A NEW JAW, A NEW FACE: HOW AI IS REVOLUTIONIZING CORRECTIVE SURGERY

• Dr. Althea R. Nkomo

  Department of Biomedical Engineering, National Institute of Medical Technology, Pretoria, South Africa

  Author

For decades, the world of medicine has been steadily embracing technology, and now Artificial Intelligence (AI) is making significant waves. In the highly specialized field of orthognathic surgery—the complex art of correcting jaw and facial deformities—AI is opening up new possibilities for precision, predictability, and personalized care. This review explores this exciting and rapidly evolving role. Following a thorough review of scientific literature from major databases, we analyzed and mapped AI's current impact. Our findings show that AI is already being applied across the entire surgical journey, from diagnosis and deciding on surgery to designing the surgical plan, creating realistic simulations of the future face, and providing objective feedback on the outcome. Furthermore, AI models are being used to forecast the risk of complications with remarkable accuracy. While hurdles like data needs and system transparency remain, AI is no longer a futuristic concept in this field. It is a transformative technology that offers surgeons powerful new ways to plan treatments, predict outcomes, and work more efficiently, making these life-changing procedures safer and more successful for every patient.

[1] V. Kaul, S. Enslin, and S. A. Gross, “History of Artificial Intel-ligence in Medicine,” Gastrointestinal Endoscopy 92, no. 4(2020): 807–812, https://doi.org/10.1016/j.gie.2020.06.040.

[2] C. Xu, J. Wu, and S. Ma, eds., “A Visual Processing System forFacial Prediction,” in International Conference on Advances inVisual Information Systems (Springer, 1999), https://doi.org/10.1007/3-540-48762-X_91.

[3] N. Lampen, D. Kim, X. Fang, et al., “Deep Learning for Biome-chanical Modeling of Facial Tissue Deformation in Orthog-nathic Surgical Planning,” International Journal of ComputerAssisted Radiology and Surgery 17, no. 5 (2022): 945–952,https://doi.org/10.1007/s11548-022-02596-1.

[4] M. Chowdhury and A. W. Sadek, “Advantages and Limitationsof Artificial Intelligence,” Artificial Intelligence Applications toCritical Transportation Issues 6, no. 3 (2012): 360–375.

[5] J. A. Nichols, H. W. Herbert Chan, and M. A. Baker, “MachineLearning: Applications of Artificial Intelligence to Imagingand Diagnosis,” Biophysical Reviews 11, no. 1 (2019): 111–118, https://doi.org/10.1007/s12551-018-0449-9.

[6] H. Mohammad-Rahimi, M. Nadimi, M. H. Rohban,E. Shamsoddin, V. Y. Lee, and S. R. Motamedian, “MachineLearning and Orthodontics, Current Trends and the FutureOpportunities: A Scoping Review,” American Journal ofOrthodontics and Dentofacial Orthopedics 160, no. 2 (2021):170–192.e4, https://doi.org/10.1016/j.ajodo.2021.02.013.

[7] F. Jiang, Y. Jiang, H. Zhi, et al., “Artificial Intelligence inHealthcare: Past, Present and Future,” Stroke and VascularNeurology 2, no. 4 (2017): 230–243, https://doi.org/10.1136/svn-2017-000101.

[8] J. H. Thrall, X. Li, Q. Li, et al., “Artificial Intelligence andMachine Learning in Radiology: Opportunities, Challenges,Pitfalls, and Criteria for Success,” Journal of the American Col-lege of Radiology 15, no. 3 (2018): 504–508, https://doi.org/10.1016/j.jacr.2017.12.026.

[9] S. B. Khanagar, A. Al-Ehaideb, S. Vishwanathaiah, et al.,“Scope and Performance of Artificial Intelligence Technologyin Orthodontic Diagnosis, Treatment Planning, and ClinicalDecision-Making-A Systematic Review,” Journal of Dental Sci-ences 16, no. 1 (2021): 482–492, https://doi.org/10.1016/j.jds.2020.05.022.

[10] A. Holzinger, G. Langs, H. Denk, K. Zatloukal, and H. Müller,“Causability and Explainability of Artificial Intelligence in22 BioMed Research International Medicine,” Discovery 9, no. 4 (2019): e 1312, https://doi.org/10.1002/widm.1312.

[11] Y.-H. Kim, J.-B. Park, M.-S. Chang, J.-J. Ryu, W. H. Lim, andS.-K. Jung, “Influence of the Depth of the Convolutional Neu-ral Networks on an Artificial Intelligence Model for Diagnosisof Orthognathic Surgery,” Journal of Personalized Medicine 11,no. 5 (2021): 356, https://doi.org/10.3390/jpm11050356.

[12] D. Xiao, C. Lian, H. Deng, et al., “Estimating Reference BonyShape Models for Orthognathic Surgical Planning Using 3DPoint-Cloud Deep Learning,” IEEE Journal of Biomedicaland Health Informatics 25, no. 8 (2021): 2958–2966, https://doi.org/10.1109/JBHI.2021.3054494.

[13] T. Shan, F. Tay, and L. Gu, “Application of Artificial Intelli-gence in Dentistry,” Journal of Dental Research 100, no. 3(2021): 232–244, https://doi.org/10.1177/0022034520969115.

[14] R. Y. Choi, A. S. Coyner, J. Kalpathy-Cramer, M. F. Chiang,and J. P. Campbell, “Introduction to Machine Learning, Neu-ral Networks, and Deep Learning,” Translational Vision Sci-ence & Technology 9, no. 2 (2020): 14-.

[15] S. Fa, W. Samek, and J. Krois, “Artificial Intelligence in Dentistry:Chances and Challenges,” Journal of Dental Research 99, no. 7(2020): 769–774, https://doi.org/10.1177/0022034520915714.

[16] V. Nasteski, “An Overview of the Supervised Machine Learn-ing Methods,” Horizons b 4 (2017): 51–62, https://doi.org/10.20544/HORIZONS.B.04.1.17.P05.

[17] P. Khosravi-Kamrani, X. Qiao, G. Zanardi, C. A. Wiesen,G. Slade, and S. A. Frazier-Bowers, “A Machine LearningApproach to Determine the Prognosis of Patients With ClassIII Malocclusion,” American Journal of Orthodontics and Den-tofacial Orthopedics 161, no. 1 (2022): e1–e11, https://doi.org/10.1016/j.ajodo.2021.06.012.

[18] J. Lim, C. Tanikawa, M. Kogo, and T. Yamashiro, “Determina-tion of Prognostic Factors for Orthognathic Surgery inChildren With Cleft Lip and/or Palate,” Orthodontics & Cra-niofacial Research 24, no. S2 (2021): 153–162, https://doi.org/10.1111/ocr.12477.

[19] C.-Y. J. Peng, K. L. Lee, and G. M. Ingersoll, “An Introductionto Logistic Regression Analysis and Reporting,” The Journal ofEducational Research 96, no. 1 (2002): 3–14, https://doi.org/10.1080/00220670209598786.

[20] C. Cortes and V. Vapnik, “Support-Vector Networks,”Machine Learning 20, no. 3 (1995): 273–297, https://doi.org/10.1007/BF00994018.

[21] P. G. Knoops, A. Papaioannou, A. Borghi, et al., “A MachineLearning Framework for Automated Diagnosis andComputer-Assisted Planning in Plastic and ReconstructiveSurgery,” Scientific Reports 9, no. 1 (2019): 1–12, https://doi.org/10.1038/s41598-019-49506-1.

[22] R. Stehrer, L. Hingsammer, C. Staudigl, et al., “Machine LearningBased Prediction of Perioperative Blood Loss in OrthognathicSurgery,” Journal of Cranio-Maxillofacial Surgery 47, no. 11(2019): 1676–1681, https://doi.org/10.1016/j.jcms.2019.08.005.

[23] G. Lin, P.-J. Kim, S.-H. Baek, H.-G. Kim, S.-W. Kim, andJ.-H. Chung, “Early Prediction of the Need for OrthognathicSurgery in Patients With Repaired Unilateral Cleft Lip and PalateUsing Machine Learning and Longitudinal Lateral CephalometricAnalysis Data,” Journal of Craniofacial Surgery 32, no. 2 (2021):616–620, https://doi.org/10.1097/SCS.0000000000006943.

[24] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature521, no. 7553 (2015): 436–444, https://doi.org/10.1038/nature14539.

[25] X. Qiu, W. Han, L. Dai, et al., “Assessment of an ArtificialIntelligence Mandibular Osteotomy Design System: A Retro-spective Study,” Aesthetic Plastic Surgery 46, no. 3 (2022):1303–1313, https://doi.org/10.1007/s00266-021-02698-2.

[26] H.-I. Choi, S.-K. Jung, S.-H. Baek, et al., “Artificial IntelligentModel With Neural Network Machine Learning for the Diag-nosis of Orthognathic Surgery,” Journal of Craniofacial Sur-gery. 30, no. 7 (2019): 1986–1989, https://doi.org/10.1097/SCS.0000000000005650.

[27] D. Moher, L. Shamseer, M. Clarke, et al., “Preferred ReportingItems for Systematic Review and Meta-Analysis Protocols(PRISMA-P) 2015 Statement,” Systematic Reviews 4, no. 1(2015): 1–9, https://doi.org/10.1186/2046-4053-4-1.

[28] M. Peters, C. Godfrey, P. McInerney, C. Soares, H. Khalil, andD. Parker, “Methodology for JBI Scoping Reviews,” in TheJoanna Briggs Institute Reviewers Manual 2015 (Joanna BriggsInstitute, 2015), 1–24.

[29] H. Mohammad-Rahimi, S. R. Motamedian, M. H. Rohban,et al., “Deep Learning for Caries Detection: A SystematicReview,” Journal of Dentistry 122 (2022): 104115, https://doi.org/10.1016/j.jdent.2022.104115.

[30] W. Shin, H. G. Yeom, G. H. Lee, et al., “Deep Learning BasedPrediction of Necessity for Orthognathic Surgery of SkeletalMalocclusion Using Cephalogram in Korean Individuals,”BMC Oral Health 21, no. 1 (2021): 130, https://doi.org/10.1186/s12903-021-01513-3.

[31] K. S. Lee, J. J. Ryu, H. S. Jang, D. Y. Lee, and S. K. Jung, “DeepConvolutional Neural Networks Based Analysis of Cephalo-metric Radiographs for Differential Diagnosis of OrthognathicSurgery Indications,” Applied Sciences 10, no. 6 (2020): 2124,https://doi.org/10.3390/app10062124.

[32] S. H. Jeong, J. P. Yun, H. G. Yeom, H. J. Lim, J. Lee, and B. C.Kim, “Deep Learning Based Discrimination of Soft Tissue Pro-files Requiring Orthognathic Surgery by Facial Photographs,”Scientific Reports 10, no. 1 (2020): 16235, https://doi.org/10.1038/s41598-020-73287-7.

[33] M. Chung, J. Lee, W. Song, et al., “Automatic RegistrationBetween Dental Cone-Beam CT and Scanned Surface via DeepPose Regression Neural Networks and Clustered Similarities,”IEEE Transactions on Medical Imaging 39, no. 12 (2020):3900–3909, https://doi.org/10.1109/TMI.2020.3007520.

[34] G. Dot, T. Schouman, G. Dubois, P. Rouch, and L. Gajny, “FullyAutomatic Segmentation of Craniomaxillofacial CT Scans forComputer-Assisted Orthognathic Surgery Planning Using thennU-Net Framework,” European Radiology 32, no. 6 (2022):3639–3648, https://doi.org/10.1007/s00330-021-08455-y.

[35] Q. Ma, E. Kobayashi, B. Fan, et al., “Machine-Learning-BasedApproach for Predicting Postoperative Skeletal Changes forOrthognathic Surgical Planning,” International Journal ofMedical Robotics and Computer Assisted Surgery 18, no. 3(2022): e2379, https://doi.org/10.1002/rcs.2379.

[36] D. Xiao, H. Deng, C. Lian, et al., “Unsupervised Learning ofReference Bony Shapes for Orthognathic Surgical PlanningWith a Surface Deformation Network,” Medical Physics 48,no. 12 (2021): 7735–7746, https://doi.org/10.1002/mp.15126.

[37] R. Ter Horst, H. van Weert, T. Loonen, et al., “Three-Dimen-sional Virtual Planning in Mandibular Advancement Surgery:Soft Tissue Prediction Based on Deep Learning,” Journal ofCranio-Maxillo-Facial Surgery: Official Publication of theEuropean Association for Cranio-Maxillo-Facial Surgery 49,no. 9 (2021): 775–782, https://doi.org/10.1016/j.jcms.2021.04.001.

[38] L. Ma, D. Kim, C. Lian, et al., “Deep Simulation of FacialAppearance Changes Following Craniomaxillofacial BonyMovements in Orthognathic Surgical Planning,” in Proceed-ings of the 24th International Conference on Medical ImageComputing and Computer Assisted Intervention, MICCAI2021, eds. M. Bruijne, M. Bruijne, P. C. Cattin, S. Cotin, N.Padoy, and S. Speidel (Springer Science and Business MediaDeutschland GmbH, 2021), 459–468, https://doi.org/10.1007/978-3-030-87202-1_44.

[39] C. Tanikawa and T. Yamashiro, “Development of Novel Arti-ficial Intelligence Systems to Predict Facial Morphology AfterOrthognathic Surgery and Orthodontic Treatment in JapanesePatients,” Scientific Reports 11, no. 1 (2021): 15853, https://doi.org/10.1038/s41598-021-95002-w.

[40] C. H. Lu, E. W. C. Ko, and L. Liu, “Improving the Video Imag-ing Prediction of Postsurgical Facial Profiles With an ArtificialNeural Network,” Journal of Dental Sciences 4, no. 3 (2009):118–129, https://doi.org/10.1016/S1991-7902(09)60017-9.

[41] J. W. Choi, H. Park, K. BsIH, N. Kim, S. M. Kwon, and J. Y.Lee, “Surgery-First Orthognathic Approach to Correct FacialAsymmetry: Artificial Intelligence-Based Cephalometric Anal-ysis,” Plastic and Reconstructive Surgery 149, no. 3 (2022):496E–499E, https://doi.org/10.1097/PRS.0000000000008818.

[42] J. Seo, I. H. Yang, J. Y. Choi, J. H. Lee, and S. H. Baek, “Three-Dimensional Facial Soft Tissue Changes After OrthognathicSurgery in Cleft Patients Using Artificial Intelligence-Assisted Landmark Autodigitization,” The Journal of Cranio-facial Surgery 32, no. 8 (2021): 2695–2700, https://doi.org/10.1097/SCS.0000000000007712.

[43] H. H. Lin, W. C. Chiang, C. T. Yang, C. T. Cheng, T. Zhang,and L. J. Lo, “On Construction of Transfer Learning for FacialSymmetry Assessment Before and After Orthognathic Sur-gery,” Computer Methods and Programs in Biomedicine 200(2021): 105928, https://doi.org/10.1016/j.cmpb.2021.105928.

[44] H. H. Lin, L. J. Lo, and W. C. Chiang, eds., “A Novel AssessmentTechnique for the Degree of Facial Symmetry Before and AfterOrthognathic Surgery Based on Three-Dimensional ContourFeatures Using Deep Learning Algorithms,” in Proceedings ofthe 9th International Conference on Biomedical Engineeringand Technology, ICBET 2019 (Association for ComputingMachinery, 2019).

[45] L. J. Lo, C. T. Yang, C. T. Ho, C. H. Liao, and H. H. Lin, “Auto-matic Assessment of 3-Dimensional Facial Soft Tissue Sym-metry Before and After Orthognathic Surgery Using aMachine Learning Model: A Preliminary Experience,” Annalsof Plastic Surgery 86, no. 3S (2021): S224–S228, https://doi.org/10.1097/SAP.0000000000002687.

[46] C. J. Peck, V. K. Patel, Y. Parsaei, et al., “Commercial ArtificialIntelligence Software as a Tool for Assessing Facial Attractive-ness: A Proof-of-Concept Study in an Orthognathic SurgeryCohort,” Aesthetic Plastic Surgery 46, no. 2 (2022): 1013–1016, https://doi.org/10.1007/s00266-021-02537-4.

[47] R. Patcas, D. A. J. Bernini, A. Volokitin, E. Agustsson,R. Rothe, and R. Timofte, “Applying Artificial Intelligence toAssess the Impact of Orthognathic Treatment on FacialAttractiveness and Estimated Age,” International Journal ofOral and Maxillofacial Surgery 48, no. 1 (2019): 77–83,https://doi.org/10.1016/j.ijom.2018.07.010.

[48] V. Allareddy, M. K. Lee, N. R. Vaid, and S. Yadav, “Use of Neu-ral Network Model to Examine Post-Operative Infections Fol-lowing Orthognathic Surgeries in the United States,” Seminarsin Orthodontics 27, no. 2 (2021): 130–137, https://doi.org/10.1053/j.sodo.2021.05.009.

[49] R. Phellan, B. Hachem, J. Clin, J. M. Mac-Thiong, andL. Duong, “Real-Time Biomechanics Using the Finite ElementMethod and Machine Learning: Review and Perspective,”Medical Physics 48, no. 1 (2021): 7–18, https://doi.org/10.1002/mp.14602.

[50] H. Li, Z. Han, H. Wu, et al., “Artificial Intelligence in Surgery:Evolution, Trends, and Future Directions,” International Jour-nal of Surgery 111, no. 2 (2025): 2101–2111, https://doi.org/10.1097/JS9.0000000000002159.

[51] L. Lubkoll, A. Schiela, and M. Weiser, “An Optimal ControlProblem in Polyconvex Hyperelasticity,” SIAM Journal onControl and Optimization 52, no. 3 (2014): 1403–1422,https://doi.org/10.1137/120876629.

[52] D. Madsen, M. Lüthi, A. Schneider, and T. Vetter, “Probabilis-tic Joint Face-Skull Modelling for Facial Reconstruction,” inProceedings of the IEEE Conference on Computer Vision andPattern Recognition (IEEE, 2018).

[53] D. Kim, T. Kuang, Y. L. Rodrigues, et al., “A Novel IncrementalSimulation of Facial Changes Following Orthognathic SurgeryUsing FEM With Realistic Lip Sliding Effect,” Medical ImageAnalysis 72 (2021): 102095, https://doi.org/10.1016/j.media.2021.102095.

[54] D. Kim, T. Kuang, Y. L. Rodrigues, et al., “A New Approach ofPredicting Facial Changes Following Orthognathic SurgeryUsing Realistic Lip Sliding Effect,” Medical Image Computingand Computer-Assisted Intervention: MICCAI InternationalConference on Medical Image Computing and Computer-Assisted Intervention 11768 (2019): 336–344, https://doi.org/10.1007/978-3-030-32254-0_38.

[55] S. Rasteau, N. Sigaux, A. Louvrier, and P. Bouletreau, “Three-Dimensional Acquisition Technologies for Facial Soft Tissues -Applications and Prospects in Orthognathic Surgery,” Journalof Stomatology, Oral and Maxillofacial Surgery 121, no. 6(2020): 721–728, https://doi.org/10.1016/j.jormas.2020.05.013.

[56] J. A. Schwitzer, F. P. Albino, R. K. Mathis, A. M. Scott,L. Gamble, and S. B. Baker, “Assessing Patient-Reported Out-comes Following Orthognathic Surgery and Osseous Genio-plasty,” The Journal of Craniofacial Surgery 26, no. 8 (2015):2293–2298, https://doi.org/10.1097/SCS.0000000000001983.

• pdf

All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated. 

Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:

• Share their article on personal websites, institutional repositories, or social media platforms.

• Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.