Artificial intelligence-based prognostic modeling in temporomandibular disorders and chronic orofacial pain: a critical conceptual review

This conceptual review (ⅰ) analyzes the outcomes predicted, data modalities, modeling approaches, validation strategies, and reporting quality of existing artificial intelligence (AI)-driven prognostic models in temporomandibular disorders (TMD) and chronic orofacial pain (OFP); (ⅱ) identifies enduring methodological and ethical constraints that hinder clinical translation; and (ⅲ) proposes a pragmatic research framework to guide the responsible development of clinically relevant prognostic tools for TMD and OFP. The review covers peer-reviewed and other relevant publications from the previous decade, emphasizing AI or machine-learning (ML) based models for prognosis, outcome prediction, or trajectory modeling in TMD and OFP populations. Established paradigms, including the Transparent Reporting of a multivariable prediction model for individual Prognosis Or Diagnosis plus Artificial Intelligence extension (TRIPOD+ AI) and the Prediction model Risk Of Bias Assessment Tool (PROBAST), were used to assess the literature. Methodologies remain highly inconsistent, and current literature lacks the volume and rigor required for clinical translation. Most AI research has concentrated on diagnostic classification rather than prognostic modeling. Small sample sizes, short follow-up, single-center datasets, omission of psychosocial factors, and a general lack of external validation hamper the few prognostic studies that exist. Most model outputs are neither clinically actionable nor suitable for direct use in treatment decisions, limiting their value for clinicians and their potential impact on patient outcomes. Research applying AI to forecast TMD and OFP remains in its early stages. Without a prognosis-first research design, longitudinal data integration, inclusion of biopsychosocial predictors, and clinically significant outcome objectives, existing models are unlikely to influence clinical practice. Clear research objectives, reporting criteria, and ethical norms must be established before AI-based prognostic models can be confidently adopted in TMD and OFP clinical practice. Future objectives comprise establishing multicenter longitudinal cohorts, conducting trajectory-based modeling, employing federated learning for external validation, and initiating prospective clinical trials to demonstrate clear clinical benefit.

Temporomandibular disorders; Chronic orofacial pain; Artificial intelligence; Machine learning; Prognostic modeling; Biopsychosocial model

[1] Schiffman E, Ohrbach R, Truelove E, Look J, Anderson G, Goulet JP, 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. 2014; 28: 6–27.

[2] Ohrbach R, Dworkin SF. The evolution of TMD diagnosis: past, present, future. Journal of Dental Research. 2016; 95: 1093–1101.

[3] Zieliński G. Quo vadis temporomandibular disorders? By 2050, the global prevalence of TMD may approach 44%. Journal of Clinical Medicine. 2025; 14: 4414.

[4] Slade GD, Ohrbach R, Greenspan JD, Fillingim RB, Bair E, Sanders AE, et al. Painful temporomandibular disorder: decade of discovery from OPPERA studies. Journal of Dental Research. 2016; 95: 1084–1092.

[5] Ohrbach R, Fillingim RB, Mulkey F, Gonzalez Y, Gordon S, Gremillion H, et al. Clinical findings and pain symptoms as potential risk factors for chronic TMD: descriptive data and empirically identified domains from the OPPERA case-control study. The Journal of Pain. 2011; 12: T27–T45.

[6] Greene CS. Managing the care of patients with temporomandibular disorders: a new guideline for care. The Journal of the American Dental Association. 2010; 141: 1086–1088.

[7] List T, Axelsson S. Management of TMD: evidence from systematic reviews and meta-analyses. Journal of Oral Rehabilitation. 2010; 37: 430–451.

[8] Slade GD, Bair E, Greenspan JD, Dubner R, Fillingim RB, Diatchenko L, et al. Signs and symptoms of first-onset TMD and sociodemographic predictors of its development: the OPPERA prospective cohort study. The Journal of Pain. 2013; 14: T20–T32.e1–3.

[9] Sharma S, Breckons M, Brönnimann Lambelet B, Chung JW, List T, Lobbezoo F, et al. Challenges in the clinical implementation of a biopsychosocial model for assessment and management of orofacial pain. Journal of Oral Rehabilitation. 2020; 47: 87–100.

[10] Fillingim RB, Slade GD, Greenspan JD, Dubner R, Maixner W, Bair E, et al. Long-term changes in biopsychosocial characteristics related to temporomandibular disorder: findings from the OPPERA study. Pain. 2018; 159: 2403–2413.

[11] Gatchel RJ, Peng YB, Peters ML, Fuchs PN, Turk DC. The biopsychosocial approach to chronic pain: scientific advances and future directions. Psychological Bulletin. 2007; 133: 581–624.

[12] Herrero Babiloni A, Exposto FG, Peck CM, Lindgren BR, Martel MO, Lenglet C, et al. Temporomandibular disorders cases with high-impact pain are more likely to experience short-term pain fluctuations. Scientific Reports. 2022; 12: 1657.

[13] van Smeden M, Reitsma JB, Riley RD, Collins GS, Moons KG. Clinical prediction models: diagnosis versus prognosis. Journal of Clinical Epidemiology. 2021; 132: 142–145.

[14] Collins GS, Dhiman P, Ma J, Schlussel MM, Archer L, Van Calster B, et al. Evaluation of clinical prediction models (part 1): from development to external validation. The BMJ. 2024; 384: e074819.

[15] Slade GD, Diatchenko L, Bhalang K, Sigurdsson A, Fillingim RB, Belfer I, et al. Influence of psychological factors on risk of temporomandibular disorders. Journal of Dental Research. 2007; 86: 1120–1125.

[16] Fillingim RB, Ohrbach R, Greenspan JD, Knott C, Diatchenko L, Dubner R, et al. Psychological factors associated with development of TMD: the OPPERA prospective cohort study. The Journal of Pain. 2013; 14: T75–T90.

[17] Steyerberg EW. Clinical prediction models: a practical approach to development, validation, and updating. 1st edn. Springer: New York. 2009.

[18] Bzdok D, Meyer-Lindenberg A. Machine learning for precision psychiatry: opportunities and challenges. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging. 2018; 3: 223–230.

[19] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine. 2019; 25: 44–56.

[20] Cui Y, Kang F, Li X, Shi X, Zhang H, Zhu X. Predicting temporomandibular disorders in adults using interpretable machine learning methods: a model development and validation study. Frontiers in Bioengineering and Biotechnology. 2024; 12: 1459903.

[21] Yıldız NT, Kocaman H, Yıldırım H, Canlı M. An investigation of machine learning algorithms for prediction of temporomandibular disorders by using clinical parameters. Medicine. 2024; 103: e39912.

[22] Rajkomar A, Dean J, Kohane I. Machine learning in medicine. The New England Journal of Medicine. 2019; 380: 1347–1358.

[23] Adams MCB, Bowness JS, Nelson AM, Hurley RW, Narouze S. A roadmap for artificial intelligence in pain medicine: current status, opportunities, and requirements. Current Opinion in Anesthesiology. 2025; 38: 680–688.

[24] Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges. Journal of Dental Research. 2020; 99: 769–774.

[25] Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nature Medicine. 2019; 25: 24–29.

[26] Jha N, Lee KS, Kim YJ. Diagnosis of temporomandibular disorders using artificial intelligence technologies: a systematic review and meta-analysis. PLOS ONE. 2022; 17: e0272715.

[27] Farook TH, Jamayet NB, Abdullah JY, Alam MK. Machine learning and intelligent diagnostics in dental and orofacial pain management: a systematic review. Pain Research and Management. 2021; 2021: 6659133.

[28] Wolff RF, Moons KGM, Riley RD, Whiting PF, Westwood M, Collins GS, et al. PROBAST: a tool to assess the risk of bias and applicability of prediction model studies. Annals of Internal Medicine. 2019; 170: 51–58.

[29] Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. The BMJ. 2024; 385: e078378.

[30] Hemingway H, Croft P, Perel P, Hayden JA, Abrams K, Timmis A, et al. Prognosis research strategy (PROGRESS) 1: a framework for researching clinical outcomes. The BMJ. 2013; 346: e5595.

[31] Dahlhamer J, Lucas J, Zelaya C, Nahin R, Mackey S, DeBar L, et al. Prevalence of chronic pain and high-impact chronic pain among adults—United States, 2016. Morbidity and Mortality Weekly Report. 2018; 67: 1001–1006.

[32] Antel R, Whitelaw S, Gore G, Ingelmo P. Moving towards the use of artificial intelligence in pain management. European Journal of Pain. 2025; 29: e4748.

[33] Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nature Medicine. 2019; 25: 1337–1340.

[34] Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Annals of Internal Medicine. 2015; 162: 55–63.

[35] Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019; 366: 447–453.

[36] Munn Z, Pollock D, Khalil H, Alexander L, Mclnerney P, Godfrey CM, et al. What are scoping reviews? Providing a formal definition of scoping reviews as a type of evidence synthesis. JBI Evidence Synthesis. 2022; 20: 950–952.

[37] Grant MJ, Booth A. A typology of reviews: an analysis of 14 review types and associated methodologies. Health Information & Libraries Journal. 2009; 26: 91–108.

[38] Moons KGM, Royston P, Vergouwe Y, Grobbee DE, Altman DG. Prognosis and prognostic research: what, why, and how? The BMJ. 2009; 338: b375.

[39] Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Medicine. 2019; 17: 195.

[40] Green BN, Johnson CD, Adams A. Writing narrative literature reviews for peer-reviewed journals: secrets of the trade. Journal of Chiropractic Medicine. 2006; 5: 101–117.

[41] Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nature Medicine. 2025; 31: 60–69.

[42] Popay J, Roberts H, Sowden A, Petticrew M, Arai L, Rodgers M, et al. Guidance on the conduct of narrative synthesis in systematic reviews: a product from the ESRC methods programme. ESRC Methods Programme: Lancaster. 2006.

[43] Bramer WM, Rethlefsen ML, Kleijnen J, Franco OH. Optimal database combinations for literature searches in systematic reviews: a prospective exploratory study. Systematic Reviews. 2017; 6: 245.

[44] Greenhalgh T, Peacock R. Effectiveness and efficiency of search methods in systematic reviews of complex evidence: audit of primary sources. The BMJ. 2005; 331: 1064–1065.

[45] Riley RD, Hayden JA, Steyerberg EW, Moons KGM, Abrams K, Kyzas PA, et al. Prognosis Research Strategy (PROGRESS) 2: prognostic factor research. PLOS Medicine. 2013; 10: e1001380.

[46] Manek M, Maita I, Bezerra Silva DF, Pita de Melo D, Major PW, Jaremko JL, et al. Temporomandibular joint assessment in MRI images using artificial intelligence tools: where are we now? A systematic review. Dentomaxillofacial Radiology. 2025; 54: 1–11.

[47] Egermark I, Magnusson T, Carlsson GE. A 20-year follow-up of signs and symptoms of temporomandibular disorders and malocclusions in subjects with and without orthodontic treatment in childhood. The Angle Orthodontist. 2003; 73: 109–115.

[48] Bair E, Ohrbach R, Fillingim RB, Greenspan JD, Dubner R, Diatchenko L, et al. Multivariable modeling of phenotypic risk factors for first-onset TMD: the OPPERA prospective cohort study. The Journal of Pain. 2013; 14: T102–T115.

[49] Slade GD, Bair E, By K, Mulkey F, Baraian C, Rothwell R, et al. Study methods, recruitment, socio-demographic findings, and demographic representativeness in the OPPERA study. The Journal of Pain. 2011; 12: T12–T26.

[50] Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Medical Research Methodology. 2018; 18: 24.

[51] Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. npj Digital Medicine. 2018; 1: 18.

[52] Durham J, Newton-John T, Zakrzewska JM. Temporomandibular disorders. The BMJ. 2015; 350: h1154.

[53] Ribeiro MT, Singh S, Guestrin C. “Why Should I Trust You?”: explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM): New York. 2016.

[54] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS). Curran Associates: Red Hook. 2017.

[55] Lipton ZC. The mythos of model interpretability. Communications of the ACM. 2018; 61: 36–43.

[56] Steyerberg EW, Harrell FE III. Prediction models need appropriate internal, internal-external, and external validation. Journal of Clinical Epidemiology. 2016; 69: 245–247.

[57] Lötsch J, Ultsch A. Machine learning in pain research. Pain. 2018; 159: 623–630.

[58] Tagliaferri SD, Angelova M, Zhao X, Owen PJ, Miller CT, Wilkin T, et al. Artificial intelligence to improve back pain outcomes and lessons learnt from clinical classification approaches: three systematic reviews. npj Digital Medicine. 2020; 3: 93.

[59] Rokhshad R, Mohammad-Rahimi H, Sohrabniya F, Jafari B, Shobeiri P, Tsolakis IA, et al. Deep learning for temporomandibular joint arthropathies: a systematic review and meta-analysis. Journal of Oral Rehabilitation. 2024; 51: 1632–1644.

[60] Bair E, Gaynor S, Slade GD, Ohrbach R, Fillingim RB, Greenspan JD, et al. Identification of clusters of individuals relevant to temporomandibular disorders and other chronic pain conditions: the OPPERA study. Pain. 2016; 157: 1266–1278.

[61] Al Turkestani N, Li T, Bianchi J, Gurgel M, Prieto J, Shah H, et al. A comprehensive patient-specific prediction model for temporomandibular joint osteoarthritis progression. Proceedings of the National Academy of Sciences of the United States of America. 2024; 121: e2306132121.

[62] Lee YH, Jeon S, Kim DH, Auh QS, Lee JH, Noh YK. Clinical and MRI markers for acute vs chronic temporomandibular disorders using a machine learning and deep neural networks. Communications Medicine. 2025; 5: 401.

[63] Xu C, Wu X, Li S, Zhong Q, Ye C, Pan J, et al. An interpretable machine learning model based on MRI features for predicting pain severity in temporomandibular disorders. Journal of Oral Rehabilitation. 2026; 53: 609–620.

[64] Lee KS, Kwak HJ, Oh JM, Jha N, Kim YJ, Kim W, et al. Automated detection of TMJ osteoarthritis based on artificial intelligence. Journal of Dental Research. 2020; 99: 1363–1367.

[65] Choi E, Kim D, Lee JY, Park HK. Artificial intelligence in detecting temporomandibular joint osteoarthritis on orthopantomogram. Scientific Reports. 2021; 11: 10246.

[66] Jung W, Lee KE, Suh BJ, Seok H, Lee DW. Deep learning for osteoarthritis classification in temporomandibular joint. Oral Diseases. 2023; 29: 1050–1059.

[67] Manfredini D, Guarda-Nardini L, Winocur E, Piccotti F, Ahlberg J, Lobbezoo F. Research diagnostic criteria for temporomandibular disorders: a systematic review of axis I epidemiologic findings. Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology. 2011; 112: 453–462.

[68] Wynants L, Van Calster B, Collins GS, Riley RD, Heinze G, Schuit E, et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. The BMJ. 2020; 369: m1328.

[69] Vabalas A, Gowen E, Poliakoff E, Casson AJ. Machine learning algorithm validation with a limited sample size. PLOS ONE. 2019; 14: e0224365.

[70] Collins GS, Moons KGM. Reporting of artificial intelligence prediction models. The Lancet. 2019; 393: 1577–1579.

[71] Riley RD, Ensor J, Snell KIE, Debray TPA, Altman DG, Moons KGM, et al. External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis. The BMJ. 2016; 353: i3140.

[72] Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, et al. The future of digital health with federated learning. npj Digital Medicine. 2020; 3: 119.

[73] Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Scientific Reports. 2020; 10: 12598.

[74] Shortliffe EH, Sepúlveda MJ. Clinical decision support in the era of artificial intelligence. JAMA. 2018; 320: 2199–2200.

[75] Char DS, Shah NH, Magnus D. Implementing machine learning in health care—addressing ethical challenges. The New England Journal of Medicine. 2018; 378: 981–983.

[76] Price WN II, Gerke S, Cohen IG. Potential liability for physicians using artificial intelligence. JAMA. 2019; 322: 1765–1766.

[77] Koleck TA, Dreisbach C, Bourne PE, Bakken S. Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review. Journal of the American Medical Informatics Association. 2019; 26: 364–379.