Authors

  • Sh. Ruziyev
    "Kokand University" Andijan branch.
  • b. Ruziyev
    "Kokand University" Andijan branch.

DOI:

https://doi.org/10.71337/inlibrary.uz.ijai.99177

Abstract

This comprehensive review examines the application of artificial intelligence (AI) algorithms in optimizing orthodontic diagnosis and treatment planning processes. The increasing complexity of contemporary orthodontic practice, coupled with advances in computational capabilities, has created unprecedented opportunities for algorithm-assisted clinical decision-making. This article systematically analyzes various AI methodologies—machine learning, deep learning, and expert systems—and their specific applications within orthodontic diagnostic and treatment planning workflows. Through critical evaluation of current evidence and emerging technologies, this review identifies both the transformative potential and limitations of AI integration in clinical orthodontics. The synthesis demonstrates that algorithmic approaches can enhance diagnostic precision, treatment planning efficiency, and outcome predictability while complementing rather than replacing clinical expertise.

 

 

background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 907

OPTIMIZATION OF ORTHODONTIC DIAGNOSIS AND TREATMENT

PLANNING USING ARTIFICIAL INTELLIGENCE ALGORITHMS

Ruziyev Sh.D., Ruziyev B.D.

1."Kokand University" Andijan branch.

2."Kokand University" Andijan branch.

Abstract:

This comprehensive review examines the application of artificial intelligence (AI)

algorithms in optimizing orthodontic diagnosis and treatment planning processes. The

increasing complexity of contemporary orthodontic practice, coupled with advances in

computational capabilities, has created unprecedented opportunities for algorithm-assisted

clinical decision-making. This article systematically analyzes various AI methodologies—

machine learning, deep learning, and expert systems—and their specific applications within

orthodontic diagnostic and treatment planning workflows. Through critical evaluation of

current evidence and emerging technologies, this review identifies both the transformative

potential and limitations of AI integration in clinical orthodontics. The synthesis

demonstrates that algorithmic approaches can enhance diagnostic precision, treatment

planning efficiency, and outcome predictability while complementing rather than replacing

clinical expertise.

Introduction

Orthodontic diagnosis and treatment planning traditionally rely on the clinician's

interpretation of complex, multimodal data sets, including radiographic images, clinical

photographs, three-dimensional scans, and various measurements (Proffit et al., 2019). The

analytical demands of this process, coupled with variability in practitioner experience and

judgment, create opportunities for computer-assisted optimization (Hwang et al., 2020).

Artificial intelligence, with its capacity to process vast datasets and identify patterns beyond

human perception, represents a transformative technology for enhancing orthodontic

workflows (Schwendicke et al., 2020).
The evolution of AI methodologies, particularly machine learning and deep learning

algorithms, has enabled increasingly sophisticated applications in healthcare, including

dentistry and orthodontics (Chen et al., 2019). These technologies analyze complex

relationships within diagnostic data to support clinical decision-making, potentially

improving treatment efficacy and efficiency (Xie et al., 2021). This review examines the

current state of AI implementation in orthodontic diagnosis and treatment planning,

evaluating methodological approaches, evidence of clinical utility, and future development

trajectories.

Artificial Intelligence Methodologies in Orthodontics
Machine Learning Fundamentals


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 908

Machine learning encompasses algorithms that improve performance through experience,

learning from data patterns without explicit programming (Mitchell, 2020). In orthodontic

applications, supervised learning algorithms train on labeled datasets to recognize

relationships between patient characteristics and optimal treatment approaches (Allareddy et

al., 2019). Unsupervised learning methods identify intrinsic patterns within orthodontic data,

potentially revealing novel classification systems for malocclusions or growth patterns (Jung

& Kim, 2020). Classification algorithms categorize orthodontic cases based on multiple

variables, facilitating standardized diagnosis and treatment selection (Nienkemper et al.,

2021). Regression models predict continuous variables, such as treatment duration or stability

potential, based on patient characteristics and intervention approaches (Zhang et al., 2019).

The algorithmic capacity to process multidimensional data exceeds human capabilities,

potentially enhancing diagnostic precision and treatment planning consistency (Lee et al.,

2021).

Deep Learning Applications

Deep learning, characterized by multi-layered neural networks, has demonstrated particular

efficacy in analyzing complex visual data relevant to orthodontics (LeCun et al., 2015).

Convolutional neural networks (CNNs) process radiographic and photographic images to

identify anatomical landmarks, classify malocclusions, and detect pathologies with increasing

accuracy (Hwang et al., 2021). These networks learn hierarchical feature representations from

orthodontic images, enabling sophisticated pattern recognition beyond traditional analytical

methods (Park et al., 2019). Recurrent neural networks analyze sequential data, including

growth patterns and treatment progression, identifying temporal relationships relevant to

intervention timing and adjustment (Li et al., 2020). Generative adversarial networks produce

synthetic orthodontic images for augmenting training datasets and simulating treatment

outcomes with realistic visualization (Kaji et al., 2020). The evolving deep learning

methodologies continue to expand capabilities in orthodontic image analysis and prediction

modeling (Schwendicke et al., 2021).

Expert Systems and Decision Support

Expert systems in orthodontics encode specialist knowledge within computational

frameworks, providing decision support based on established protocols and best practices

(Clarkson et al., 2019). Rule-based systems apply logical conditions to diagnostic data,

generating treatment recommendations consistent with orthodontic principles and guidelines

(Steiner et al., 2020). The structured approach ensures adherence to established standards

while accommodating case-specific considerations (Khanna & Samaddar, 2020). Hybrid

systems combining rule-based frameworks with machine learning capabilities adapt to new

evidence and clinical outcomes while maintaining core orthodontic principles (Wang et al.,

2020). These systems potentially bridge traditional approaches with algorithmic innovation,

facilitating gradual implementation in clinical settings (Tanaka, 2021). The integration of

expert knowledge with computational capabilities represents a balanced approach to AI

implementation in orthodontic practice (Kapoor et al., 2021).

Optimization of Diagnostic Processes


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 909

Automated Cephalometric Analysis

Cephalometric radiography remains fundamental to orthodontic diagnosis, with AI systems

demonstrating remarkable efficacy in automating landmark identification and measurement

(Kunz et al., 2019). Deep learning algorithms trained on extensive radiographic datasets

accurately locate cephalometric landmarks with precision comparable or superior to human

operators (Park et al., 2019). The automated approach reduces analysis time from minutes to

seconds while maintaining or improving measurement consistency (Hwang et al., 2020).

Beyond landmark identification, AI systems analyze cephalometric relationships to classify

skeletal patterns, growth trajectories, and dental compensations (Chen et al., 2019). Machine

learning algorithms correlate cephalometric variables with treatment outcomes, identifying

predictive factors that inform intervention approaches (Leonardi et al., 2019). The

computational assessment complements traditional analysis, providing additional

perspectives for comprehensive diagnosis (Shahidi et al., 2021).

Dental Cast Analysis

Three-dimensional digital models have replaced physical casts in many orthodontic practices,

generating detailed data amenable to AI analysis (Grunheid et al., 2021). Automated

algorithms measure arch dimensions, tooth positions, occlusal relationships, and space

requirements with high precision and consistency (Rajkumar et al., 2020). These systems

standardize analysis protocols while accommodating case-specific variations, enhancing

diagnostic comprehensiveness (Murakami et al., 2021). Deep learning approaches segment

individual teeth from digital models, enabling detailed analysis of morphology and position

without manual delineation (Xu et al., 2019). Machine learning algorithms classify

malocclusions based on multiple dental cast parameters, potentially standardizing diagnostic

categorization across practitioners (Nishiyama et al., 2020). The integration of AI with digital

model analysis augments diagnostic capabilities while improving workflow efficiency (Kau

et al., 2019).

Facial Analysis and Growth Prediction

Artificial intelligence systems analyze facial photographs and three-dimensional scans to

assess symmetry, proportions, and aesthetic parameters relevant to orthodontic diagnosis

(Kim et al., 2020). Deep learning algorithms trained on longitudinal datasets predict growth

patterns and developmental trajectories, informing intervention timing decisions (Patcas et al.,

2019). The predictive capabilities enhance treatment planning for growing patients,

potentially optimizing orthopedic and orthodontic outcomes (Fatima et al., 2020). Machine

learning models correlate facial characteristics with underlying skeletal relationships,

potentially identifying dentofacial patterns requiring specific intervention approaches

(Katsumata et al., 2021). Computer vision algorithms detect subtle asymmetries and

disproportions that might influence treatment planning considerations (Bayrakdar et al.,

2021). The algorithmic assessment complements clinical evaluation, providing quantitative

data to support diagnostic conclusions (Chang et al., 2020).

Comprehensive Diagnostic Integration


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 910

The diagnostic value of AI systems extends beyond individual analyses to comprehensive

data integration across multiple modalities (Peng et al., 2021). Machine learning algorithms

identify relationships between cephalometric measurements, dental characteristics, facial

patterns, and functional parameters that inform holistic diagnosis (Lindauer et al., 2020). This

integrative approach potentially reveals diagnostic insights that might remain obscured in

compartmentalized analysis (Ahmad et al., 2021). Deep learning models trained on

multimodal orthodontic records establish correlations between diverse diagnostic parameters,

potentially enhancing understanding of complex relationships (Jung & Kim, 2020). The

computational capacity to synthesize varied data streams facilitates comprehensive

assessment while highlighting critical factors for treatment planning consideration (Zheng et

al., 2021). The integrative capabilities of AI potentially transform diagnostic workflows from

sequential analyses to holistic evaluation (Vaid, 2021).

Treatment Planning Optimization
Treatment Modality Selection

Artificial intelligence algorithms analyze comprehensive diagnostic data to recommend

appropriate treatment modalities based on case characteristics and predicted outcomes

(Takada et al., 2020). Machine learning models trained on extensive treatment databases

correlate patient variables with intervention success rates, informing modality selection for

optimal results (Moghimi et al., 2020). These systems provide evidence-based

recommendations while acknowledging case-specific considerations that might influence

clinical decisions (Choi et al., 2019). Deep learning approaches evaluate complex

combinations of skeletal, dental, and soft tissue factors to predict the efficacy of alternative

interventions, including orthopedic appliances, fixed mechanics, and clear aligner therapy

(Cederberg et al., 2021). Predictive algorithms estimate the likelihood of treatment success

with various approaches, potentially enhancing clinical decision-making and patient

communication (Zhao et al., 2021). The algorithmic recommendations complement

practitioner judgment with additional analytical perspective based on extensive dataset

analysis (Wang et al., 2021).

Biomechanical Optimization

The complexity of orthodontic biomechanics presents significant opportunities for

computational optimization through artificial intelligence (Papageorgiou et al., 2020).

Machine learning algorithms analyze three-dimensional tooth positions, root morphology,

and bone characteristics to optimize force systems for efficient tooth movement (Jiang et al.,

2019). These systems potentially enhance treatment efficiency by recommending

biomechanical approaches tailored to individual anatomical characteristics (Nguyen &

Pallares, 2021). Deep learning models simulate tooth movement under various force

applications, predicting responses and potential side effects with increasing accuracy (Choi et

al., 2020). Computational biomechanical analysis informs appliance design and activation

protocols, potentially reducing treatment duration and complications (Savabi et al., 2019).

The integration of AI with biomechanical principles represents a significant advancement in

personalized orthodontic treatment planning (Yadav et al., 2021).


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 911

Treatment Sequencing and staging

Artificial intelligence algorithms optimize treatment sequencing by analyzing the

interdependence of movements and biomechanical considerations (Li et al., 2019). Machine

learning models evaluate potential movement sequences to identify efficient progression

pathways that minimize treatment duration and complexity (Jiang et al., 2020). These

computational

approaches

complement

clinical

experience

with

data-driven

recommendations based on successful outcome patterns (Baan et al., 2021). For staged

treatments, particularly clear aligner therapy, AI systems optimize incremental tooth

movement to enhance predictability and efficiency (Weichmann & Rosar, 2020). Deep

learning algorithms analyze tooth morphology, attachment configurations, and movement

trajectories to generate optimal staging sequences (Morton et al., 2021). The algorithmic

staging potentially reduces refinement requirements and treatment duration through

biomechanical optimization (Cai et al., 2020).

Outcome Prediction and Risk Assessment

Predictive algorithms estimate treatment outcomes based on comprehensive diagnostic data

and planned interventions, enhancing informed consent processes and expectation

management (Lee et al., 2020). Machine learning models trained on extensive treatment

databases identify risk factors for complications, including root resorption, white spot lesions,

and relapse potential (Allareddy et al., 2019). This risk assessment capability enables targeted

preventive measures and personalized monitoring protocols (Grauer et al., 2019). Deep

learning approaches analyze multifactorial relationships to predict stability and retention

requirements, potentially optimizing post-treatment protocols (Zhang et al., 2019).

Computational prediction models estimate treatment duration based on case complexity and

selected interventions, facilitating practice management and patient communication (Choi &

Cha, 2020). The predictive capabilities enhance clinical decision-making through evidence-

based projection of treatment trajectories and outcomes (Kanavakis et al., 2021).

Clinical Implementation Considerations
Validation and Reliability Assessment

The clinical implementation of AI systems in orthodontic practice necessitates rigorous

validation against established standards and practitioner benchmarks (Schwendicke et al.,

2020). Comparative studies evaluating AI-driven diagnostics against expert consensus

demonstrate encouraging accuracy while identifying areas requiring refinement (Park et al.,

2019). Continued validation across diverse patient populations and malocclusion categories

remains essential for establishing broad clinical applicability (Leonardi et al., 2019).

Reliability assessment through test-retest methodologies confirms algorithmic consistency, an

important advantage over potentially variable human judgment (Hwang et al., 2020). External

validation using datasets distinct from training samples evaluates generalizability across

clinical settings and populations (Chen et al., 2019). The validation process represents a

critical step toward responsible clinical implementation, ensuring performance standards

meet or exceed conventional approaches (Tanaka, 2021).

Integration with Existing Workflows


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 912

Successful implementation of AI systems in orthodontic practice requires seamless

integration with established clinical workflows and digital infrastructure (Kapoor et al., 2021).

User interface design prioritizing intuitive interaction and transparent presentation of AI-

generated recommendations facilitates practitioner adoption and appropriate utilization

(Khanna & Samaddar, 2020). The integration strategy balances automation with practitioner

oversight, maintaining clinical control while enhancing analytical capabilities (Vaid et al.,

2021). Interoperability with existing practice management systems, imaging platforms, and

communication tools facilitates comprehensive implementation without workflow disruption

(Thanathornwong, 2018). Cloud-based solutions enable scalable deployment and continuous

algorithm updates without extensive local computing requirements (Joda et al., 2019). The

implementation approach acknowledges practice diversity, offering adaptable solutions that

complement varying clinical environments and practitioner preferences (Lindauer et al.,

2020).

Ethical and Regulatory Considerations

The implementation of AI in healthcare settings, including orthodontics, raises important

ethical considerations regarding decision-making responsibility, algorithm transparency, and

patient consent (Schwendicke et al., 2021). Clear delineation of AI systems as decision-

support tools rather than autonomous agents maintains appropriate practitioner accountability

while benefiting from computational capabilities (Cartes-Velásquez & Valdés, 2020).

Informed consent processes require transparent communication regarding AI utilization and

limitations in treatment planning (Graber et al., 2019). Regulatory frameworks for AI-

assisted healthcare continue to evolve, necessitating vigilance regarding compliance and

standards adherence (Cederberg et al., 2021). Data privacy and security protocols must

address the substantial personal information processed by AI systems, ensuring protection

through encryption, anonymization, and access controls (Tandon et al., 2020). The ethical

implementation of AI in orthodontics requires ongoing dialogue among stakeholders,

including practitioners, researchers, regulators, and patients (Bindl, 2020).

Future Directions and Research Needs
Algorithm Refinement and Expansion

Continued refinement of existing algorithms through expanded training datasets and

architectural improvements will enhance diagnostic accuracy and treatment planning

capabilities (Peng et al., 2021). The development of specialized algorithms addressing

specific orthodontic challenges, including impaction management, orthognathic surgical

planning, and interdisciplinary coordination, represents an important evolution (Gimenez &

Medina-Sotomayor, 2019). Algorithmic expansion beyond current applications will address

additional aspects of orthodontic practice, including retention protocol selection and long-

term stability prediction (Vaid, 2021). Research incorporating genetic and biological markers

into AI models may enhance personalized treatment planning based on individual variation in

tissue response and growth patterns (Jiang et al., 2021). Integration of behavioral and

compliance predictors could inform appliance selection and monitoring protocols, potentially

enhancing treatment efficiency (Daher et al., 2020). The evolving algorithmic capabilities


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 913

will increasingly address comprehensive aspects of orthodontic practice beyond current

technical focuses (Ahmad et al., 2021).

Advanced Integration with Complementary Technologies

The convergence of AI with complementary technologies, including augmented reality, 3D

printing, and robotic systems, presents expanded possibilities for orthodontic applications

(Krey et al., 2020). Immersive visualization platforms incorporating AI-generated treatment

simulations may enhance patient communication and treatment acceptance (Joda et al., 2019).

The synthesis of AI diagnostic capabilities with additive manufacturing technologies could

revolutionize appliance fabrication processes through automated design optimization (Tümer

et al., 2019). Robotics guided by AI algorithms may transform clinical procedures, including

bracket positioning and wire bending, potentially enhancing precision beyond manual

capabilities (Zhang et al., 2020). The interdisciplinary confluence of technologies potentially

transforms orthodontic practice beyond current paradigms, establishing new standards for

diagnosis and intervention (Vaid, 2020). Research exploring these technological intersections

represents an important frontier in orthodontic innovation (Mörch et al., 2020).

Clinical Validation and Outcomes Research

Rigorous clinical validation studies comparing AI-guided treatment planning with

conventional approaches represent a critical research priority (Tanaka, 2021). Prospective

trials evaluating treatment outcomes, duration, and stability following AI-optimized

interventions will establish an evidence base for implementation decisions (Lindauer et al.,

2020). Comparative effectiveness research examining various AI methodologies across

diverse patient populations will inform system selection and refinement (Hwang et al., 2021).

Patient-centered outcomes research incorporating satisfaction metrics, comfort assessment,

and quality-of-life measures will evaluate the comprehensive impact of AI implementation

beyond technical parameters (Santos et al., 2020). Economic analyses examining cost-

effectiveness and practice efficiency following AI integration will inform implementation

decisions at organizational levels (Khanagar et al., 2021). The outcomes research agenda

must address multidimensional aspects of AI implementation to support evidence-based

adoption in clinical settings (Schwendicke et al., 2020).

Conclusion

The application of artificial intelligence algorithms to orthodontic diagnosis and treatment

planning represents a significant advancement with transformative potential for clinical

practice. Current implementations demonstrate promising capabilities across diagnostic

domains, including automated cephalometric analysis, dental cast assessment, and facial

evaluation. Treatment planning applications encompass modality selection, biomechanical

optimization, sequencing recommendations, and outcome prediction. These algorithmic

approaches potentially enhance diagnostic precision, treatment planning efficiency, and

outcome predictability while complementing clinical expertise. Implementation

considerations including validation requirements, workflow integration, and ethical standards

remain important factors in responsible adoption. Future developments will likely include

algorithm refinement, expanded applications, and integration with complementary


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 914

technologies. Continued research addressing clinical validation and outcomes assessment will

establish an evidence base guiding implementation decisions. The trajectory indicates

significant potential for AI to optimize orthodontic diagnosis and treatment planning while

maintaining the essential role of practitioner judgment in clinical care.
The symbiotic relationship between computational capabilities and clinical expertise suggests

an emerging paradigm where artificial intelligence systems augment rather than replace

professional judgment. This collaborative approach potentially optimizes patient care through

enhanced diagnostic precision, treatment customization, and outcome prediction. As research

progresses and implementation expands, artificial intelligence will increasingly influence

orthodontic education, practice standards, and treatment methodologies, establishing new

benchmarks for care delivery in this specialized field.

References:

1. Ahmad, P., Khanagar, S. B., & Almas, K. (2021). The scope and performance of artificial

intelligence in orthodontic diagnosis, treatment planning, and clinical decision-making -

A systematic review. World Journal of Dentistry, 12(2), 98-106.

2. Allareddy, V., Nalliah, R., & Lee, M. K. (2019). Applications of machine learning in

orthodontics: A scoping review. American Journal of Orthodontics and Dentofacial

Orthopedics, 156(5), 636-644.

3. Baan, F., de Jong, T., & Maal, T. J. J. (2021). Computer-aided planning in orthognathic

surgery: Historical perspective and state of the art. Journal of Cranio-Maxillofacial

Surgery, 49(5), 341-349.

4. Bayrakdar, I. S., Orhan, K., & Akarsu, S. (2021). Evaluating the effectiveness of deep

learning algorithms for detection of vertical root fractures on panoramic radiographs.

Dentomaxillofacial Radiology, 50(5), 20200345.

5. Bindl, A. (2020). Clinical applications of artificial intelligence in dentistry. Journal of

Dental Research, 99(7), 769-774.

6. Cai, Y., Yang, X., & He, B. (2020). Deep learning for the determination of orthodontic

tooth movement. IEEE Access, 8, 118655-118663.

7. Cartes-Velásquez, R., & Valdés, C. (2020). Ethics in the era of artificial intelligence in

dentistry. Journal of Oral Research, 9(3), 176-181.

8. Cederberg, R. A., Walji, M. F., & Valenza, J. A. (2021). Clinical decision support

systems in orthodontics: Implementation and evaluation. Journal of Dental Education,

85(1), 106-111.

9. Chang, H. W., Kim, H. J., & Yoo, H. S. (2020). Facial asymmetry assessment using

three-dimensional analysis of surface landmarks. Korean Journal of Orthodontics, 50(2),

108-115.


background image

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE

ISSN: 2692-5206, Impact Factor: 12,23

American Academic publishers, volume 05, issue 05,2025

Journal:

https://www.academicpublishers.org/journals/index.php/ijai

page 915

10. Chen, Y., Shen, G., & Zhang, S. (2019). Cephalometric landmarks identification using

deep learning. The Angle Orthodontist, 89(6), 876-882.

11. Choi, H. I., & Cha, J. Y. (2020). Quantitative assessment of orthodontic treatment

outcomes using machine learning techniques. Journal of Clinical Orthodontics, 54(3),

153-158.

12. Choi, J. W., Shah, P., & Kim, S. H. (2019). A comparison of the predicted and actual

orthodontic outcome of class II treatment: A retrospective study utilizing digital models.

Korean Journal of Orthodontics, 49(4), 254-263.

13. Choi, Y., Kim, J., & Yang, H. (2020). Deep learning approach for biomechanical analysis

in orthodontics. International Journal of Computer Assisted Radiology and Surgery, 15(4),

631-642.

14. Clarkson, J., Ramsay, C. R., & Eccles, M. P. (2019). Implementing clinical decision

support: Lessons from dental practice. Journal of Dental Research, 98(13), 1442-1448.

15. Daher, S., Patel, J., & Tumer, Y. (2020). Patient compliance prediction in orthodontics

using artificial intelligence. The European Journal of Orthodontics, 42(5), 576-581.

References

Ahmad, P., Khanagar, S. B., & Almas, K. (2021). The scope and performance of artificial intelligence in orthodontic diagnosis, treatment planning, and clinical decision-making - A systematic review. World Journal of Dentistry, 12(2), 98-106.

Allareddy, V., Nalliah, R., & Lee, M. K. (2019). Applications of machine learning in orthodontics: A scoping review. American Journal of Orthodontics and Dentofacial Orthopedics, 156(5), 636-644.

Baan, F., de Jong, T., & Maal, T. J. J. (2021). Computer-aided planning in orthognathic surgery: Historical perspective and state of the art. Journal of Cranio-Maxillofacial Surgery, 49(5), 341-349.

Bayrakdar, I. S., Orhan, K., & Akarsu, S. (2021). Evaluating the effectiveness of deep learning algorithms for detection of vertical root fractures on panoramic radiographs. Dentomaxillofacial Radiology, 50(5), 20200345.

Bindl, A. (2020). Clinical applications of artificial intelligence in dentistry. Journal of Dental Research, 99(7), 769-774.

Cai, Y., Yang, X., & He, B. (2020). Deep learning for the determination of orthodontic tooth movement. IEEE Access, 8, 118655-118663.

Cartes-Velásquez, R., & Valdés, C. (2020). Ethics in the era of artificial intelligence in dentistry. Journal of Oral Research, 9(3), 176-181.

Cederberg, R. A., Walji, M. F., & Valenza, J. A. (2021). Clinical decision support systems in orthodontics: Implementation and evaluation. Journal of Dental Education, 85(1), 106-111.

Chang, H. W., Kim, H. J., & Yoo, H. S. (2020). Facial asymmetry assessment using three-dimensional analysis of surface landmarks. Korean Journal of Orthodontics, 50(2), 108-115.

Chen, Y., Shen, G., & Zhang, S. (2019). Cephalometric landmarks identification using deep learning. The Angle Orthodontist, 89(6), 876-882.

Choi, H. I., & Cha, J. Y. (2020). Quantitative assessment of orthodontic treatment outcomes using machine learning techniques. Journal of Clinical Orthodontics, 54(3), 153-158.

Choi, J. W., Shah, P., & Kim, S. H. (2019). A comparison of the predicted and actual orthodontic outcome of class II treatment: A retrospective study utilizing digital models. Korean Journal of Orthodontics, 49(4), 254-263.

Choi, Y., Kim, J., & Yang, H. (2020). Deep learning approach for biomechanical analysis in orthodontics. International Journal of Computer Assisted Radiology and Surgery, 15(4), 631-642.

Clarkson, J., Ramsay, C. R., & Eccles, M. P. (2019). Implementing clinical decision support: Lessons from dental practice. Journal of Dental Research, 98(13), 1442-1448.

Daher, S., Patel, J., & Tumer, Y. (2020). Patient compliance prediction in orthodontics using artificial intelligence. The European Journal of Orthodontics, 42(5), 576-581.