Prognostic subgroups of chronic pain patients using latent variable mixture modeling within a supervised machine learning framework.
Latent variable mixture modeling
Machine learning
Pain classification
Pain prognosis
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
31 May 2024
31 May 2024
Historique:
received:
22
06
2023
accepted:
17
05
2024
medline:
1
6
2024
pubmed:
1
6
2024
entrez:
31
5
2024
Statut:
epublish
Résumé
The present study combined a supervised machine learning framework with an unsupervised method, finite mixture modeling, to identify prognostically meaningful subgroups of diverse chronic pain patients undergoing interdisciplinary treatment. Questionnaire data collected at pre-treatment and 1-year follow up from 11,995 patients from the Swedish Quality Registry for Pain Rehabilitation were used. Indicators measuring pain characteristics, psychological aspects, and social functioning and general health status were used to form subgroups, and pain interference at follow-up was used for the selection and the performance evaluation of models. A nested cross-validation procedure was used for determining the number of classes (inner cross-validation) and the prediction accuracy of the selected model among unseen cases (outer cross-validation). A four-class solution was identified as the optimal model. Identified subgroups were separable on indicators, predictive of long-term outcomes, and related to background characteristics. Results are discussed in relation to previous clustering attempts of patients with diverse chronic pain conditions. Our analytical approach, as the first to combine mixture modeling with supervised, targeted learning, provides a promising framework that can be further extended and optimized for improving accurate prognosis in pain treatment and identifying clinically meaningful subgroups among chronic pain patients.
Identifiants
pubmed: 38822075
doi: 10.1038/s41598-024-62542-w
pii: 10.1038/s41598-024-62542-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
12543Subventions
Organisme : AFA Försäkring
ID : DNR 190054
Organisme : Vetenskapsrådet
ID : 2015-02512
Organisme : Forskningsrådet om Hälsa, Arbetsliv och Välfärd
ID : 2017-00177
Informations de copyright
© 2024. The Author(s).
Références
Hamburg, M. A. & Collins, F. S. The path to personalized medicine. N. Engl. J. Med. 363, 301–304. https://doi.org/10.1056/NEJMp1006304 (2010).
doi: 10.1056/NEJMp1006304
pubmed: 20551152
Edwards, R. R. et al. Patient phenotyping in clinical trials of chronic pain treatments: IMMPACT recommendations. PAIN Rep. 6, e896. https://doi.org/10.1097/pr9.0000000000000896 (2021).
doi: 10.1097/pr9.0000000000000896
Breivik, H., Collett, B., Ventafridda, V., Cohen, R. & Gallacher, D. Survey of chronic pain in Europe: Prevalence, impact on daily life, and treatment. Eur. J. Pain 10, 287–287. https://doi.org/10.1016/j.ejpain.2005.06.009 (2006).
doi: 10.1016/j.ejpain.2005.06.009
pubmed: 16095934
Gatchel, R. J., Peng, Y. B., Peters, M. L., Fuchs, P. N. & Turk, D. C. The biopsychosocial approach to chronic pain: Scientific advances and future directions. Psychol. Bull. 133, 581–624. https://doi.org/10.1037/0033-2909.133.4.581 (2007).
doi: 10.1037/0033-2909.133.4.581
pubmed: 17592957
Turk, D. C. The potential of treatment matching for subgroups of patients with chronic pain: Lumping versus splitting. Clin. J. Pain 21, 44–55. https://doi.org/10.1097/00002508-200501000-00006 (2005).
doi: 10.1097/00002508-200501000-00006
pubmed: 15599131
Boersma, K. & Linton, S. J. Screening to identify patients at risk: Profiles of psychological risk factors for early intervention. Clin. J. Pain 21, 38–43. https://doi.org/10.1097/00002508-200501000-00005 (2005).
doi: 10.1097/00002508-200501000-00005
pubmed: 15599130
Viniol, A. et al. Chronic low back pain patient groups in primary care–A cross sectional cluster analysis. BMC Musculoskelet Disord. 14, 294. https://doi.org/10.1186/1471-2474-14-294 (2013).
doi: 10.1186/1471-2474-14-294
pubmed: 24131707
pmcid: 3852748
Maixner, W., Fillingim, R. B., Williams, D. A., Smith, S. B. & Slade, G. D. Overlapping chronic pain conditions: Implications for diagnosis and classification. J. Pain 17, T93–T107. https://doi.org/10.1016/j.jpain.2016.06.002 (2016).
doi: 10.1016/j.jpain.2016.06.002
pubmed: 27586833
pmcid: 6193199
Linton, S. J. & Shaw, W. S. Impact of psychological factors in the experience of pain. Phys. Ther. 91, 700–711. https://doi.org/10.2522/ptj.20100330 (2011).
doi: 10.2522/ptj.20100330
pubmed: 21451097
Gerdle, B. et al. Who benefits from multimodal rehabilitation—An exploration of pain, psychological distress, and life impacts in over 35,000 chronic pain patients identified in the Swedish Quality Registry for Pain Rehabilitation. J. Pain Res. 12, 891–908. https://doi.org/10.2147/JPR.S190003 (2019).
doi: 10.2147/JPR.S190003
pubmed: 30881099
pmcid: 6411315
Gerdle, B., Molander, P., Stenberg, G., Stålnacke, B.-M. & Enthoven, P. Weak outcome predictors of multimodal rehabilitation at one-year follow-up in patients with chronic pain—a practice based evidence study from two SQRP centres. BMC Musculoskelet Disord. 17, 490. https://doi.org/10.1186/s12891-016-1346-7 (2016).
doi: 10.1186/s12891-016-1346-7
pubmed: 27887616
pmcid: 5124266
Khoury, M. J. & Ioannidis, J. P. A. Big data meets public health. Science 346, 1054–1055. https://doi.org/10.1126/science.aaa2709 (2014).
doi: 10.1126/science.aaa2709
pubmed: 25430753
pmcid: 4684636
Yim, Y.-R. et al. Identifying fibromyalgia subgroups using cluster analysis: Relationships with clinical variables. Eur. J. Pain 21, 374–384. https://doi.org/10.1002/ejp.935 (2017).
doi: 10.1002/ejp.935
pubmed: 27633925
Davis, F. et al. Characterizing classes of fibromyalgia within the continuum of central sensitization syndrome. J. Pain Res. 11, 2551–2560. https://doi.org/10.2147/JPR.S147199 (2018).
doi: 10.2147/JPR.S147199
pubmed: 30425566
pmcid: 6205129
Ringqvist, Å., Dragioti, E., Björk, M., Larsson, B. & Gerdle, B. Moderate and stable pain reductions as a result of interdisciplinary pain rehabilitation—A cohort study from the Swedish Quality Registry for Pain Rehabilitation (SQRP). J. Clin. Med. 8, 905. https://doi.org/10.3390/jcm8060905 (2019).
doi: 10.3390/jcm8060905
pubmed: 31238588
pmcid: 6617026
Obbarius, A. et al. A step towards a better understanding of pain phenotypes: Latent class analysis in chronic pain patients receiving multimodal inpatient treatment. J. Pain Res. 13, 1023–1038. https://doi.org/10.2147/jpr.s223092 (2020).
doi: 10.2147/jpr.s223092
pubmed: 32523372
pmcid: 7234963
Bäckryd, E., Persson, E. B., Larsson, A. I., Fischer, M. R. & Gerdle, B. Chronic pain patients can be classified into four groups: Clustering-based discriminant analysis of psychometric data from 4665 patients referred to a multidisciplinary pain centre (a SQRP study). PLoS ONE 13, e0192623. https://doi.org/10.1371/journal.pone.0192623 (2018).
doi: 10.1371/journal.pone.0192623
pubmed: 29420607
pmcid: 5805304
Turk, D. C. & Okifuji, A. Psychological factors in chronic pain: Evolution and revolution. J. Consult. Clin. Psychol. 70, 678–690. https://doi.org/10.1037/0022-006X.70.3.678 (2002).
doi: 10.1037/0022-006X.70.3.678
pubmed: 12090376
Pincus, T. & McCracken, L. M. Psychological factors and treatment opportunities in low back pain. Best Pract. Res. Clin. Rheumatol. 27, 625–635. https://doi.org/10.1016/j.berh.2013.09.010 (2013).
doi: 10.1016/j.berh.2013.09.010
pubmed: 24315144
Turk, D. C. & Rudy, T. E. Toward an empirically derived taxonomy of chronic pain patients: Integration of psychological assessment data. J. Consult. Clin. Psychol. 56, 233–238. https://doi.org/10.1037/0022-006X.56.2.233 (1988).
doi: 10.1037/0022-006X.56.2.233
pubmed: 3372831
Day, M. A., Ehde, D. M. & Jensen, M. P. Psychosocial pain management moderation: The limit, activate, and enhance model. J. Pain 16, 947–960. https://doi.org/10.1016/j.jpain.2015.07.003 (2015).
doi: 10.1016/j.jpain.2015.07.003
pubmed: 26351009
Clark, S. L. et al. Models and strategies for factor mixture analysis: An example concerning the structure underlying psychological disorders. Struct. Equ. Model. 20, 681–703. https://doi.org/10.1080/10705511.2013.824786 (2013).
doi: 10.1080/10705511.2013.824786
Lubke, G. H. & Luningham, J. Fitting latent variable mixture models. Behav. Res. Ther. 98, 91–102. https://doi.org/10.1016/j.brat.2017.04.003 (2017).
doi: 10.1016/j.brat.2017.04.003
pubmed: 28460845
pmcid: 5776694
Lipton, R. B. et al. Improving the classification of migraine subtypes: An empirical approach based on factor mixture models in the American Migraine Prevalence and Prevention (AMPP) study. J. Headache Pain 54, 830–849. https://doi.org/10.1111/head.12332 (2014).
doi: 10.1111/head.12332
Muthén, B. Statistical and substantive checking in growth mixture modeling: Comment on Bauer and Curran (2003). Psychol. Methods 8, 369–377. https://doi.org/10.1037/1082-989X.8.3.369 (2003).
doi: 10.1037/1082-989X.8.3.369
pubmed: 14596497
Jo, B. et al. Targeted use of growth mixture modeling: A learning perspective. Stat. Med. 36, 671–686. https://doi.org/10.1002/sim.7152 (2017).
doi: 10.1002/sim.7152
pubmed: 27804177
Dworkin, R. H. et al. Core outcome measures for chronic pain clinical trials: IMMPACT recommendations. Pain 113, 9–19. https://doi.org/10.1016/j.pain.2004.09.012 (2005).
doi: 10.1016/j.pain.2004.09.012
pubmed: 15621359
Kaiser, U. et al. Developing a core outcome domain set to assessing effectiveness of interdisciplinary multimodal pain therapy: The VAPAIN consensus statement on core outcome domains. Pain 159, 673–683. https://doi.org/10.1097/j.pain.0000000000001129 (2018).
doi: 10.1097/j.pain.0000000000001129
pubmed: 29300277
Kerns, R. D., Turk, D. C. & Rudy, T. E. The west haven-Yale multidimensional pain inventory (WHYMPI). Pain 23, 345–356. https://doi.org/10.1016/0304-3959(85)90004-1 (1985).
doi: 10.1016/0304-3959(85)90004-1
pubmed: 4088697
Nyberg, V. E., Novo, M. & Sjölund, B. H. Do multidimensional pain inventory scale score changes indicate risk of receiving sick leave benefits 1 year after a pain rehabilitation programme?. Disabil. Rehabil. 33, 1548–1556. https://doi.org/10.3109/09638288.2010.533815 (2011).
doi: 10.3109/09638288.2010.533815
pubmed: 21110725
Gerdle, B., Fischer, M. R., Cervin, M. & Ringqvist, Å. Spreading of pain in patients with chronic pain is related to pain duration and clinical presentation and weakly associated with outcomes of interdisciplinary pain rehabilitation: A cohort study from the Swedish Quality Registry for Pain Rehabilitation (SQRP). J. Pain Res. 14, 173–187. https://doi.org/10.2147/JPR.S288638 (2021).
doi: 10.2147/JPR.S288638
pubmed: 33542650
pmcid: 7850976
Zigmond, A. S. & Snaith, R. P. The hospital anxiety and depression scale. Acta Psychiatr. Scand. 67, 361–370. https://doi.org/10.1111/j.1600-0447.1983.tb09716.x (1983).
doi: 10.1111/j.1600-0447.1983.tb09716.x
pubmed: 6880820
Lisspers, J., Nygren, A. & Söderman, E. Hospital anxiety and depression scale (HAD): Some psychometric data for a Swedish sample. Acta Psychiatr. Scand. 96, 281–286. https://doi.org/10.1111/j.1600-0447.1997.tb10164.x (1997).
doi: 10.1111/j.1600-0447.1997.tb10164.x
pubmed: 9350957
Vlaeyen, J. W. S., Crombez, G. & Linton, S. J. The fear-avoidance model of pain. Pain 157, 1588–1589. https://doi.org/10.1097/j.pain.0000000000000574 (2016).
doi: 10.1097/j.pain.0000000000000574
pubmed: 27428892
Vlaeyen, J. W. S., Kole-Snijders, A. M. J., Boeren, R. G. B. & van Eek, H. Fear of movement/(re)injury in chronic low back pain and its relation to behavioral performance. Pain 62, 363–372. https://doi.org/10.1016/0304-3959(94)00279-N (1995).
doi: 10.1016/0304-3959(94)00279-N
pubmed: 8657437
Lundberg, M. K. E., Styf, J. & Carlsson, S. G. A psychometric evaluation of the Tampa Scale for Kinesiophobia—from a physiotherapeutic perspective. Physiother. Theory Pract. 20, 121–133. https://doi.org/10.1080/09593980490453002 (2004).
doi: 10.1080/09593980490453002
Ware, J. E. J. & Sherbourne, C. D. The MOS 36-ltem short-form health survey (SF-36): I. Conceptual framework and item selection. Med. Care 30, 473–483 (1992).
doi: 10.1097/00005650-199206000-00002
pubmed: 1593914
Sullivan, M., Karlsson, J. & Ware, J. E. The Swedish SF-36 health survey—I. Evaluation of data quality, scaling assumptions, reliability and construct validity across general populations in Sweden. Soc. Sci. Med. 41, 1349–1358. https://doi.org/10.1016/0277-9536(95)00125-Q (1995).
doi: 10.1016/0277-9536(95)00125-Q
pubmed: 8560302
Eccles, J. A. & Davies, K. A. The challenges of chronic pain and fatigue. Clin. Med. 21, 19–27. https://doi.org/10.7861/clinmed.2020-1009 (2021).
doi: 10.7861/clinmed.2020-1009
Ware, J. E., Snow, K. K., Kosinski, M. & Gandek, B. SF-36 health survey: Manual and interpretation guide (Quality Metric, 1993).
The EuroQol Group. EuroQol-a new facility for the measurement of health-related quality of life. Health Policy 16, 199–208. https://doi.org/10.1016/0168-8510(90)90421-9
Taylor, A. M. et al. Assessment of physical function and participation in chronic pain clinical trials: IMMPACT/OMERACT recommendations. Pain 157, 1836–1850. https://doi.org/10.1097/j.pain.0000000000000577 (2016).
doi: 10.1097/j.pain.0000000000000577
pubmed: 27058676
pmcid: 7453823
Turk, D. C. et al. Identifying important outcome domains for chronic pain clinical trials: An IMMPACT survey of people with pain. Pain 137, 276–285. https://doi.org/10.1016/j.pain.2007.09.002 (2008).
doi: 10.1016/j.pain.2007.09.002
pubmed: 17937976
McLachlan, G. & Peel, D. Finite mixture models (Wiley, 2000).
doi: 10.1002/0471721182
Muthén, B. & Shedden, K. Finite mixture modeling with mixture outcomes using the EM algorithm. Biometrics 55, 463–469. https://doi.org/10.1111/j.0006-341X.1999.00463.x (1999).
doi: 10.1111/j.0006-341X.1999.00463.x
pubmed: 11318201
Muthén, B. O. Beyond SEM: General latent variable modeling. Behaviormetrika 29, 81–117. https://doi.org/10.2333/bhmk.29.81 (2002).
doi: 10.2333/bhmk.29.81
Poldrack, R. A., Huckins, G. & Varoquaux, G. Establishment of best practices for evidence for prediction: A review. JAMA Psychiatry 77, 534–540. https://doi.org/10.1001/jamapsychiatry.2019.3671 (2020).
doi: 10.1001/jamapsychiatry.2019.3671
pubmed: 31774490
pmcid: 7250718
Dankers, F. J. W. M., Traverso, A., Wee, L. & van Kuijk, S. M. J. Prediction modeling methodology. In Fundamentals of clinical data science (eds Kubben, P. et al.) 101–120 (Springer, 2019). https://doi.org/10.1007/978-3-319-99713-1_8 .
doi: 10.1007/978-3-319-99713-1_8
Rodriguez, J. D., Perez, A. & Lozano, J. A. Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans. Pattern Anal. Mach. Intell. 32, 569–575. https://doi.org/10.1109/TPAMI.2009.187 (2010).
doi: 10.1109/TPAMI.2009.187
pubmed: 20075479
Hosseini, M. et al. I tried a bunch of things: The dangers of unexpected overfitting in classification of brain data. Neurosci. Biobehav. Rev. 119, 456–467. https://doi.org/10.1016/j.neubiorev.2020.09.036 (2020).
doi: 10.1016/j.neubiorev.2020.09.036
pubmed: 33035522
Stone, M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. Ser. B Methodol. 36, 111–133. https://doi.org/10.1111/j.2517-6161.1974.tb00994.x (1974).
doi: 10.1111/j.2517-6161.1974.tb00994.x
Cawley, G. C. & Talbot, N. L. C. On over-fitting in model selection and subsequent selection bias in performance evaluation. JMLR 11, 2079–2107 (2010).
Hallquist, M. N. & Wiley, J. F. MplusAutomation: An R package for facilitating large-scale latent variable analyses in Mplus. Struct. Equ. Model. Multidiscip. J. 25, 621–638. https://doi.org/10.1080/10705511.2017.1402334 (2018).
doi: 10.1080/10705511.2017.1402334
Muthén, L. K. & Muthén, B. O. Mplus user's guide. 8 edn, (Muthén & Muthén, 1998–2017).
Kuhn, M. Building predictive models in R using the caret package. J. Stat. Softw. 28, 1–26. https://doi.org/10.18637/jss.v028.i05 (2008).
doi: 10.18637/jss.v028.i05
Asparouhov, T. & Muthén, B. Auxiliary variables in mixture modeling: Three-step approaches using Mplus. Struct. Equ. Model. 21, 329–341. https://doi.org/10.1080/10705511.2014.915181 (2014).
doi: 10.1080/10705511.2014.915181
Santana, A. N., de Santana, C. N. & Montoya, P. Chronic pain diagnosis using machine learning, questionnaires, and QST: A sensitivity experiment. Diagnostics 10, 958. https://doi.org/10.3390/diagnostics10110958 (2020).
doi: 10.3390/diagnostics10110958
pubmed: 33212774
pmcid: 7697204
Lumley, M. A. et al. Emotional awareness and other emotional processes: Implications for the assessment and treatment of chronic pain. Pain Manag. 11, 325–332. https://doi.org/10.2217/pmt-2020-0081 (2021).
doi: 10.2217/pmt-2020-0081
pubmed: 33533272
pmcid: 7923252
Boersma, K. et al. Efficacy of a transdiagnostic emotion–focused exposure treatment for chronic pain patients with comorbid anxiety and depression: A randomized controlled trial. Pain 160, 1708–1718. https://doi.org/10.1097/j.pain.0000000000001575 (2019).
doi: 10.1097/j.pain.0000000000001575
pubmed: 31335641
pmcid: 6687409
Jamison, R. N., Rudy, T. E., Penzien, D. B. & Mosley, T. H. J. Cognitive-behavioral classifications of chronic pain: Replication and extension of empirically derived patient profiles. Pain 57, 277–292. https://doi.org/10.1016/0304-3959(94)90003-5 (1994).
doi: 10.1016/0304-3959(94)90003-5
pubmed: 7936707
Wilson, H. D., Robinson, J. P. & Turk, D. C. Toward the identification of symptom patterns in people with fibromyalgia. Arthritis Care Res. 61, 527–534. https://doi.org/10.1002/art.24163 (2009).
doi: 10.1002/art.24163
Wilson, M. W., Richards, J. S., Klapow, J. C., DeVivo, M. J. & Greene, P. Cluster analysis and chronic pain: An empirical classification of pain subgroups in a spinal cord injury sample. Rehabil. Psychol. 50, 381–388. https://doi.org/10.1037/0090-5550.50.4.381 (2005).
doi: 10.1037/0090-5550.50.4.381
pubmed: 26339107
pmcid: 4556427
Muthén, B. & Asparouhov, T. Growth mixture modeling with non-normal distributions. Stat. Med. 34, 1041–1058. https://doi.org/10.1002/sim.6388 (2015).
doi: 10.1002/sim.6388
pubmed: 25504555
DeGood, D. E. & Kiernan, B. Perception of fault in patients with chronic pain. Pain 64, 153–159. https://doi.org/10.1016/0304-3959(95)00090-9 (1996).
doi: 10.1016/0304-3959(95)00090-9
pubmed: 8867258