Osteoarthritis of the Temporomandibular Joint can be diagnosed earlier using biomarkers and machine learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
15 05 2020
15 05 2020
Historique:
received:
25
11
2019
accepted:
21
04
2020
entrez:
17
5
2020
pubmed:
18
5
2020
medline:
15
12
2020
Statut:
epublish
Résumé
After chronic low back pain, Temporomandibular Joint (TMJ) disorders are the second most common musculoskeletal condition affecting 5 to 12% of the population, with an annual health cost estimated at $4 billion. Chronic disability in TMJ osteoarthritis (OA) increases with aging, and the main goal is to diagnosis before morphological degeneration occurs. Here, we address this challenge using advanced data science to capture, process and analyze 52 clinical, biological and high-resolution CBCT (radiomics) markers from TMJ OA patients and controls. We tested the diagnostic performance of four machine learning models: Logistic Regression, Random Forest, LightGBM, XGBoost. Headaches, Range of mouth opening without pain, Energy, Haralick Correlation, Entropy and interactions of TGF-β1 in Saliva and Headaches, VE-cadherin in Serum and Angiogenin in Saliva, VE-cadherin in Saliva and Headaches, PA1 in Saliva and Headaches, PA1 in Saliva and Range of mouth opening without pain; Gender and Muscle Soreness; Short Run Low Grey Level Emphasis and Headaches, Inverse Difference Moment and Trabecular Separation accurately diagnose early stages of this clinical condition. Our results show the XGBoost + LightGBM model with these features and interactions achieves the accuracy of 0.823, AUC 0.870, and F1-score 0.823 to diagnose the TMJ OA status. Thus, we expect to boost future studies into osteoarthritis patient-specific therapeutic interventions, and thereby improve the health of articular joints.
Identifiants
pubmed: 32415284
doi: 10.1038/s41598-020-64942-0
pii: 10.1038/s41598-020-64942-0
pmc: PMC7228972
doi:
Substances chimiques
Biomarkers
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
8012Subventions
Organisme : NIDCR NIH HHS
ID : R01 DE024450
Pays : United States
Références
Vos, T. et al. Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990–2016: A systematic analysis for the Global Burden of Disease Study 2016. Lancet 390, 1211–1259 (2017).
doi: 10.1016/S0140-6736(17)32154-2
March, L. & Cross, M. Epidemiology and risk factors for osteoarthritis. Available at, https://www.uptodate.com/contents/epidemiology-and-risk-factors-for-osteoarthritis .
Herrero-Beaumont, G., Roman-Blas, J. A., Castañeda, S. & Jimenez, S. A. Primary Osteoarthritis No Longer Primary: Three Subsets with Distinct Etiological, Clinical, and Therapeutic Characteristics. Semin. Arthritis Rheum. 39, 71–80 (2009).
pubmed: 19589561
doi: 10.1016/j.semarthrit.2009.03.006
pmcid: 19589561
Wang, X. D., Zhang, J. N., Gan, Y. H. & Zhou, Y. H. Current Understanding of Pathogenesis and Treatment of TMJ Osteoarthritis. J. Dent. Res. 94, 666–673 (2015).
pubmed: 25744069
doi: 10.1177/0022034515574770
pmcid: 25744069
National Institute of Dental and Craniofacial Research. Facial Pain. Available at, https://www.nidcr.nih.gov/research/data-statistics/facial-pain .
Embree, M. et al. Role of Subchondral Bone during Early-stage Experimental TMJ Osteoarthritis. J. Dent. Res. 90, 1331–1338 (2011).
pubmed: 21917603
pmcid: 3188464
doi: 10.1177/0022034511421930
Wang, X. D., Zhang, J. N., Gan, Y. H. & Zhou, Y. H. Current understanding of pathogenesis and treatment of TMJ osteoarthritis. J. Dent. Res. 94, 666–73 (2015).
pubmed: 25744069
doi: 10.1177/0022034515574770
pmcid: 25744069
Jiao, K. et al. Subchondral bone loss following orthodontically induced cartilage degradation in the mandibular condyles of rats. Bone 48, 362–371 (2011).
pubmed: 20850574
doi: 10.1016/j.bone.2010.09.010
pmcid: 20850574
Nieminen, M. T., Casula, V., Nevalainen, M. T. & Saarakkala, S. Osteoarthritis year in review 2018: imaging. Osteoarthr. Cartil. 27, 401–411 (2019).
pubmed: 30590194
doi: 10.1016/j.joca.2018.12.009
pmcid: 30590194
Ebrahim, F. H. et al. Accuracy of biomarkers obtained from cone beam computed tomography in assessing the internal trabecular structure of the mandibular condyle. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. 124, 588–599 (2017).
pubmed: 29055644
pmcid: 5701846
doi: 10.1016/j.oooo.2017.08.013
Pauwels, R., Araki, K., Siewerdsen, J. H. & Thongvigitmanee, S. S. Technical aspects of dental CBCT: State of the art. Dentomaxillofacial Radiol. 44, 1–20 (2015).
Paniagua, B. et al. Validation of CBCT for the computation of textural biomarkers. Proc. SPIE–the Int. Soc. Opt. Eng. 9417, 1–15 (2015).
Panmekiate, S., Ngonphloy, N., Charoenkarn, T., Faruangsaeng, T. & Pauwels, R. Comparison of mandibular bone microarchitecture between micro-CT and CBCT images. Dentomaxillofacial Radiol. 44 (2015).
Buch, K. et al. Quantitative assessment of variation in CT parameters on texture features: Pilot study using a nonanatomic phantom. Am. J. Neuroradiol. 38, 981–985 (2017).
pubmed: 28341714
doi: 10.3174/ajnr.A5139
pmcid: 28341714
Schiffman, E. et al. Diagnostic Criteria for Temporomandibular Disorders (DC/TMD) for Clinical and Research Applications: Recommendations of the International RDC/TMD Consortium Network* and Orofacial Pain Special Interest Group†. Journal of Oral & Facial Pain and Headache 28, 6–27 (2014).
doi: 10.11607/jop.1151
Ahmad, M. et al. Research diagnostic criteria for temporomandibular disorders (RDC/TMD): development of image analysis criteria and examiner reliability for image analysis. Oral Surgery, Oral Med. Oral Pathol. Oral Radiol. Endodontology 107, 844–860 (2009).
doi: 10.1016/j.tripleo.2009.02.023
Li, G. et al. Subchondral bone in osteoarthritis: insight into risk factors and microstructural changes. Arthritis Res. Ther. 15, 223 (2013).
pubmed: 24321104
pmcid: 4061721
doi: 10.1186/ar4405
Chen, J. et al. Altered functional loading causes differential effects in the subchondral bone and condylar cartilage in the temporomandibular joint from young mice. Osteoarthr. Cartil. 17, 354–61 (2009).
pubmed: 18789726
doi: 10.1016/j.joca.2008.05.021
pmcid: 18789726
Brandt, K. D. & Radin, E. L. & Dieppe, P. a. Not a Cartilage Disease. Ann. Rheum. Dis. 65, 1261–1265 (2006).
pubmed: 16973787
pmcid: 1798332
doi: 10.1136/ard.2006.058347
Hunter, D. J. & Bierma-Zeinstra, S. Osteoarthritis. Lancet 393, 1745–1759 (2019).
pubmed: 31034380
doi: 10.1016/S0140-6736(19)30417-9
pmcid: 31034380
Ghahramani, Z. Probabilistic machine learning and artificial intelligence. Nature 521, 452–459 (2015).
pubmed: 26017444
doi: 10.1038/nature14541
pmcid: 26017444
Raghupathi, W. & Raghupathi, V. Big data analytics in healthcare: promise and potential. Heal. Inf. Sci. Syst. 2, 3 (2014).
doi: 10.1186/2047-2501-2-3
Jamshidi, A., Pelletier, J. P. & Martel-Pelletier, J. Machine-learning-based patient-specific prediction models for knee osteoarthritis. Nat. Rev. Rheumatol. 15, 49–60 (2019).
pubmed: 30523334
doi: 10.1038/s41584-018-0130-5
pmcid: 30523334
O’Connor, J. P. B. et al. Imaging biomarker roadmap for cancer studies. Nat. Rev. Clin. Oncol. 14, 169–186 (2017).
pubmed: 27725679
doi: 10.1038/nrclinonc.2016.162
pmcid: 27725679
Johnson, V. L., Giuffre, B. M. & Hunter, D. J. Osteoarthritis: What does imaging tell us about its etiology? Semin. Musculoskelet. Radiol. 16, 410–418 (2012).
pubmed: 23212876
doi: 10.1055/s-0032-1329894
pmcid: 23212876
Brahim, A. et al. A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative. Comput. Med. Imaging Graph. 73, 11–18 (2019).
pubmed: 30784984
doi: 10.1016/j.compmedimag.2019.01.007
pmcid: 30784984
Lazzarini, N. et al. A machine learning approach for the identification of new biomarkers for knee osteoarthritis development in overweight and obese women. Osteoarthr. Cartil. 25, 2014–2021 (2017).
pubmed: 28899843
doi: 10.1016/j.joca.2017.09.001
pmcid: 28899843
Heard, B. J. et al. A computational method to differentiate normal individuals, osteoarthritis and rheumatoid arthritis patients using serum biomarkers. J. R. Soc. Interface 11 (2014).
Donoghue, C. R. Analysis of MRI for Knee Osteoarthritis using Machine Learning. Dep. Comput. Imp. Coll. London 199 (2013).
Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 785–794 (ACM, 2016).
Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 3146–3154 (2017).
Miotto, R., Wang, F., Wang, S., Jiang, X. & Dudley, J. T. Deep learning for healthcare: Review, opportunities and challenges. Brief. Bioinform. 19, 1236–1246 (2017).
pmcid: 6455466
doi: 10.1093/bib/bbx044
Tiulpin, A., Thevenot, J., Rahtu, E., Lehenkari, P. & Saarakkala, S. Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach. Sci. Rep. 8, 1727 (2018).
pubmed: 29379060
pmcid: 5789045
doi: 10.1038/s41598-018-20132-7
Chaudhari, A. S. et al. Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers. J. Magn. Reson. Imaging 51, 768–779 (2020).
pubmed: 31313397
doi: 10.1002/jmri.26872
pmcid: 31313397
Shoukri, B. et al. Minimally Invasive Approach for Diagnosing TMJ Osteoarthritis. J. Dent. Res. 98, 1103–1111 (2019).
pubmed: 31340134
doi: 10.1177/0022034519865187
pmcid: 31340134
de Dumast, P. et al. SVA: Shape variation analyzer. Proc. SPIE–the Int. Soc. Opt. Eng. 10578, 89 (2018).
Nelson, A. E. et al. A machine learning approach to knee osteoarthritis phenotyping: data from the FNIH Biomarkers Consortium. Osteoarthr. Cartil. 27, 994–1001 (2019).
pubmed: 31002938
doi: 10.1016/j.joca.2018.12.027
Bianchi, J. et al. Software comparison to analyze bone radiomics from high resolution CBCT scans of mandibular condyles. Dentomaxillofac. Radiol. 20190049, https://doi.org/10.1259/dmfr.20190049 (2019)
Cevidanes, L. H. S. et al. 3D osteoarthritic changes in TMJ condylar morphology correlates with specific systemic and local biomarkers of disease. Osteoarthr. Cartil. 22, 1657–67 (2014).
pubmed: 25278075
pmcid: 4185299
doi: 10.1016/j.joca.2014.06.014
Michoud, L. et al. A web-based system for statistical shape analysis in temporomandibular joint osteoarthritis. Proc. SPIE–the Int. Soc. Opt. Eng. 10953 (2019).
Pieper, S., Halle, M. & Kikinis, R. 3D Slicer. In 2004 2nd IEEE international symposium on biomedical imaging: nano to macro (IEEE Cat No. 04EX821) 632–635 (IEEE, 2004).
Mirabel, C. DatabaseInteractor. Available at, https://www.slicer.org/wiki/Documentation/Nightly/Modules/DatabaseInteractor .
Goldring, M. B. & Goldring, S. R. Articular cartilage and subchondral bone in the pathogenesis of osteoarthritis. Ann. N. Y. Acad. Sci. 1192, 230–7 (2010).
pubmed: 20392241
doi: 10.1111/j.1749-6632.2009.05240.x
pmcid: 20392241
Pfaffe, T., Cooper-White, J., Beyerlein, P., Kostner, K. & Punyadeera, C. Diagnostic potential of saliva: Current state and future applications. Clin. Chem. 57, 675–687 (2011).
pubmed: 21383043
doi: 10.1373/clinchem.2010.153767
pmcid: 21383043
Alyass, A., Turcotte, M. & Meyre, D. From big data analysis to personalized medicine for all: challenges and opportunities. 1–12, https://doi.org/10.1186/s12920-015-0108-y (2015).
Marx, V. Biology: The big challenges of big data. Nature 498, 255–60 (2013).
pubmed: 23765498
doi: 10.1038/498255a
pmcid: 23765498
Sejdić, E. Medicine: Adapt current tools for handling big data. Nature 507, 306 (2014).
pubmed: 24646986
doi: 10.1038/507306a
pmcid: 24646986
Gillies, R. J., Kinahan, P. E. & Hricak, H. Radiomics: Images Are More than Pictures, They Are Data. Radiology, https://doi.org/10.1148/radiol.2015151169 (2016).
Ciancaglini, R. & Radaelli, G. The relationship between headache and symptoms of temporomandibular disorder in the general population. 29 (2001).
Güzel, I., Taşdemir, N., Celik, Y. & Çelik, Y. Evaluation of serum transforming growth factor β1 and C-reactive protein levels in migraine patients. Neurol. Neurochir. Pol. 47, 357–362 (2013).
pubmed: 23986426
doi: 10.5114/ninp.2013.36760
pmcid: 23986426
Bruno, P. P., Carpino, F., Carpino, G. & Zicari, A. An overview on immune system and migraine. Eur. Rev. Med. Pharmacol. Sci. 11, 245 (2007).
pubmed: 17876959
pmcid: 17876959
Jiao, K. et al. Overexpressed TGF-β in subchondral bone leads to mandibular condyle degradation. J. Dent. Res. 93, 140–147 (2014).
pubmed: 24309371
doi: 10.1177/0022034513513034
pmcid: 24309371
Ishizaki, K. et al. Increased Plasma Transforming Growth Factor-β1 in Migraine. Headache J. Head Face Pain 45, 1224–1228 (2005).
doi: 10.1111/j.1526-4610.2005.00246.x
Ghosh, P. & Cheras, P. A. Vascular mechanisms in osteoarthritis. Best Pract. Res. Clin. Rheumatol. 15, 693–709 (2001).
pubmed: 11812016
doi: 10.1053/berh.2001.0188
pmcid: 11812016
Rando, C. & Waldron, T. TMJ osteoarthritis: A new approach to diagnosis. Am. J. Phys. Anthropol. 148, 45–53 (2012).
pubmed: 22371124
doi: 10.1002/ajpa.22039
pmcid: 22371124
Sarlani, E., Garrett, P. H., Grace, E. G. & Greenspan, J. D. Temporal summation of pain characterizes women but not men with temporomandibular disorders. J. Orofac. Pain 21, 309–17 (2007).
pubmed: 18018992
pmcid: 5086416
Bajaj, P. P. et al. Osteoarthritis and its association with muscle hyperalgesia: an experimental controlled study. Pain 93, 107–114 (2001).
pubmed: 11427321
doi: 10.1016/S0304-3959(01)00300-1
pmcid: 11427321
Aksehirli, Ö., Aydin, D., Ankarali, H. & Sezgin, M. Knee Osteoarthritis Diagnosis Using Support Vector Machine and Probabilistic Neural Network. Int. J. Comput. Sci. Issues 10, 283–291 (2013).
Slade, G. D. et al. Cytokine biomarkers and chronic pain: association of genes, transcription, and circulating proteins with temporomandibular disorders and widespread palpation tenderness. Pain 152, 2802–12 (2011).
pubmed: 22000099
pmcid: 3221458
doi: 10.1016/j.pain.2011.09.005
Kellesarian, S. V. et al. Cytokine profile in the synovial fluid of patients with temporomandibular joint disorders: A systematic review. Cytokine 77, 98–106 (2016).
pubmed: 26556103
doi: 10.1016/j.cyto.2015.11.005
pmcid: 26556103
Ahmed, U. et al. Biomarkers of early stage osteoarthritis, rheumatoid arthritis and musculoskeletal health. Sci. Rep. 5, 1–7 (2015).
Swan, A. L., Mobasheri, A., Allaway, D. & Liddell, S. Application of Machine Learning to Proteomics Data: Classification and Biomarker Identification in Postgenomics Biology. 17 (2013).
Deng, L. et al. PDRLGB: Precise DNA-binding residue prediction using a light gradient boosting machine. BMC Bioinformatics 19 (2018).
Vanneste, S., Song, J. J. & De Ridder, D. Thalamocortical dysrhythmia detected by machine learning. Nat. Commun. 9 (2018).
Ashinsky, B. G. et al. Machine learning classification of OARSI-scored human articular cartilage using magnetic resonance imaging. Osteoarthr. Cartil. 23, 1704–12 (2015).
pubmed: 26067517
pmcid: 4577440
doi: 10.1016/j.joca.2015.05.028
Vandenbroucke, J. P. et al. Strengthening the Reporting of Observational Studies in Epidemiology (STROBE). Epidemiology 18, 805–835 (2009).
doi: 10.1097/EDE.0b013e3181577511
Kaczor-Urbanowicz, K. E. et al. Salivary exRNA biomarkers to detect gingivitis and monitor disease regression. J. Clin. Periodontol. 45, 806–817 (2018).
pubmed: 29779262
pmcid: 6023773
doi: 10.1111/jcpe.12930
Jiang, W. et al. Protein expression profiling by antibody array analysis with use of dried blood spot samples on filter paper. J. Immunol. Methods 403, 79–86 (2014).
pubmed: 24287424
doi: 10.1016/j.jim.2013.11.016
pmcid: 24287424
Huang, R. et al. A biotin label-based antibody array for high-content profiling of protein expression. Cancer Genomics and Proteomics 7, 129–141 (2010).
pubmed: 20551245
pmcid: 20551245
Storey, J. D. The positive false discovery rate: a Bayesian interpretation and the q-value. Ann. Stat. 31, 2013–2035 (2003).
doi: 10.1214/aos/1074290335
Robin, X. et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 12, 77 (2011).
pubmed: 21414208
pmcid: 3068975
doi: 10.1186/1471-2105-12-77
DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44, 837–845 (1988).
pubmed: 3203132
doi: 10.2307/2531595
pmcid: 3203132
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
Lipton, Z. C., Elkan, C. & Naryanaswamy, B. Optimal thresholding of classifiers to maximize F1 measure. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases 225–239 (Springer, 2014).