear regression","volume":"44","author":"Hurvich","year":"1990","journal-title":"Am Stat"},{"key":"2026051413304001900_ooag035-B46","first-page":"49","article-title":"Inflation of R2 in best subset regression","volume":"22","author":"Rencher","year":"1980","journal-title":"Technometrics"},{"key":"2026051413304001900_ooag035-B47","author":"Hastie","year":"2017"},{"key":"2026051413304001900_ooag035-B48","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1214\/15-AOS1388","article-title":"Best subset selection via a modern optimization lens","volume":"44","author":"Bertsimas","year":"2016","journal-title":"Ann Stat"},{"key":"2026051413304001900_ooag035-B49","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 Soc Ser B (Methodol)"},{"key":"2026051413304001900_ooag035-B50","first-page":"129","volume-title":"Encyclopedia of Statistical Sciences","author":"Hoerl","year":"1988"},{"key":"2026051413304001900_ooag035-B51","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J R Stat Soc Ser B (Stat Methodol)"},{"key":"2026051413304001900_ooag035-B52","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1214\/13-AOS1096","article-title":"A lasso for hierarchical interactions","volume":"41","author":"Bien","year":"2013","journal-title":"Ann Stat"},{"key":"2026051413304001900_ooag035-B53","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1093\/jamia\/ocw161","article-title":"Synergistic drug combinations from electronic health records and gene expression","volume":"24","author":"Low","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"2026051413304001900_ooag035-B54","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.1186\/s12940-017-0277-6","article-title":"A systematic comparison of statistical methods to detect interactions in exposome-health associations","volume":"16","author":"Barrera-G\u00f3mez","year":"2017","journal-title":"Environ Health"},{"key":"2026051413304001900_ooag035-B55","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.energy.2015.02.008","article-title":"Identifying key variables and interactions in statistical models of building energy consumption using regularization","volume":"83","author":"Hsu","year":"2015","journal-title":"Energy"},{"key":"2026051413304001900_ooag035-B56","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1111\/j.1467-9868.2005.00532.x","article-title":"Model selection and estimation in regression with grouped variables","volume":"68","author":"Yuan","year":"2006","journal-title":"J R Stat Soc Ser B"},{"key":"2026051413304001900_ooag035-B57","author":"Lim","year":"2025"},{"key":"2026051413304001900_ooag035-B58","volume-title":"Handbook of Regression Analysis","author":"Chatterjee","year":"2013"},{"key":"2026051413304001900_ooag035-B59","doi-asserted-by":"crossref","first-page":"467","DOI":"10.2519\/jospt.2011.3637","article-title":"Factors associated with care seeking from physicians, physical therapists, or chiropractors by persons with spinal pain: a population-based study","volume":"41","author":"Chevan","year":"2011","journal-title":"J Orthopaedic Sports Phys Therapy"},{"key":"2026051413304001900_ooag035-B60","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmpt.2015.10.006","article-title":"Clinical practice guideline: chiropractic care for low back pain","volume":"39","author":"Globe","year":"2016","journal-title":"J Manipulative Physiol Ther"},{"key":"2026051413304001900_ooag035-B61","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.jmpt.2017.10.001","article-title":"Chiropractic integrated care pathway for low back pain in veterans: results of a Delphi consensus process","volume":"41","author":"Lisi","year":"2018","journal-title":"J Manipulative Physiol Therapeut"},{"key":"2026051413304001900_ooag035-B62","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1080\/00031305.2018.1518269","article-title":"Limitations of P-values and R-squared for stepwise regression building: a fairness demonstration in health policy risk adjustment","volume":"73","author":"Rose","year":"2019","journal-title":"Am Stat"},{"key":"2026051413304001900_ooag035-B63","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1080\/01621459.1984.10478083","article-title":"Cross-validation of regression models","volume":"79","author":"Picard","year":"1984","journal-title":"J Am Stat Assoc"},{"key":"2026051413304001900_ooag035-B64","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1007\/978-0-387-39940-9_565","volume-title":"Encyclopedia of Database Systems","author":"Refaeilzadeh","year":"2009"},{"key":"2026051413304001900_ooag035-B65","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1080\/00401706.1977.10489581","article-title":"Validation of regression models: methods and examples","volume":"19","author":"Snee","year":"1977","journal-title":"Technometrics"},{"key":"2026051413304001900_ooag035-B66","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1080\/00031305.1990.10475704","article-title":"Data splitting","volume":"44","author":"Picard","year":"1990","journal-title":"Am Stat"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/3\/ooag035\/68287325\/ooag035.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/3\/ooag035\/68287325\/ooag035.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:30:52Z","timestamp":1778779852000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooag035\/8678313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":66,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,5]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooag035","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,5]]},"article-number":"ooag035"}}