Use of artificial intelligence to predict outcomes of nonextraction treatment of Class II malocclusions

Orthodontic treatment outcome predictive performance differences between artificial intelligence and conventional methods

OBJECTIVES

To evaluate an artificial intelligence (AI) model in predicting soft tissue and alveolar bone changes following orthodontic treatment and compare the predictive performance of the AI model with conventional prediction models.

MATERIALS AND METHODS

A total of 1774 lateral cephalograms of 887 adult patients who had undergone orthodontic treatment were collected. Patients who had orthognathic surgery were excluded. On each cephalogram, 78 landmarks were detected using PIPNet-based AI. Prediction models consisted of 132 predictor variables and 88 outcome variables. Predictor variables were demographics (age, sex), clinical (treatment time, premolar extraction), and Cartesian coordinates of the 64 anatomic landmarks. Outcome variables were Cartesian coordinates of the 22 soft tissue and 22 hard tissue landmarks after orthodontic treatment. The AI prediction model was based on the TabNet deep neural network. Two conventional statistical methods, multivariate multiple linear regression (MMLR) and partial least squares regression (PLSR), were each implemented for comparison. Prediction accuracy among the methods was compared.

RESULTS

Overall, MMLR demonstrated the most accurate results, while AI was least accurate. AI showed superior predictions in only 5 of the 44 anatomic landmarks, all of which were soft tissue landmarks inferior to menton to the terminal point of the neck.

CONCLUSIONS

When predicting changes following orthodontic treatment, AI was not as effective as conventional statistical methods. However, AI had an outstanding advantage in predicting soft tissue landmarks with substantial variability. Overall, results may indicate the need for a hybrid prediction model that combines conventional and AI methods.

Accuracy of artificial intelligence-assisted growth prediction in skeletal Class I preadolescent patients using serial lateral cephalograms for a 2-year growth interval

OBJECTIVE

To investigate the accuracy of artificial intelligence-assisted growth prediction using a convolutional neural network (CNN) algorithm and longitudinal lateral cephalograms (Lat-cephs).

MATERIALS AND METHODS

A total of 198 Japanese preadolescent children, who had skeletal Class I malocclusion and whose Lat-cephs were available at age 8 years (T0) and 10 years (T1), were allocated into the training, validation, and test phases (n = 161, n = 17, n = 20). Orthodontists and the CNN model identified 28 hard-tissue landmarks (HTL) and 19 soft-tissue landmarks (STL). The mean prediction error values were defined as 'excellent,' 'very good,' 'good,' 'acceptable,' and 'unsatisfactory' (criteria: 0.5 mm, 1.0 mm, 1.5 mm, and 2.0 mm, respectively). The degree of accurate prediction percentage (APP) was defined as 'very high,' 'high,' 'medium,' and 'low' (criteria: 90%, 70%, and 50%, respectively) according to the percentage of subjects that showed the error range within 1.5 mm.

RESULTS

All HTLs showed acceptable-to-excellent mean PE values, while the STLs Pog', Gn', and Me' showed unsatisfactory values, and the rest showed good-to-acceptable values. Regarding the degree of APP, HTLs Ba, ramus posterior, Pm, Pog, B-point, Me, and mandibular first molar root apex exhibited low APPs. The STLs labrale superius, lower embrasure, lower lip, point of lower profile, B', Pog,' Gn' and Me' also exhibited low APPs. The remainder of HTLs and STLs showed medium-to-very high APPs.

CONCLUSION

Despite the possibility of using the CNN model to predict growth, further studies are needed to improve the prediction accuracy in HTLs and STLs of the chin area.

The Future of Orthodontics: Deep Learning Technologies

Deep learning has emerged as a revolutionary technical advancement in modern orthodontics, offering novel methods for diagnosis, treatment planning, and outcome prediction. Over the past 25 years, the field of dentistry has widely adopted information technology (IT), resulting in several benefits, including decreased expenses, increased efficiency, decreased need for human expertise, and reduced errors. The transition from preset rules to learning from real-world examples, particularly machine learning (ML) and artificial intelligence (AI), has greatly benefited the organization, analysis, and storage of medical data. Deep learning, a type of AI, enables robots to mimic human neural networks, allowing them to learn and make decisions independently without the need for explicit programming. Its ability to automate cephalometric analysis and enhance diagnosis through 3D imaging has revolutionized orthodontic operations. Deep learning models have the potential to significantly improve treatment outcomes and reduce human errors by accurately identifying anatomical characteristics on radiographs, thereby expediting analytical processes. Additionally, the use of 3D imaging technologies such as cone-beam computed tomography (CBCT) can facilitate precise treatment planning, allowing for comprehensive examinations of craniofacial architecture, tooth movements, and airway dimensions. In today's era of personalized medicine, deep learning's ability to customize treatments for individual patients has propelled the field of orthodontics forward tremendously. However, it is essential to address issues related to data privacy, model interpretability, and ethical considerations before orthodontic practices can use deep learning in an ethical and responsible manner. Modern orthodontics is evolving, thanks to the ability of deep learning to deliver more accurate, effective, and personalized orthodontic treatments, improving patient care as technology develops.

AI in Orthodontics: Revolutionizing Diagnostics and Treatment Planning-A Comprehensive Review

The advent of artificial intelligence (AI) in medicine has transformed various medical specialties, including orthodontics. AI has shown promising results in enhancing the accuracy of diagnoses, treatment planning, and predicting treatment outcomes. Its usage in orthodontic practices worldwide has increased with the availability of various AI applications and tools. This review explores the principles of AI, its applications in orthodontics, and its implementation in clinical practice. A comprehensive literature review was conducted, focusing on AI applications in dental diagnostics, cephalometric evaluation, skeletal age determination, temporomandibular joint (TMJ) evaluation, decision making, and patient telemonitoring. Due to study heterogeneity, no meta-analysis was possible. AI has demonstrated high efficacy in all these areas, but variations in performance and the need for manual supervision suggest caution in clinical settings. The complexity and unpredictability of AI algorithms call for cautious implementation and regular manual validation. Continuous AI learning, proper governance, and addressing privacy and ethical concerns are crucial for successful integration into orthodontic practice.

Effectiveness of miniscrew-supported maxillary molar distalization according to temporary anchorage device features and appliance design: systematic review and meta-analysis

OBJECTIVES

To evaluate the effectiveness of distalizing maxillary first molars (U6) by temporary anchorage devices (TADs) according to their location (palatal, buccal, and zygomatic), their number, and appliance design.

MATERIALS AND METHODS

An electronic search of maxillary molar distalization with TADs was done through April 2023. After study selection, data extraction, and risk-of-bias assessment, meta-analyses were performed for the extent of distalization, distal tipping, and vertical movement of U6 using the generic inverse variance and random-effects model. The significance level was set at 0.05.

RESULTS

Forty studies met the inclusion criteria: 4 randomized controlled trials (RCTs), 13 prospective studies, and 23 retrospective studies (total of 1182 patients). Distalization of the U6 was not significantly greater (P = .64) by palatal (3.74 mm) and zygomatic (3.68 mm) than by buccal (3.23 mm) TADs. Distal tipping was significantly higher (P < .001) in nonrigid (9.84°) than in rigid (1.97°) appliances. Vertical movement was mostly intrusive and higher but not significantly different (P = .28) in zygomatic anchorage (-1.16 mm).

CONCLUSIONS

Distalization of U6 with TADs can be an effective and stable treatment procedure, especially when performed with rigid palatal appliances. However, further RCTs or prospective cohort studies are strongly recommended to provide more clinical evidence.

Orthognathic surgical planning using graph CNN with dual embedding module: External validations with multi-hospital datasets

BACKGROUND AND OBJECTIVE

Despite recent development of AI, prediction of the surgical movement in the maxilla and mandible by OGS might be more difficult than that of tooth movement by orthodontic treatment. To evaluate the prediction accuracy of the surgical movement using pairs of pre-(T0) and post-surgical (T1) lateral cephalograms (lat-ceph) of orthognathic surgery (OGS) patients and dual embedding module-graph convolution neural network (DEM-GCNN) model.

METHODS

599 pairs from 3 institutions were used as training, internal validation, and internal test sets and 201 pairs from other 6 institutions were used as external test set. DEM-GCNN model (IEM, learning the lat-ceph images; LTEM, learning the landmarks) was developed to predict the amount and direction of surgical movement of ANS and PNS in the maxilla and B-point and Md1crown in the mandible. The distance between T1 landmark coordinates actually moved by OGS (ground truth) and predicted by DEM-GCNN model and pre-existed CNN-based Model-C (learning the lat-ceph images) was compared.

RESULTS

In both internal and external tests, DEM-GCNN did not exhibit significant difference from ground truth in all landmarks (ANS, PNS, B-point, Md1crown, all P > 0.05). When the accumulated successful detection rate for each landmark was compared, DEM-GCNN showed higher values than Model-C in both the internal and external tests. In violin plots exhibiting the error distribution of the prediction results, both internal and external tests showed that DEM-GCNN had significant performance improvement in PNS, ANS, B-point, Md1crown than Model-C. DEM-GCNN showed significantly lower prediction error values than Model-C (one-jaw surgery, B-point, Md1crown, all P < 0.005; two-jaw surgery, PNS, ANS, all P < 0.05; B point, Md1crown, all P < 0.005).

CONCLUSION

We developed a robust OGS planning model with maximized generalizability despite diverse qualities of lat-cephs from 9 institutions.

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

In recent years, there has been the notable emergency of artificial intelligence (AI) as a transformative force in multiple domains, including orthodontics. This review aims to provide a comprehensive overview of the present state of AI applications in orthodontics, which can be categorized into the following domains: (1) diagnosis, including cephalometric analysis, dental analysis, facial analysis, skeletal-maturation-stage determination and upper-airway obstruction assessment; (2) treatment planning, including decision making for extractions and orthognathic surgery, and treatment outcome prediction; and (3) clinical practice, including practice guidance, remote care, and clinical documentation. We have witnessed a broadening of the application of AI in orthodontics, accompanied by advancements in its performance. Additionally, this review outlines the existing limitations within the field and offers future perspectives.

Development and accuracy of artificial intelligence-generated prediction of facial changes in orthodontic treatment: a scoping review

Artificial intelligence (AI) has been utilized in soft-tissue analysis and prediction in orthodontic treatment planning, although its reliability has not been systematically assessed. This scoping review was conducted to outline the development of AI in terms of predicting soft-tissue changes after orthodontic treatment, as well as to comprehensively evaluate its prediction accuracy. Six electronic databases (PubMed, EBSCOhost, Web of Science, Embase, Cochrane Library, and Scopus) were searched up to March 14, 2023. Clinical studies investigating the performance of AI-based systems in predicting post-orthodontic soft-tissue alterations were included. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) and Joanna Briggs Institute (JBI) appraisal checklist for diagnostic test accuracy studies were applied to assess risk of bias, while the Grading of Recommendation, Assessment, Development, and Evaluation (GRADE) assessment was conducted to evaluate the certainty of outcomes. After screening 2500 studies, four non-randomized clinical trials were finally included for full-text evaluation. We found a low level of evidence indicating an estimated high overall accuracy of AI-generated prediction, whereas the lower lip and chin seemed to be the least predictable regions. Furthermore, the facial morphology simulated by AI via the fusion of multimodality images was considered to be reasonably true. Since all of the included studies that were not randomized clinical trials (non-RCTs) showed a moderate to high risk of bias, more well-designed clinical trials with sufficient sample size are needed in future work.

Age- and sex-related differences in 3D facial shape and muscle pressure in subjects with normal occlusion

BACKGROUND AND OBJECTIVE(S): (1) To derive descriptive statistics of three-dimensional (3D) facial shape, lip and cheek muscle pressure in subjects of European descent with normal dental occlusion. (2) To analyse the effect of age and sex on 3D-facial soft tissue morphology and muscle pressure in the same sample. (3) To assess the independent effect of muscle pressure on face shape.

METHOD

129 subjects with normal occlusion were cross-sectionally recruited and divided into: children (mixed dentition), adolescents and adults (permanent dentition, < and ≥18 years respectively). Muscle pressure was recorded using the Iowa Oral Performance Instrument. MeshLab, MeVisLab and Meshmonk tool box were used to clean, annotate landmarks and generate the 3D images. Two-way analysis of variance and post-hoc tests were used to analyse age and sex differences in face shape and muscle pressure. The effect of muscle pressure on face shape was analysed by Pearson correlation and Partial Least Square regression.

RESULTS

Significant facial differences were observed between adults and adolescents and adults and children in both sexes, showing flattening of cheeks and lips and protrusion of nose and chin. Significant cheek protrusion and retrusion of the vertical midface were found in adult women compared to men. Lip and cheek pressure increased with age, but their effect on face shape was not significant.

CONCLUSIONS

This study provides 3D age- and sex-specific facial models and muscle pressure of subjects without malocclusion. These can be used as a reference for clinicians focused on facial assessment in treatment planning and follow-up.

Efficiency of maxillary total arch distalization using temporary anchorage devices (TADs) for treatment of Class II-malocclusions: A systematic review and meta-analysis

OBJECTIVES

To evaluate the treatment effects and post-treatment stability of the maxillary total arch distalization using TADs during the non-extraction treatment of class II malocclusions.

MATERIALS AND METHODS

Study involved an electronic search followed by hand searching for randomized and non-randomized clinical studies about maxillary total arch distalization using TADs. After data extraction and risk of bias assessment, meta-analysis was performed for dental, skeletal and soft tissue changes using the Generic-inverse variance approach by use of the mean difference and random-effect model.

RESULTS

In total, 1788 articles were identified, 88 full texts were screened and 22 studies were found eligible; 17 of them were included in the quantitative analysis. The means of distalization/distal tipping of the maxillary first molar were 4mm/3.17° in adults, 3.95mm/1.61° in adolescents after treatment with the Modified C-Palatal plate (MCPP), while they were 2.44mm/2.91° with the inter-radicular mini-screws. Both MCPP's treatment in adults and inter-radicular mini-screws resulted in significant intrusion of U6 (1.64 and 0.75mm, respectively), while insignificant extrusion of U6 was resulted in adolescents treated by MCPP. MCPP appliances resulted in palatal inclination/extrusion of maxillary incisors U1 (6.77°/2mm in adults, 7.46°/3.14mm in adolescents). In contrast, inter-radicular mini-screws resulted in less palatal less amount of palatal inclination/insignificant intrusion of U1 (2.42°/0.14mm). MCPP treatment also resulted in significant changes in the skeletal measurements (SNA, ANB, occlusal and mandibular planes). Insignificant differences were found between subgroups in the retraction amount of maxillary incisors, as well as the upper and lower lips. In the follow-up of adolescents treated with MCPP, a significant amount of mesial movement, mesial tipping, and extrusion (2.94mm, 2.84°, and 3.94mm, respectively) was found. However, skeletal and occlusal corrections of the Class II relationship were maintained.

CONCLUSIONS

Maxillary total arch distalization using TADs can be an effective and stable treatment procedure. However, RCTs or prospective cohort studies are highly recommended to establish a clinical evidence regarding their efficiency.