International dental journal最新文献

{"title":"Corrigendum to ‘Mechanosensitive Yes-Associated Protein/TAZ–cGAS–STING Axis Induces Periodontal Ligament Fibroblasts Senescence and Mediates Compression-Induced Root Resorption’ [International Dental Journal, Volume 76, Issue 1, February 2026, 109303]","authors":"Zuping Wu , Siqi Bao , Qian Chen , Xiao Lu , Guzhe Guan , Ruifeng Song , Qianming Chen , Xiaoyan Chen","doi":"10.1016/j.identj.2026.109431","DOIUrl":"10.1016/j.identj.2026.109431","url":null,"abstract":"","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109431"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146165247","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":"Segmentation of Cemento-Osseous Dysplasias Using an Artificial Intelligence Algorithm","authors":"Duygu Çelik Özen ,&nbsp;Oğuzhan Altun ,&nbsp;Şuayip Burak Duman ,&nbsp;İbrahim Şevki Bayrakdar","doi":"10.1016/j.identj.2025.109340","DOIUrl":"10.1016/j.identj.2025.109340","url":null,"abstract":"<div><h3>Introduction and Aims</h3><div>In recent years, artificial intelligence (AI) has emerged as a powerful tool in medical imaging and in the analysis of complex bone pathologies such as cemento-osseous dysplasias. The aim of this study is to perform segmentation of cemento-osseous lesions using AI algorithms on cone beam computed tomography (CBCT) images and to evaluate the diagnostic performance of a diagnostic AI model designed for the diagnosis of cemento-osseous dysplasias.</div></div><div><h3>Methods</h3><div>In this study, cone beam computed tomography (CBCT) images taken for various reasons in radiology archive Department of Oral and Maxillofacial Radiology were retrospectively reviewed. As a result of radiographic evaluation, images recorded in the archive with at diagnosis of cemento-osseous dysplasias were determined. Fifty DICOM images were uploaded to the 3D slicer software, and cemento-osseous dysplasias were polygonally labeled and saved in Neuroimaging Informatics Technology Initiative (NIfTI) format. The nnU-Net v2-based automated algorithm for lesion segmentation was developed using the CranioCatch (CranioCatch, Eskişehir) software program using the PyTorch library in the Python framework (v3.6.1; Python Software Foundation). 80% of the data was used for training, 10% for validation and 10% for testing. The results were evaluated according to the criteria of precision, sensitivity, Dice Coefficient, Jaccard Index.</div></div><div><h3>Results</h3><div>The precision, sensitivity, Dice Coefficient and Jaccard Index for the segmentation of cemento-osseous dysplasias were 0.805, 0.889, 0.839, and 0.730, respectively.</div></div><div><h3>Conclusions</h3><div>The model we used achieved successful results in cemento-osseous dysplasias segments. The results of this planned study are promising in terms of providing a guidance for physicians in diagnosis.</div></div><div><h3>Clinical Relevance</h3><div>Automated segmentation of cemento-osseous lesions, where radiological images play a critical role in both diagnosis and follow-up, has the potential to enable precise and consistent definition of lesion boundaries and standardize the follow-up process, enabling more reliable data for long-term studies.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109340"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883297","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":"Balancing Demineralisation and Collagen Integrity: A Nanoscale Analysis of Etching Time in Human Dentin","authors":"Wafa Alzubaidi ,&nbsp;Emily Ganss ,&nbsp;Mina Vaez ,&nbsp;Mehrnoosh Neshatian ,&nbsp;Sebastian Aguayo ,&nbsp;Eszter Somogyi-Ganss ,&nbsp;Laurent Bozec","doi":"10.1016/j.identj.2026.109413","DOIUrl":"10.1016/j.identj.2026.109413","url":null,"abstract":"<div><h3>Objectives</h3><div>To investigate the effect of varying phosphoric acid etching times on dentin demineralisation and collagen fibril morphology and to identify a time-dependent balance between sufficient mineral removal and preservation of collagen nanostructure.</div></div><div><h3>Methods</h3><div>Dentin specimens from human third molars were etched with 37% phosphoric acid for 6 different durations: 0, 5, 10, 15, 30, and 60 seconds. Demineralisation was assessed using attenuated total reflectance Fourier-transform infrared (ATR-FTIR) spectroscopy by calculating the phosphate-to-amide I absorbance ratio. Collagen integrity was evaluated using scanning electron microscopy (SEM) and atomic force microscopy (AFM) imaging, with the percentage of visible D-banding serving as a morphometric indicator.</div></div><div><h3>Results</h3><div>FTIR analysis revealed a progressive reduction in the phosphate signal with increasing etching time, following an exponential decay pattern and approaching a plateau at approximately 10 seconds. AFM imaging revealed that the D-banding periodicity reached its peak at 10 seconds (mean: 71.7%) and subsequently decreased, with notable degradation observed at 30 and 60 seconds. Statistical analysis indicated significant differences in D-banding between the 10-second group and longer etching durations (<em>P</em> &lt; .05).</div></div><div><h3>Clinical significance</h3><div>This study provides nanoscale evidence that phosphoric acid etching of dentin for approximately 10 seconds achieves effective demineralisation while preserving collagen integrity. Longer etching times compromise fibril structure, underscoring the need for precise, time-controlled protocols to optimise resin–dentin bonding performance.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109413"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146137237","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":"Long Noncoding RNA SATB1-AS1 Suppresses Inflammatory Response and Injury in Dental Pulp Stem Cells Through the miR-15a-5p/E2F3 Axis","authors":"Shuyue Ding ,&nbsp;Yuan Shi","doi":"10.1016/j.identj.2026.109412","DOIUrl":"10.1016/j.identj.2026.109412","url":null,"abstract":"<div><h3>Introduction and aims</h3><div>Pulpitis represents a prevalent dental condition where inflammatory tissue damage can advance into irreversible stages or pulp death, ultimately compromising oral health-related quality of life. This study investigated the role and underlying mechanisms of long noncoding RNA SATB1-AS1 in pulpitis progression, offering potential therapeutic targets for this condition.</div></div><div><h3>Methods</h3><div>This study included 50 patients with irreversible pulpitis (pulpitis group) and 50 age- and gender-matched orthodontic extraction controls (control group). The expression of SATB1-AS1 in pulpitis tissues was assayed using real-time quantitative PCR. A pulpitis model was established by treating human dental pulp stem cells (DPSCs) with lipopolysaccharide (LPS). Evaluation of DPSC proliferation was performed using CCK-8. The levels of cell cycle-related proteins and inflammatory factors were measured by ELISA, and oxidative stress was evaluated by detecting superoxide dismutase, glutathione peroxidase, glutathione, and malondialdehyde. Bioinformatics tools were utilized to identify potential targets, followed by experimental validation through dual-luciferase reporter assays.</div></div><div><h3>Results</h3><div>Downregulation of SATB1-AS1 was identified in diseased pulpitis tissues and cell models. In LPS-induced DPSCs, SATB1-AS1 facilitated cell proliferation and modulated Cyclin D1 and p21 expression. Furthermore, SATB1-AS1 alleviated the LPS-induced release of IL-1β, IL-6, and IL-8, and mitigated oxidative stress-related injury by altering the levels of superoxide dismutase, glutathione peroxidase, glutathione, and malondialdehyde. MiR-15a-5p was negatively modulated by SATB1-AS1. Concurrent expression of miR-15a-5p eliminated the beneficial effects of SATB1-AS1 on DPSC function. Further investigation identified E2F3 as a target of miR-15a-5p, establishing the SATB1-AS1/miR-15a-5p/E2F3 axis as a regulatory pathway in LPS-treated DPSCs.</div></div><div><h3>Conclusion</h3><div>The findings indicate that SATB1-AS1 potentially mitigates inflammatory processes and oxidative damage via modulation of the miR-15a-5p/E2F3 axis, consequently suppressing pulpitis development.</div></div><div><h3>Clinical relevance</h3><div>This study suggests that SATB1-AS1 may serve as a novel diagnostic biomarker and therapeutic target for pulpitis, providing a potential strategy to preserve pulp vitality and improve clinical outcomes.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109412"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146131796","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":"Serum and Salivary microRNA Biomarkers Reveal Oxidative Stress Dysregulation in Coronary Artery Disease","authors":"Anandhi Sekar Arthisri ,&nbsp;Vishnu Priya Veeraraghavan ,&nbsp;A Thirumal Raj ,&nbsp;Raghavendra M. Shetty ,&nbsp;Shankargouda Patil","doi":"10.1016/j.identj.2025.109391","DOIUrl":"10.1016/j.identj.2025.109391","url":null,"abstract":"<div><h3>Introduction and aim</h3><div>Coronary artery disease (CAD) is a major cause of death. Epicardial adipose tissue (ECAT) contributes to CAD via oxidative stress, regulated by non-coding RNAs like miRNAs and lncRNAs.</div></div><div><h3>Methods</h3><div>Oxidative stress-related genes were retrieved from GeneCards. Microarray datasets (GSE64554 and GSE64563) identified differentially expressed genes and miRNAs in ECAT. PPI network and clustering revealed 51 key genes. Bottleneck analysis highlighted CD44, RUNX3, and KLRD1. miR-127-3p, regulating these genes, showed downregulation in ECAT, saliva, and plasma samples from 30 CAD patients.</div></div><div><h3>Results</h3><div>Out of 407 overlapping oxidative stress genes, 51 were strongly regulated via miRNA–lncRNA networks. CD44, RUNX3, and KLRD1 were key biomarkers. miR-127-3p showed significant downregulation (<em>P</em> &lt; .05) and the highest lncRNA interaction count. Its consistent decrease in ECAT, saliva, and plasma indicates systemic dysregulation in CAD.</div></div><div><h3>Conclusions</h3><div>CD44, RUNX3, and KLRD1 are oxidative stress biomarkers in ECAT, regulated by miR-127-3p. Its consistent downregulation in ECAT, plasma, and saliva supports its role in CAD pathogenesis and systemic relevance.</div></div><div><h3>Clinical relevance</h3><div>The consistent downregulation of miR-127-3p in plasma and saliva highlights its potential as a clinically relevant, non-invasive biomarker, supporting early detection and monitoring strategies for CAD through accessible body fluids.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109391"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035004","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":"Generative Artificial Intelligence and Large Language Models in Paediatric Dentistry: A Scoping Review","authors":"Tatsuya Akitomo ,&nbsp;Masakazu Hamada ,&nbsp;Shuma Hamaguchi ,&nbsp;Satoru Kusaka ,&nbsp;Ryota Nomura","doi":"10.1016/j.identj.2025.109401","DOIUrl":"10.1016/j.identj.2025.109401","url":null,"abstract":"<div><div>Large language models (LLMs), a type of artificial intelligence (AI), have been applied to various fields of dentistry in recent years. Although several reviews have examined AI applications in paediatric dentistry, most have focused on diagnostic assistance, and none have comprehensively addressed LLM use, including not only dental professionals but also patients or their guardians. PubMed, Scopus, and Web of Science were searched in September 2025 using the terms “Pediatric dentistry” AND “ChatGPT” OR “Gemini” OR “Claude” OR “Copilot” OR “DeepSeek.” Of the 262 articles identified, 30 met the eligibility criteria and were included in this review—24 published in 2025 and 6 in 2024. The largest group of studies (18 articles) focused on “answers to questions,” followed by 8 on “diagnostic assistance” and 3 on “dental examination.” LLMs demonstrated promising potential in paediatric dentistry across a range of users, including dental students, professionals, patients, and guardians. However, because LLMs can still provide inaccurate or misleading information, they should currently be used only as a supplementary tool. Recognizing these limitations and applying LLMs appropriately is essential. Continued research may further expand the scope and reliability of LLM applications in paediatric dentistry.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109401"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146073890","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":"4632427E13Rik Facilitates Jaw Marrow-Derived Mesenchymal Stem Cells Osteogenesis and Angiogenesis Under Hypoxia Through miR-34a-5p/Aldoa/Hif-1α Pathway","authors":"Zhenning Wang ,&nbsp;Yu Zhang ,&nbsp;Yan Wang ,&nbsp;Rui Xue ,&nbsp;Qiaozhen Qin ,&nbsp;Heyang Zhang ,&nbsp;Zhenhua Xu ,&nbsp;Shuirong Liu ,&nbsp;Liu Liu ,&nbsp;Xiaoxia Jiang ,&nbsp;Lulu Xu","doi":"10.1016/j.identj.2025.109364","DOIUrl":"10.1016/j.identj.2025.109364","url":null,"abstract":"<div><h3>Introduction and aims</h3><div>The regeneration and repair of maxillofacial bone defects remain a significant clinical challenge. Jaw marrow-derived mesenchymal stem cells (JMMSCs) have attracted considerable attention owing to their favourable biological properties; however, the low survival rate of transplanted MSCs in vivo has substantially limited their therapeutic application. In this study, we demonstrate that hypoxic preconditioning enhances both the osteogenic and angiogenic potential of JMMSCs in vitro and in vivo.</div></div><div><h3>Methods</h3><div>In vitro, the expression levels of osteogenic and angiogenic-related genes were assessed via qRT-PCR and Western blot following hypoxic preconditioning. In vivo, the impact of hypoxic preconditioning on the bone defect repair capacity of JMMSCs was evaluated. Micro–CT scanning was employed to compare microstructural changes at the defect sites. Microarray analysis identified differentially expressed long noncoding RNAs (lncRNAs) in JMMSCs subjected to hypoxic preconditioning. Subsequent bioinformatics analysis was conducted to explore potential regulatory interactions and key signalling pathways among lncRNAs, miRNAs, and mRNAs, followed by experimental validation.</div></div><div><h3>Results</h3><div>Microarray analysis revealed a significant upregulation of lnc-4632427E13Rik in JMMSCs following hypoxic preconditioning. Mechanistic studies demonstrated that lnc-4632427E13Rik functions as a molecular ‘sponge’ by sequestering miR-34a-5p, leading to activation of the Aldoa/ERK/Hif-1α signalling axis and subsequent promotion of both angiogenesis and osteogenesis in JMMSCs.</div></div><div><h3>Conclusion</h3><div>Our findings reveal hypoxic preconditioning as a highly effective strategy for enhancing the differentiation potential of JMMSCs, and further highlight the therapeutic potential of targeting the lnc-4632427E13Rik/miR-34a-5p/Aldoa axis to improve the bone repair capacity of JMMSCs.</div></div><div><h3>Clinical relevance</h3><div>The lnc-4632427E13Rik/miR-34a-5p/Aldoa axis significantly enhances the efficiency and reliability of bone regeneration, representing a promising therapeutic target for clinical applications in the repair of maxillofacial bone defects.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109364"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146018470","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":"Effect of Mitophagy on the Tension-Driven Osteogenic Differentiation of Periodontal Ligament Stem Cells During Ageing","authors":"Chuhan Peng,&nbsp;Yidan Zhang,&nbsp;Linna Bai,&nbsp;Xinyu Zhang,&nbsp;Bowen Xu,&nbsp;Kai Yang","doi":"10.1016/j.identj.2026.109408","DOIUrl":"10.1016/j.identj.2026.109408","url":null,"abstract":"<div><h3>Objectives</h3><div>Age-related differences in orthodontic tooth movement (OTM) and mechanical force-induced osteogenesis have been reported. Mitophagy plays a crucial role in bone metabolism and various age-related diseases, and BCL2-interacting protein 3 (BNIP3) is a mitophagy-related receptor. This study aimed to elucidate the role of mitophagy associated with BNIP3 on age-related changes in the orthodontic tension-driven osteogenic differentiation of periodontal ligament stem cells.</div></div><div><h3>Materials and methods</h3><div>Periodontal ligament stem cells (PDLSCs) from adolescent (6-week-old) and adult (8-month-old) rats were cultured and stretched using a Flexcell system. The effects of mitophagy associated with BNIP3 were assessed via real-time quantitative PCR and western blot analyses. Moreover, a rat model of OTM across different ages was established for in vivo analyses. The function of mitophagy in age-related osteogenic differentiation induced by orthodontic force on the tension side was evaluated via microcomputed tomography and immunohistochemistry analyses.</div></div><div><h3>Results</h3><div>Under tension, the expression of the mitophagy factor BNIP3, the autophagy factor microtubule-associated protein light chain 3 (LC3), and the osteogenic factors Runt-related transcription factor 2 (RUNX2) and Osterix (OSX) significantly increased in rPDLSCs over time. The expression of these factors was also upregulated in the rat OTM model under orthodontic force. Compared with the adolescent group, the adult group exhibited lower levels of mitophagy and osteogenic differentiation after tension both in vivo and in vitro. Enhanced mitophagy induced by carbonyl cyanide m-chlorophenyl hydrazone upregulated the expression of the aforementioned factors in an adult rat OTM model.</div></div><div><h3>Conclusions</h3><div>Mitophagy is associated with osteogenic activity induced by tension force in PDLSCs and may play a substantial role in regulating age-related changes in the OTM process.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109408"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146142434","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":"Dual Framework for Classification and Detection of Third Molar Impaction in Panoramic Radiographs","authors":"Zohaib Khurshid,&nbsp;Mousa Haney Alsleem,&nbsp;Fahad Ahmed Aljubairah,&nbsp;Hussain Adel Alghafli,&nbsp;Abdullah Othman Alasafirah,&nbsp;Bassam Abbas Alibrahim,&nbsp;Abdullah Abdulrahman Alshamrani,&nbsp;Abdulelah Nasser Alsuhaymi","doi":"10.1016/j.identj.2026.109430","DOIUrl":"10.1016/j.identj.2026.109430","url":null,"abstract":"<div><h3>Background</h3><div>The surgical extraction of impacted mandibular third molars present significant clinical challenges, where accurate preoperative assessment is crucial to mitigate risks such as Inferior Alveolar Nerve injury. Although artificial intelligence shows promise in dental radiology, existing approaches are often limited to binary classification, affected by class imbalance, and lack standardized evaluation protocols, thereby restricting their clinical applicability.</div></div><div><h3>Methods</h3><div>This study proposes two independent deep learning frameworks for comprehensive analysis of third molar impactions. The first framework is an end-to-end object detection pipeline employing modified YOLOv10 and YOLOv11n architectures enhanced with multihead self-attention. The second framework is a feature-based classification approach, where deep features extracted using ResNet50 and InceptionNetV3 are classified using traditional machine learning algorithms.</div></div><div><h3>Results</h3><div>Validated on a multinational dataset of 5796 expertly annotated orthopantomograms with high inter-rater agreement (<em>κ</em> = 0.92), the proposed frameworks demonstrated competitive performance. The Fine KNN classifier using ResNet50 features achieved the best classification performance, yielding 97.56% accuracy, 96.07% precision, 96.21% recall, and an F1-score of 96.10%, while InceptionNetV3-based classification achieved 97.33% accuracy with an F1-score of 95.30%. For object detection, YOLOv11n attained a mean average precision of 88.9% ([email protected]) and 85.7% ([email protected]:0.95), while maintaining substantially lower computational complexity (19.7 vs 28.4 GFLOPs). Ablation experiments confirmed that the integration of multihead self-attention modules and generative adversarial network-based augmentation improved detection performance by 6.4% mean average precision.</div></div><div><h3>Conclusions</h3><div>The proposed frameworks enable accurate and automated multiclass assessment of third molar impactions, achieving high diagnostic performance while preserving computational efficiency suitable for clinical deployment. This work advances artificial intelligence-assisted surgical planning by providing reliable F1-score-based evaluation, reliable real-time detection, and enhanced preoperative risk stratification in oral and maxillofacial surgery.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109430"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146142471","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":"Developing an Interpretable Machine Learning Framework to Predict and Analyse Early Childhood Caries in Children Aged 2 to 6 Years: A Single-centre Observational Study","authors":"Xinyue Yuan,&nbsp;Yiting Chu,&nbsp;Wenyan Cai","doi":"10.1016/j.identj.2026.109419","DOIUrl":"10.1016/j.identj.2026.109419","url":null,"abstract":"<div><h3>Background</h3><div>Early childhood caries (ECC) is a prevalent global oral health condition, exerting profound adverse effects on children’s oral health, general health, and quality of life. Its onset involves demographic, socioeconomic, behavioural, and clinical factors. While many studies report individual risks, systematic analyses to prioritise predictors remain limited.</div></div><div><h3>Methods</h3><div>This single-centre observational study included 900 children who visited the hospital between October 2022 and May 2024. Collected variables included age, parental background, feeding practices, general health status, oral hygiene and dietary habits. Univariate and multivariate analyses were conducted to identify factors associated with ECC. Five machine learning (ML) models – logistic regression (LR), random forest (RF), decision tree (DT), k-nearest neighbours (KNN) and support vector machine (SVM) – were developed to predict ECC. ECC presence or absence was used as the clinical outcome. Risk stratification classified children into low-, moderate-, and high-risk groups.</div></div><div><h3>Results</h3><div>Significant predictors included age, maternal education, vitamin supplementation during pregnancy and for the child, carbohydrate intake, nighttime feeding behaviours, cessation timing, light exposure during sleep and outdoor activity (<em>P</em> &lt; .05). LR achieved the highest accuracy (99.4%), followed by SVM (98.9%), RF (96.7%), DT (95.0%) and KNN (91.1%).</div></div><div><h3>Conclusion</h3><div>The machine learning models effectively identified key determinants of ECC, underscoring the critical roles of maternal education, dietary patterns, and lifestyle-related factors. Risk-based stratification derived from these models may inform targeted early preventive interventions in both clinical and community settings, thereby contributing to a reduction in the overall burden of ECC.</div></div>","PeriodicalId":13785,"journal":{"name":"International dental journal","volume":"76 2","pages":"Article 109419"},"PeriodicalIF":3.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146131786","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}