Artificial intelligence and machine learning in orthodontics

Comparison Between an Expert Operator an Inexperienced Operator, and Artificial Intelligence Software: A Brief Clinical Study of Cephalometric Diagnostic

INTRODUCTION

Artificial intelligence (AI) is constantly developing in several medical areas and has become useful to assist with treatment planning. Orthodontics and maxillofacial surgery use AI-based technology to identify and select cephalometric points for diagnostics. Although some studies have shown promising results from the use of AI, the evidence is still limited. Hence, additional investigation is justified.

MATERIALS AND METHODS

In this retrospective study, 2 human operators (1 expert and 1 inexperienced) and 1 software analyzed 30 lateral cephalograms of individuals with orthodontic treatment indications. They measured 10 cephalometric variables and then 2 weeks later, repeated measurements on 30% of the sample. We evaluated the reliability of the measurements between the 2-time points and the differences in the means between the expert operator and the AI software and between the expert and inexperienced operators.

RESULTS

There was high reliability for the expert operator and AI measurements, and moderate reliability for the inexperienced operator measurements. There were some significant differences in the means produced by the AI software and the inexperienced operator compared with the expert operator.

CONCLUSION

Although AI is useful for cephalometric analysis, it should be used with caution because there are differences compared with analysis by humans.

Cephalometric analysis performance discrepancy between orthodontists and an artificial intelligence model using lateral cephalometric radiographs

PURPOSE

The purpose of the present clinical study was to compare the Ricketts and Steiner cephalometric analysis obtained by two experienced orthodontists and artificial intelligence (AI)-based software program and measure the orthodontist variability.

MATERIALS AND METHODS

A total of 50 lateral cephalometric radiographs from 50 patients were obtained. Two groups were created depending on the operator performing the cephalometric analysis: orthodontists (Orthod group) and an AI software program (AI group). In the Orthod group, two independent experienced orthodontists performed the measurements by performing a manual identification of the cephalometric landmarks and a software program (NemoCeph; Nemotec) to calculate the measurements. In the AI group, an AI software program (CephX; ORCA Dental AI) was selected for both the automatic landmark identification and cephalometric measurements. The Ricketts and Steiner cephalometric analyses were assessed in both groups including a total of 24 measurements. The Shapiro-Wilk test showed that the data was normally distributed. The t-test was used to analyze the data (α = 0.05).

RESULTS

The t-test analysis showed significant measurement discrepancies between the Orthod and AI group in seven of the 24 cephalometric parameters tested, namely the corpus length (p = 0.003), mandibular arc (p < 0.001), lower face height (p = 0.005), overjet (p = 0.019), and overbite (p = 0.022) in the Ricketts cephalometric analysis and occlusal to SN (p = 0.002) and GoGn-SN (p < 0.001) in the Steiner cephalometric analysis. The intraclass correlation coefficient (ICC) between both orthodontists of the Orthod group for each cephalometric measurement was calculated.

CONCLUSIONS

Significant discrepancies were found in seven of the 24 cephalometric measurements tested between the orthodontists and the AI-based program assessed. The intra-operator reliability analysis showed reproducible measurements between both orthodontists, except for the corpus length measurement.

CLINICAL SIGNIFICANCE

The artificial intelligence software program tested has the potential to automatically obtain cephalometric analysis using lateral cephalometric radiographs; however, additional studies are needed to further evaluate the accuracy of this AI-based system.

Bone cement reinforcement improves the therapeutic effects of screws in elderly patients with pelvic fragility factures

BACKGROUND

Pelvic fragility fractures in elderly individuals present significant challenges in orthopedic and geriatric medicine due to reduced bone density and increased frailty associated with aging.

METHODS

This study involved 150 elderly patients with pelvic fragility fractures. The patients were divided into two groups, the observation group (Observation) and the control group (Control), using a random number table. Artificial intelligence, specifically the Tianji Orthopedic Robot, was employed for surgical assistance. The observation group received bone cement reinforcement along with screw fixation using the robotic system, while the control group received conventional screw fixation alone. Follow-up data were collected for one-year post-treatment.

RESULTS

The observation group exhibited significantly lower clinical healing time of fractures and reduced bed rest time compared to the control group. Additionally, the observation group experienced less postoperative pain at 1 and 3 months, indicating the benefits of bone cement reinforcement. Moreover, patients in the observation group demonstrated significantly better functional recovery at 1-, 3-, and 6-months post-surgery compared to the control group.

CONCLUSION

The combination of bone cement reinforcement and robotic technology resulted in accelerated fracture healing, reduced bed rest time, and improved postoperative pain relief and functional recovery.

Assessing the impact of occlusal plane rotation on facial aesthetics in orthodontic treatment: a machine learning approach

BACKGROUND

Adequate occlusal plane (OP) rotation through orthodontic therapy enables satisfying profile improvements for patients who are disturbed by their maxillomandibular imbalance but reluctant to surgery. The study aims to quantify profile improvements that OP rotation could produce in orthodontic treatment and whether the efficacy differs among skeletal types via machine learning.

MATERIALS AND METHODS

Cephalometric radiographs of 903 patients were marked and analyzed by trained orthodontists with assistance of Uceph, a commercial software which use artificial intelligence to perform the cephalometrics analysis. Back-propagation artificial neural network (BP-ANN) models were then trained based on collected samples to fit the relationship among maxillomandibular structural indicators, SN-OP and P-A Face Height ratio (FHR), Facial Angle (FA). After corroborating the precision and reliability of the models by T-test and Bland-Altman analysis, simulation strategy and matrix computation were combined to predict the consequent changes of FHR, FA to OP rotation. Linear regression and statistical approaches were then applied for coefficient calculation and differences comparison.

RESULTS

The regression scores calculating the similarity between predicted and true values reached 0.916 and 0.908 in FHR, FA models respectively, and almost all pairs were in 95% CI of Bland-Altman analysis, confirming the effectiveness of our models. Matrix simulation was used to ascertain the efficacy of OP control in aesthetic improvements. Intriguingly, though FHR change rate appeared to be constant across groups, in FA models, hypodivergent group displayed more sensitive changes to SN-OP than normodivergent, hypodivergent group, and Class III group significantly showed larger changes than Class I and II.

CONCLUSIONS

Rotation of OP could yield differently to facial aesthetic improvements as more efficient in hypodivergent groups vertically and Class III groups sagittally.

Call for algorithmic fairness to mitigate amplification of racial biases in artificial intelligence models used in orthodontics and craniofacial health

Machine Learning (ML), a subfield of Artificial Intelligence (AI), is being increasingly used in Orthodontics and craniofacial health for predicting clinical outcomes. Current ML/AI models are prone to accentuate racial disparities. The objective of this narrative review is to provide an overview of how AI/ML models perpetuate racial biases and how we can mitigate this situation. A narrative review of articles published in the medical literature on racial biases and the use of AI/ML models was undertaken. Current AI/ML models are built on homogenous clinical datasets that have a gross underrepresentation of historically disadvantages demographic groups, especially the ethno-racial minorities. The consequence of such AI/ML models is that they perform poorly when deployed on ethno-racial minorities thus further amplifying racial biases. Healthcare providers, policymakers, AI developers and all stakeholders should pay close attention to various steps in the pipeline of building AI/ML models and every effort must be made to establish algorithmic fairness to redress inequities.

Artificial intelligence in orthodontics and orthognathic surgery: a bibliometric analysis of the 100 most-cited articles

BACKGROUND

The application of artificial intelligence (AI) in orthodontics and orthognathic surgery has gained significant attention in recent years. However, there is a lack of bibliometric reports that analyze the academic literature in this field to identify publishing and citation trends. By conducting an analysis of the top 100 most-cited articles on AI in orthodontics and orthognathic surgery, we aim to unveil popular research topics, key authors, institutions, countries, and journals in this area.

METHODS

A comprehensive search was conducted in the Web of Science (WOS) electronic database to identify the top 100 most-cited articles on AI in orthodontics and orthognathic surgery. Publication and citation data were obtained and further analyzed and visualized using R Biblioshiny. The key domains of the 100 articles were also identified.

RESULTS

The top 100 most-cited articles were published between 2005 and 2022, contributed by 458 authors, with an average citation count of 22.09. South Korea emerged as the leading contributor with the highest number of publications (28) and citations (595), followed by China (16, 373), and the United States (7, 248). Notably, six South Korean authors ranked among the top 10 contributors, and three South Korean institutions were listed as the most productive. International collaborations were predominantly observed between the United States, China, and South Korea. The main domains of the articles focused on automated imaging assessment (42%), aiding diagnosis and treatment planning (34%), and the assessment of growth and development (10%). Besides, a positive correlation was observed between the testing sample size and citation counts (P = 0.010), as well as between the time of publication and citation counts (P < 0.001).

CONCLUSIONS

The utilization of AI in orthodontics and orthognathic surgery has shown remarkable progress, particularly in the domains of imaging analysis, diagnosis and treatment planning, and growth and development assessment. This bibliometric analysis provides valuable insights into the top-cited articles and the trends of AI research in this field.

Compliance with retainer wear using audiovisual integration and reminder: a randomized clinical trial

Active audiovisual representation of instructions ensures vibrant knowledge acquisition and improves acquaintance needed for self-care with retainer wear. The aim of this trial is to assess the impact of audiovisual instructions with additional weekly electronic reminder messages on improving adherence to instructed wear time of Hawley retainer, periodontal outcomes, and participants' experiences. Fifty-two participants (mean age 26.1 y) planned for removable retention, were randomly assigned to two parallel groups to receive either (1) audiovisual instructions with an additional weekly reminder, or (2) verbal instructions alone. Each participant received a Hawley retainer equipped with a TheraMon microsensor and was instructed to wear it for 22 h daily. Participants were monitored for adherence to the wear time after 3 (T1) and 6 months (T2), and had their periodontal health and experiences assessed at T2. Overall, the mean objectively measured daily wear time at T1 was 14.9 (± 4.9 h), and 14.3 (± 5.4 h) at T2. After 3 months, no significant differences were found between the groups (p = 0.065), however, a significant difference favoring better compliance with wear instructions was observed in the audiovisual group after 6 months (p = 0.033). A non-significant difference was observed between both groups regarding the gingival (p = 0.165) and plaque index scores (p = 0.173). Participants' experiences were similar in both groups, except for satisfaction with the way of delivering instructions, being favorably reported in the audiovisual group. Audiovisual instructions with weekly reminders seem to have a significant effect on patient compliance in the longer term.Trial registration: TCTR20230220002.

Accuracy of thermal microsensors embedded in orthodontic retainers of different material composition and thickness: An in vitro study

Objectives: The present research aimed to assess the accuracy and precision of the TheraMon® microsensor embedded in different thicknesses of Hawley retainers (HR) for comparison with vacuum formed retainers (VFR).

Methods: Thirty microsensors contained within different thicknesses and composition of retainers were divided into three equal groups: Group A thick coverage HR (3 mm), Group B thin coverage HR (1 mm), and Group C VFR (1 mm). The microsensors were immersed in thermostatic water at a controlled temperature of 35°C, which corresponds to the average intra-oral temperature. After 1 week, data were gathered using the TheraMon® client software and analysed using ANOVA and Turkey’s HSD tests.

Results: All TheraMon® microsensors were functional and produced uninterrupted recordings during the 1-week test period. Thermal detection differed between the three removable retainer groups. A near accurate thermostatic water detection was noticed with the thin HR with a mean temperature of 34.81 ± 0.04°C, followed by VFR 34.77 ± 0.09°C, and finally the thick HR 34.73 ± 0.05°C (ANOVA p-value = 0.025). A between-group comparison showed a significant mean difference (MD) between the thin and thick HR groups (MD: 0.08, p-value = 0.01). However, there were no significant differences between VFR and neither the thick Hawley (MD: 0.04, p-value = 0.27) nor the thin Hawley group (MD: -0.03, p-value = 0.39).

Conclusion: A removable retainer’s variation in material thickness and composition could induce small but detectable changes in the precision of thermal detection by TheraMon® microsensors.