Orthodontics & Craniofacial Research最新文献

{"title":"Accuracy of Artificial Intelligence in Predicting the Treatment Effects of Headgear and/or Functional Appliance on the Maxillo-Mandibular Growth in Preadolescent Patients With Skeletal Class II Malocclusion.","authors":"Soichiro Yamada, Hee Ji Yoon, Youna Huh, Yoshinobu Yanagi, Jae Hyun Park, Kiyoshi Tai, Namkug Kim, Seung-Hak Baek","doi":"10.1111/ocr.70006","DOIUrl":"https://doi.org/10.1111/ocr.70006","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the accuracy of artificial intelligence (AI) in predicting the effects of headgear (HG) and/or functional appliance (FA) on the maxillo-mandibular growth in preadolescent patients with skeletal Class II (C-II) malocclusion.</p><p><strong>Materials and methods: </strong>The study included 206 Japanese preadolescent C-II patients treated with HG and/or FA, with serial lateral cephalograms taken at ages of 8 (T0) and 10 (T1). A single orthodontist with 7 years of experience identified 28 hard-tissue cephalometric landmarks. A Treatment Prediction Graph Convolutional Neural Network (TP-GCNN), integrating a high-resolution network and a graph neural network, was trained and validated using the landmarks' x- and y-coordinates. Data was split into training, validation and testing sets (ratio of 8:1:1; n = 164, n = 21 and n = 21). Model performance was assessed using the values of prediction error (PE, excellent, ≤ 0.5 mm; very good, 0.5-1.0 mm; good, 1.0-1.5 mm; acceptable, 1.5-2.0 mm; unsatisfactory, > 2.0 mm) and the degree of accurate prediction percentage (APP; very high, ≥ 90%; high, 70%-90%; medium, 50%-70%; low, < 50%).</p><p><strong>Results: </strong>The mean PE value was 1.45 mm. In terms of PE, all landmarks showed the accuracy above the 'acceptable' category. In terms of APP, 'High' APP was observed at Hinge axis, Pterygoid point, A-point, PNS, ANS, R1, R3 and Articulare. However, 'Low' APP was noted for Pm, Pogonion, B-point and Menton. The remaining landmarks demonstrated 'Medium' APP.</p><p><strong>Conclusion: </strong>This study demonstrates the potential of AI to reliably predict the effects of HG and/or FA treatment in preadolescent patients with Class II malocclusion.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144708405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Based Evaluation of Skeletal Maturation: A Comparative Analysis of Five Hand-Wrist Methods.","authors":"Serhat Tentaş, Samet Özden","doi":"10.1111/ocr.70008","DOIUrl":"https://doi.org/10.1111/ocr.70008","url":null,"abstract":"<p><strong>Objective: </strong>The study aims to evaluate the effectiveness of deep learning algorithms in skeletal age estimation by comparing the diagnostic reliability of five different hand-wrist maturation (HWM) assessment methods.</p><p><strong>Materials and methods: </strong>A total of 6572 hand-wrist radiographs from orthodontic patients aged 8-16 years were retrospectively analysed. Radiographs were categorised into five groups based on HWM classification methods: (I) Björk's nine-stage, (II) Hägg and Taranger's five-stage, (III) Chapman's four-stage, (IV) three-stage hook of hamate ossification based and (V) simplified three-stage Björk's classification based. YOLOv8x-based deep learning models were trained separately for each group. The dataset was split into training, validation and test subsets. Performance was evaluated using accuracy, precision, recall, F1 score and AUC metrics.</p><p><strong>Results: </strong>The YOLOv8x-cls model demonstrated high classification performance across all five groups. Group IV and Group II achieved the highest accuracy and F1 scores, with average F1 values of 0.99 and 0.96, respectively. Group III and Group V also showed strong performance (F1 = 0.93 and 0.92). In Group I, slightly lower classification performance was observed in the S-H2 and MP3-Cap stages (F1 = 0.72-0.74), which correspond to the pubertal growth peak, while early and late skeletal maturation stages were classified with high accuracy and F1 scores. ROC curve analysis further supported these findings, with AUC values for MP3-Cap and S-H2 recorded as 0.70 and 0.75, respectively, whereas higher AUC values were achieved in most other stages across all groups.</p><p><strong>Conclusion: </strong>Deep learning models proved effective in evaluating skeletal maturation across five different HWM methods. Particularly high performance was observed in anatomically distinct regions such as the MP3, adductor sesamoid and hamate bone, which can be reliably identified by general dentists, enabling earlier referrals and timely orthodontic interventions.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144699211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Double-Axis Maxillary Skeletal Expander Suggests Higher Expansion Efficiency in Early Activation: A Finite Element Analysis.","authors":"Kaviya Kanokpongsak, Prajak Jariyapongpaiboon, Sorapon Na Lampang, Phetcharat Dhammayannarangsi, Nicha Ungvijanpunya, Thanaphum Osathanon, Pornchai Jansisyanont, Nuttapol Limjeerajarus, Chalida Nakalekha Limjeerajarus","doi":"10.1111/ocr.70007","DOIUrl":"https://doi.org/10.1111/ocr.70007","url":null,"abstract":"<p><strong>Introduction: </strong>Conventional single-axis maxillary skeletal expanders (MSE) have some drawbacks, such as limited control over maxillary expansion and possible asymmetric expansion between the anterior nasal spine (ANS) and posterior nasal spine (PNS). This report introduces a double-axis maxillary skeletal expander (DAMSE) concept to overcome these drawbacks and enhance the efficiency of maxillary skeletal expansion.</p><p><strong>Materials and methods: </strong>Five different DAMSE designs were compared with a conventional single-axis MSE. Finite element analysis was performed to analyse their expansion efficiency, stress magnitude and distribution occurring in a simplified bone model.</p><p><strong>Results: </strong>DAMSE outperformed the single-axis MSE and provided better control over ANS and PNS expansion. During early activation, the highest expansion efficiency (31.7%) was achieved by DAMSE Model V, 13% more efficient than the single-axis MSE. This efficiency was increased to 100.8% by combining the DAMSE Model V with midpalatal suture surgery. However, with the simplified bone model, the current study could not demonstrate that DAMSE can resolve the issue of asymmetric expansion between ANS and PNS.</p><p><strong>Conclusions: </strong>An appropriately designed DAMSE can be a promising tool for maxillary expansion treatment. DAMSE offers more efficient treatment than the conventional single-axis MSE while maintaining similar levels of patient comfort and invasiveness.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144699212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Treatment Effects and Treatment Time in Adolescents With Crowded and Displaced Teeth Treated With Fixed Appliance Systems Without Extractions: A Multi-Centre Randomised Controlled Trial.","authors":"Linda Bokander Matilainen, Kristina Johansson, Michal Wiaderny, Anna Brechter, Sofia Petrén, Vincenzo D'Antò, Liselotte Paulsson","doi":"10.1111/ocr.70005","DOIUrl":"https://doi.org/10.1111/ocr.70005","url":null,"abstract":"<p><strong>Objectives: </strong>To assess and compare treatment effects and treatment time in adolescents with crowded and displaced teeth during and after non-extraction treatments using a passive self-ligating bracket system (PSLB) and a conventional bracket system (CB).</p><p><strong>Materials and methods: </strong>Consecutive adolescents (12-17 years old) with crowded and displaced teeth were randomised through computer generated block randomisation in a two-arm parallel-group design, to non-extraction fixed appliance treatment with either PSLB (Damon Q, n = 62) or CB (Victory, n = 70) at four orthodontic clinics. Study models and cephalograms were collected at baseline, post-alignment and post-treatment. Primary outcome was assessed with weighted Peer Assessment Rating index (wPAR) and secondary outcomes with Little's Irregularity Index (LII), and as transversal width (mm), incisor inclination (°), position (mm) and treatment time (months).</p><p><strong>Results: </strong>Intergroup differences in wPAR with mean score reductions of -24.07 (CB) and -22.11 (PSLB), LII upper/lower arch reductions of -9.02/-5.96 (CB) and -8.44/-5.29 (PSLB), and mean treatment times of 21.74 (CB) and 24.35 (PSLB) months were non-significant (NS). Lateral expansion was greater in the PSLB group during alignment; mean intergroup maxillary differences (MD) were 1.35 at inter-canines, 1.21 mm at first inter-premolars, and mandibular MD were 0.75 at first, 0.76 mm at second inter-premolars (p ≤ 0.019). Greater incisor proclination was observed in the CB group (L1NB, MD = 2.28°; ILiML, MD = 2.23°) (p ≤ 0.016). Intergroup differences post-treatment were NS.</p><p><strong>Conclusion: </strong>Great occlusal treatment outcomes were observed in both groups with no significant difference in treatment time. Although the expansion patterns differed during alignment, no significant intergroup difference remained after treatment.</p><p><strong>Trial registration: </strong>The protocol is registered on ClinicalTrials.gov (NCT05664282).</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144691093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of Nasal Airway Obstruction in an Orthodontic Population Using the NOSE Scale.","authors":"Rebecca Petts, Diana Ponsky, Luciane Macedo de Menezes, Tarek ElShebiny, Kristina Wolf, Juan Martin Palomo","doi":"10.1111/ocr.70004","DOIUrl":"https://doi.org/10.1111/ocr.70004","url":null,"abstract":"<p><strong>Introduction: </strong>Nasal Airway Obstruction is a common problem affecting 30% of the general population and significantly impacts the quality of life. The objective of this research was to determine nasal airway obstruction prevalence in a population seeking orthodontic treatment using the Nasal Obstruction Symptom Evaluation (NOSE) scale and to determine if practice modalities play a role.</p><p><strong>Methods: </strong>The sample consisted of 431 patients seeking orthodontic care who completed the NOSE survey at an orthodontic residency programme, a corporate practice, and a private practice.</p><p><strong>Results: </strong>Obstruction was not correlated with age, gender, or trauma (p < 0.05). The mean of all scores was 8.4 ± 14.7 (95% confidence interval [CI]: 7.0-9.8), ranging from 0 to 80 on a scale of 100. The prevalence of nasal airway obstruction in the orthodontic population was: mild or above-43.9% (95% CI: 39.1%-48.7%); moderate or above-11.4% (95% CI: 8.6%-14.9%); severe-2.6% (95% CI: 1.3%-4.5%); and extreme-0.2% (95% CI: 0.0%-1.3%). The Kruskal-Wallis test showed no significant difference among patients at the three locations.</p><p><strong>Conclusions: </strong>The Prevalence of Nasal Airway Obstruction (Mild to Extreme) in orthodontic populations was 43.9% (95% CI: 39.1%-48.7%), representing or slightly exceeding that of the general population. There was no significant difference between an orthodontic residency programme, a corporate practice, and a private practice, indicating that the results are widely applicable. Orthodontists are encouraged to use the NOSE scale as a risk assessment tool, providing additional healthcare services to patients and potentially improving their quality of life.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144601147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Facial Asymmetry Phenotypes in Adult Patients With Bilateral Cleft Lip and Palate and Skeletal Class III Malocclusion Using Principal Component Analysis and Cluster Analysis.","authors":"Mihee Hong, Su-Ji Yoon, Il-Hyung Yang, Jin-Young Choi, Jong-Ho Lee, Myung-Jin Kim, Jee Hyeok Chung, Sukwha Kim, Seung-Hak Baek","doi":"10.1111/ocr.70003","DOIUrl":"https://doi.org/10.1111/ocr.70003","url":null,"abstract":"<p><strong>Objective: </strong>To classify and characterise facial asymmetry (FA) phenotypes in adult patients with bilateral cleft lip and palate (BCLP) and skeletal Class III (C-III) malocclusion.</p><p><strong>Materials and methods: </strong>The samples consisted of 72 adult BCLP patients (56 males, 16 females; mean age, 21.0 years), who were candidates for orthognathic surgery (OGS) or had undergone OGS for the correction of C-III malocclusion. Because BCLP patients have two cleft sides, the vertically longer defect (VLD) side was used for the reference side. Twenty-three cephalometric parameters were measured in posteroanterior cephalograms taken at least 1month before OGS. Principal component analysis was performed to obtain seven representative parameters [ANS-deviation (mm), U1-deviation (mm), L1-deviation (mm), Me-deviation (mm), MaxAntOP-cant (°), MaxPostOP-cant (°), ManBorder-cant (°)]. K-means cluster analysis was conducted using these representative parameters. Differences in cephalometric parameters among the clusters were statistically analysed.</p><p><strong>Results: </strong>FA phenotypes were classified based on the deviation direction towards the VLD or less VLD side and the upward or downward cant in the VLD side. The classifications were: (1) Symmetry type (20.8%); (2) MxMn-VLD-dev & MxMn-no-cant type (22.2%); (3) MxMn-less-VLD-dev & Mnbase-VLD-down-cant type (9.7%); (4) Mn-less-VLD-dev & MxMn-VLD-down-cant type (20.8%); (5) MxMn-no-dev & MxMn-VLD-up-cant type (19.4%), and (6) MxMn-VLD-dev & MxMn-VLD-up-cant type (6.9%). The possible etiologies of FA phenotypes included ANS deviation, movement of the maxillary incisor by pre-operative orthodontic treatment, and adaptive growth or compensatory growth of the maxilla and/or mandible.</p><p><strong>Conclusion: </strong>This FA phenotype classification could serve as a guideline for diagnosis and OGS planning for BCLP patients.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144541773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low Tongue Posture Improvement Effect of Orofacial Myofunctional Therapy Comprehensive Study of Nasal Ventilation Condition Using Computational Fluid Dynamics and Dental Arch Morphology.","authors":"Kei Maeo, Takamasa Kitamura, Wakana Kohira, Yukari Suzuki, Yoshihito Yamakawa, Kimiko Ueda, Hitomi Ishii, Ryuzo Kanomi, Tomonori Iwasaki","doi":"10.1111/ocr.70000","DOIUrl":"https://doi.org/10.1111/ocr.70000","url":null,"abstract":"<p><strong>Objectives: </strong>Oral myofunctional therapy (OMFT) has been proposed as a potential treatment for improving low tongue posture (LTP) and alleviating obstructive sleep apnea. However, its effectiveness remains uncertain. This study aimed to quantify the effects of OMFT on LTP.</p><p><strong>Materials and methods: </strong>This study analysed pre- and post-treatment cone-beam computed tomography images from 43 children with LTP treated with rapid maxillary expansion (RME) only (mean age: 9.09 years, no-OMFT group), 46 children with LTP treated with RME plus OMFT (mean age: 9.40 years, OMFT group), and 20 children (mean age: 9.87 years, control group). The primary outcomes measured were intraoral airway volume (an indicator of LTP), nasal airway pressure differences (assessed using computational fluid dynamics), and maxillary dental arch width. Comparisons were made among groups, with the frequency and relationship between these measures investigated.</p><p><strong>Results: </strong>There were no significant differences between OMFT and no-OMFT groups before treatment. Post-treatment, the OMFT group showed significantly smaller intraoral airway volume (0.66 cm³) compared to the no-OMFT group (1.34 cm³). Nasal airway pressure drop was also significantly lower in the OMFT group (44.2 Pa) than in the no-OMFT group (143.3 Pa). The LTP improvement rate was significantly higher in the OMFT group (76.1%) than in the no-OMFT group (51.2%). Similarly, the improvement rate of nasal airway obstruction was significantly higher in the OMFT group than in the no-OMFT group.</p><p><strong>Conclusion: </strong>OMFT improves LTP and nasal airway obstruction. Improvements in nasal airway obstruction by OMFT are likely correlated with the observed improvements in LTP.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144541786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Compressive Stress and Inflammation Induce Ferroptosis in Periodontal Ligament Cells Through ACSL4 Activation in Orthodontically Induced Inflammatory Root Resorption.","authors":"Liyan Liu, Jie Zhang, Runze Zhang, Tian Wei, Chunmiao Jiang","doi":"10.1111/ocr.70002","DOIUrl":"https://doi.org/10.1111/ocr.70002","url":null,"abstract":"<p><strong>Objectives: </strong>Orthodontically induced inflammatory root resorption (OIIRR) is an inflammation induced by excessive orthodontic force in the periodontium. The aim of this study was to identify the role of ferroptosis in periodontal ligament cells in OIIRR and its underlying mechanism.</p><p><strong>Materials and methods: </strong>Human periodontal ligament cells (hPDLCs) were subjected to 2 g/cm² of compressive stress along with 20 ng/mL of interleukin-1β (IL-1β) stimulation for 24 h. The occurrence of ferroptosis in hPDLCs is detected by Western blot analysis and ferroptosis-related kits. For in vivo analyses, a mouse OIIRR model was established, and the ACSL4 inhibitor (Rosiglitazone, Rosi) was administered intraperitoneally. Micro-CT was employed to evaluate the occurrence of OIIRR, and immunohistochemical staining (IHC) was performed to detect changes in ferroptosis-related markers.</p><p><strong>Results: </strong>Upon applying compressive stress and IL-1β stimulation to hPDLCs, Western blot analysis showed an upregulation of the ferroptosis marker ACSL4 and a downregulation of GPX4, along with significant increases in ROS, MDA and Fe²⁺ levels, indicating enhanced ferroptosis. However, when hPDLCs were treated with Rosi (1 μM), ferroptosis was alleviated. Micro-CT analysis showed that root resorption volume decreased after Rosi application. Additionally, Ferroptosis-related markers changed significantly in the PDLCs in mice via IHC staining.</p><p><strong>Conclusions: </strong>ACSL4-mediated ferroptosis, triggered by compressive stress and inflammation in hPDLCs, contributed to the development of OIIRR. Rosi has been shown to inhibit OIIRR and serve as a novel therapeutic target for OIIRR treatment.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144529166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gender Distribution Among Invited Speakers at the Italian Orthodontic Society (SIDO) Conferences Held Between 2013 and 2023: A Cross-Sectional Analysis.","authors":"Valentina Lanteri, Alessandro Bruni, Andrea Abate, Cinzia Maspero, Elis Kola, Alessandro Ugolini","doi":"10.1111/ocr.70001","DOIUrl":"https://doi.org/10.1111/ocr.70001","url":null,"abstract":"<p><p>Scientific conferences play a key role in shaping professional visibility and recognition. Investigating gender balance among invited speakers can provide insight into broader patterns of inclusion in the context of orthodontic congresses. The purpose of this study was to evaluate gender representation among invited speakers at the Italian Orthodontic Society (SIDO) congresses from 2013 to 2023, identifying trends and potential disparities during this decade-long period. A cross-sectional review of the abstract books and programmes of the SIDO Spring and Winter congresses held between 2013 and 2023 was conducted. The gender, country of origin, affiliation, topic of presentation and H-index were recorded for each invited speakers. Presentations lasting less than 30 min, involving more than three speakers, focusing on non-orthodontic topics (e.g., dental hygiene or dental technician presentations) or held during sponsored sessions, roundtables and collateral events were excluded. Descriptive statistics were performed to summarise speaker characteristics. Univariate and multivariate logistic regression analyses were conducted to examine the effect of predictor variables, including year of presentation, country (non-Italian speakers), H-index (≥ 8) and affiliation (non-academic) on the likelihood of a speaker being female. The Mantel-Haenszel test for homogeneity of odds ratios (OR) was used to assess whether trends in female representation were consistent over time. The predefined level of statistical significance was set at p < 0.05 (two-sided). The analysis revealed a significant gender imbalance, with male speakers accounting for 77.2% and female speakers 22.8% throughout the study period (p < 0.001). Logistic regression indicated that the likelihood of a speaker being female increased by 6% for each additional year (OR: 1.055, 95% CI: 1.010-1.110, p = 0.015), while other variables such as country of origin, H-index and affiliation were not significant. The majority of speakers were from Italy (62.3%), followed by the United States (9.6%) and Spain (3.2%). The topics discussed most frequently were Interdisciplinary (14.2%), New Technologies (8.4%) and Clear Aligner Treatment (8.2%). A large proportion of the invited speakers lacked academic affiliation (36.4%). Although the proportion of female speakers at SIDO congresses remains limited, the data reveal a steady annual increase in female representation. Nevertheless, a substantial gender imbalance persists, indicating that initiatives aimed at improving diversity could contribute to a more balanced representation in the future.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144507271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building and Evaluating an Orthodontic Natural Language Processing Model for Automated Clinical Note Information Extraction.","authors":"Jay S Patel, Divakar Karanth","doi":"10.1111/ocr.12944","DOIUrl":"https://doi.org/10.1111/ocr.12944","url":null,"abstract":"<p><strong>Introduction: </strong>Malocclusion presents functional and aesthetic challenges, necessitating accurate diagnosis and treatment. However, variability in orthodontic treatment planning persists due to subjective assessments, limiting consistency and objectivity. Electronic dental records (EDRs) contain vast patient data that could address these challenges, but much of the rich clinical information is documented as free text, complicating analysis. This study aims to develop an Orthodontic Natural Language Processing (ONLP) model to extract structured orthodontics-related information from unstructured EDRs and identify critical features influencing malocclusion using machine learning (ML).</p><p><strong>Methods: </strong>Data from 7693 orthodontic patients were analysed to train, test and validate the ONLP and ML models. A gold-standard dataset was created through manual review. The ONLP model utilised supervised (Named Entity Recognition-NER) and unsupervised (K-means clustering) approaches to structure information from free text. Machine learning models, including Logistic Regression, Gaussian Naive Bayes, Random Forest and XGBoost, were subsequently applied to identify feature importance for malocclusion classification.</p><p><strong>Results: </strong>The ONLP model achieved 89% sensitivity, 92% specificity and 91% accuracy in extracting orthodontics-related information. The supervised model demonstrated 84% accuracy, 82% F1-score and 84% recall, excelling in identifying Classes I and III malocclusions but showing reduced sensitivity for Class II. Machine learning analysis highlighted key features for malocclusion classification: maxillary crowding, overjet and arch perimeter discrepancy for Class I; maxillary spacing and anterior crossbite for Class II; and dental midline deviation and occlusal wear for Class III.</p><p><strong>Conclusion: </strong>This study demonstrates a novel approach to automating orthodontic data extraction using the ONLP model, enabling advanced big data analytics and enhancing data-driven orthodontic research and care.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144294206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}