Journal of Dental Research最新文献

{"title":"Impact of Poverty Reduction on Oral Health Outcomes among US Adults.","authors":"U Cooray,A Singh,J Aida,G Tsakos,M A Peres","doi":"10.1177/00220345251323183","DOIUrl":"https://doi.org/10.1177/00220345251323183","url":null,"abstract":"Poor oral health is a public health issue in the United States, disproportionately affecting people in poverty. This cross-sectional study investigates the impact of reducing absolute and relative poverty on the prevalence of periodontitis, caries, and dental pain among US adults. Data from 13,139 adults aged 30 to 70 y who completed dental examinations in the 2011-2018 National Health and Nutrition Examination Surveys were used. Periodontitis and dental caries outcomes were assessed with the 2011-2014 surveys (n = 6,563). Assessment of absolute and relative poverty was based on the poverty income ratio established by the US Census Bureau. Hypothetical counterfactual scenarios were emulated to assess the impact of poverty reductions (10%, 25%, and 50%) on periodontitis, dental caries, and dental pain. A targeted minimum loss-based estimator was used to estimate the outcomes under each scenario adjusted for age, sex, race, comorbidity, and marital status. Reductions in absolute and relative poverty were associated with a lower prevalence of oral disease. A 50% reduction in absolute poverty would avert 1.1 million cases of periodontitis, 0.4 million individuals with dental caries, and 0.6 million dental pain cases. A similar reduction in relative poverty would avert 5.4 million cases of periodontitis, 3.8 million individuals with caries, and 2 million cases of dental pain. The greatest impact was seen with a 50% relative poverty reduction: 12% reduction in periodontitis (prevalence ratio [PR], 0.88; 95% CI, 0.85 to 0.92), 13% reduction in caries (PR, 0.87; 95% CI, 0.81 to 0.92), and 18% reduction in frequent dental pain (PR, 0.82; 95% CI, 0.73 to 0.91). These findings highlight the potential of poverty reduction, especially relative poverty, to significantly lower the US oral disease burden and emphasize policy importance for reducing income inequality to achieve equitable oral health.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"31 1","pages":"220345251323183"},"PeriodicalIF":7.6,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143914873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SDoH Impact on Periodontal Disease Using Machine Learning and Dental Records","authors":"J. Patel, M. Badi, R. Katiyar, C. Ogwo, R.C. Wiener, T. Tiwari, U. Sambamoorthi, T. Folks","doi":"10.1177/00220345251328968","DOIUrl":"https://doi.org/10.1177/00220345251328968","url":null,"abstract":"The impact of social determinants of health (SDoH) on periodontal disease (PD) is critical to study, as a deeper understanding of SDoH offers significant potential to inform policy and help clinicians provide holistic patient care. The use of machine learning (ML) to analyze the association of SDoH with PD provides significant advantages over traditional statistical methods. While statistical approaches are effective for identifying trends, they often struggle with the complexity and unstructured nature of data from dental electronic health records (DEHRs). The objective of this study was to determine the association between PD and SDoH using big data through linked DEHR and census data using ML. We used the records of 89,937 unique patients (754,414 longitudinal records) from the Temple University School of Dentistry who received at least 1 treatment between 2007 and 2023. Patient PD outcomes were categorized based on progression, improvement, or no change, using longitudinal data spanning up to 16 y. We applied ML models, including logistic regression, Gaussian naive Bayes, random forest, and XGBoost, to identify SDoH predictors and their associations with PD. XGBoost demonstrated the best performance with 94% accuracy and high precision, recall, and F1 scores. SHapley Additive exPlanations (SHAP) values were used to provide explainable ML analysis. The leading predictors for PD progression were higher social vulnerability index, poverty, population density, fewer dental offices, more fast-food restaurants, longer travel times, higher stress levels, tobacco use, and multiple comorbidities. Our findings underscore the critical role of SDoH in PD progression and oral health inequity, advocating for the integration of these factors in PD risk assessment and management. This study also demonstrates the potential of big data analytics and ML in providing valuable insights for clinicians and researchers to study oral health disparities and promote equitable health outcomes.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"113 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143909703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preclinical Evaluation of an Interactive Image Search System of Oral Pathology","authors":"R.R. Herdiantoputri, D. Komura, M. Ochi, Y. Fukawa, K. Oba, M. Tsuchiya, Y. Kikuchi, Y. Matsuyama, T. Ushiku, T. Ikeda, S. Ishikawa","doi":"10.1177/00220345251329042","DOIUrl":"https://doi.org/10.1177/00220345251329042","url":null,"abstract":"The limited number of specialists and diseases’ long-tail distribution create challenges in diagnosing oral tumors. Health care facilities with sole practicing pathologists face difficulties when encountering the rare cases. Such specialists may lack prior exposure to uncommon presentations, needing external reference materials to formulate accurate diagnoses. An image search or content-based image retrieval (CBIR) system may help diagnose rare tumors by providing histologically similar reference images, thus reducing the pathologists’ workload. However, the effectiveness of CBIR systems in aiding pathologists’ diagnoses through interactive use has not been evaluated. We conducted a remote evaluation in a near-clinical environment using Luigi-Oral, an interactive patch-based CBIR system that uses deep learning to diagnose oral tumors. The database comprised 54,676 image patches at multiple magnifications from 603 cases across 85 oral tumor categories. We recruited 15 general pathologists and 13 oral pathologists with varied experience to evaluate 10 retrospective test cases from 2 institutions using this dedicated system. At top-1 and top-3 differential diagnoses, the overall diagnostic accuracy among the 2 groups was significantly higher with Luigi-Oral than without (12.05% and 21.61% increase, <jats:italic>P</jats:italic> = 0.002 and <jats:italic>P</jats:italic> &lt; 0.001, respectively). Improvements were more evident for tumor cases in which the category was underrepresented in the database, benefiting novice and experienced pathologists. Misdiagnoses using Luigi-Oral could be due to inappropriate query input, poor retrieval performance in cases with a rare morphologic type, the difficulty of diagnosis without elaborate clinical information, or the system’s inability to retrieve accurate categories with convincing images. This study proves the clinical usability of an interactive CBIR system and highlights areas for improvement to ensure adequate assistance for pathologists, which potentially reduces pathologists’ workload and provides accessible specialist-level histopathology diagnosis.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"18 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143909708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Behavioral Pathway between Social Support and Network, and Edentulism","authors":"F. Alobaidi, E. Heidari, W. Sabbah","doi":"10.1177/00220345251329337","DOIUrl":"https://doi.org/10.1177/00220345251329337","url":null,"abstract":"The aims of this study were to evaluate how behaviors cluster together and to investigate the relationship among cluster of behaviors, social support and network, socioeconomic factors, and edentulism in older English adults. Data on social factors (Wave 3, 2006/07), behaviors (Wave 5, 2010/11), and edentulism (Wave 7, 2014/15) were extracted from the English Longitudinal Study of Ageing (ELSA). Baseline demographic factors (gender, ethnicity, and age) were included. Latent class analysis (LCA) was conducted on 4 behaviors (smoking, alcohol intake, fruit and vegetable consumption, physical activity). Confirmatory factor analysis (CFA) was used to create 2 latent variables, social support and network (positive support, negative support, network), and socioeconomic factors (education, wealth, self-rated social status). Two models of structural equation modeling (SEM) were constructed to assess the direct and indirect effect of latent variables on edentulism. A total of 3,087 participants were included. In the LCA, a 2-class model was chosen: class 1 (risky) and class 2 (healthy). The first SEM model showed that social support and network was not linked directly to edentulism, but higher levels of social support and network predicted being dentate indirectly through cluster of behaviors. The second model additionally accounting for socioeconomic position showed that social support and network was not associated with edentulism directly or indirectly, but higher socioeconomic position predicted directly and indirectly being dentate. In both models, cluster of behaviors was associated with edentulism. The result of this study clearly shows that cluster of behaviors mediate the relationship between each of social support and socioeconomic position and edentulism. Actions to improve socioeconomic conditions might have strong effects on changing behaviors and improved oral health.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"36 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143909702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bioheterojunctions Prevent Tooth Caries via Cascade Antibacterial Strategy","authors":"J. Zhu, L. He, X. Xu, H. Wu, J. Li, B. Yan, Y. Deng, Y. Gao, K. Liang","doi":"10.1177/00220345251329334","DOIUrl":"https://doi.org/10.1177/00220345251329334","url":null,"abstract":"Tooth caries is a prevalent chronic oral disease with microorganisms as the initiating factor and carbohydrates as the key environmental factor. Clinical antimicrobial therapies rely mainly on broad-spectrum antibiotics, which usually increase the risk of bacterial resistance. Recently, phototherapy has shown powerful antibacterial effects, although it cannot effectively eliminate cariogenic microenvironments and the antibacterial effect is not sustained after the light is removed. Here, we developed novel bioheterojunctions (bio-HJs) comprising MXene/Ag <jats:sub>3</jats:sub> PO <jats:sub>4</jats:sub> (MX/AgP) and glucose oxidase (GOx), denoted MX/AgP-GOx, aiming at both the chemical and biological components of dental plaque biofilm. The bio-HJs decomposed the glucose rich in the cariogenic environment through GOx while providing abundant H <jats:sub>2</jats:sub> O <jats:sub>2</jats:sub> for subsequent Fenton reaction. Under near-infrared (NIR) light, the bio-HJs produced hyperthermia and generated large amounts of reactive oxygen species based on the above H <jats:sub>2</jats:sub> O <jats:sub>2</jats:sub> , exerting powerful phototherapy properties (log reduction: 1.45 log 10 CFU/mL). It is worth noting that MX/AgP-GOx still exerted antibacterial effects in the dark via Ag <jats:sup>+</jats:sup> bactericidal effects, Ag <jats:sup>0</jats:sup> NPs catalytic activity, and GOx-mediated glucose depletion (log reduction: 0.39 log 10 CFU/mL), ensuring a sustained anticaries effect after the removal of NIR light. In addition, the rat caries model revealed that MX/AgP-GOx significantly reduced enamel mineral loss and had good biocompatibility. This study constructed efficacy-cascade bio-HJs targeting the sugar-rich cariogenic microenvironment, which promotes subsequent photodynamic therapy and combines photothermal and metal ion synergistic antibacterial means to continuously and effectively eliminate biofilm and prevent the occurrence and development of tooth caries.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"15 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of TRPM2 in Oxidative Stress–Mediated Bone Loss in Periodontitis","authors":"Y. Jiang, J. Chen, S. Guo, W. Cui, Y. Zhou, X. Chen, D. Wang, X. Wang, L. Li, Y. Xu","doi":"10.1177/00220345251329330","DOIUrl":"https://doi.org/10.1177/00220345251329330","url":null,"abstract":"Oxidative stress has emerged as a critical player in the development and progression of periodontitis. Transient receptor potential melastatin 2 (TRPM2) is a crucial oxidative stress sensor, while its role in periodontitis and its relationship with the oxidative stress microenvironment remains poorly understood. The objective of this research is to unravel the mechanism by which reactive oxygen species (ROS) activate the TRPM2 channel, driving osteoclast differentiation and eventually leading to bone degradation in periodontitis. By doing so, we aim to provide novel insights into the initiation, progress, and potential treatment methodologies for bone loss instigated by periodontitis. In this study, our results revealed significant upregulation of TRPM2 expression in inflamed periodontal tissues and a close alliance with osteoclast differentiation. First, significant upregulation of TRPM2 in periodontitis, with a clear association with osteoclast differentiation, was observed based on the GEO database. In addition, enhanced levels of TRPM2 and oxidative stress markers were evident in samples from both periodontitis patients and the mouse model of periodontitis. Importantly, the ablation of TRPM2 distinctly alleviated alveolar bone resorption in periodontitis-affected mice. In vitro assays concluded that ROS-induced TRPM2 activation fostered osteoclast differentiation and amplification of osteoclast-related genes. Moreover, RNA-seq results illuminated a close alliance of TRPM2 with osteoclast differentiation, oxidative phosphorylation, mitochondrial inner membrane, and mitochondrial protein complexes. Further validation indicated that damaged mitophagy could overproduce ROS to activate TRPM2 as a positive regulator of osteoclast differentiation via the Ca <jats:sup>2+</jats:sup> /NFATc1 signaling pathway. Finally, we conducted in vivo and in vitro interventions using a TRPM2 inhibitor and found that the inhibition of TRPM2 significantly alleviated bone loss induced by periodontitis. Consequently, our results suggest that TRPM2 plays a crucial role in triggering osteoclast differentiation in periodontitis’s oxidative stress microenvironment, signifying a potential therapeutic target for prevention and treatment of bone erosion induced by periodontitis.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"52 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dimethyl Citraconate Alleviates Periodontitis via Activating the NRF2 Cascade","authors":"Y. Wang, Y. Li, Y. Cai, X. Yang, H. Li, Q. Wang, D. Huang, L. Liu, Z. Fan, Q. Yuan, Y. Wang","doi":"10.1177/00220345251319249","DOIUrl":"https://doi.org/10.1177/00220345251319249","url":null,"abstract":"Nuclear factor erythroid 2–related factor 2 (NRF2) is a pivotal transcription factor that regulates redox signaling, playing a protective role in inflammation. Citraconate is verified as the strongest NRF2 agonist among its isomers. Dimethyl citraconate (DMC), an esterified derivative of citraconate, holds the potential for activating NRF2 and relieving inflammation. Here, we show that DMC is a strong NRF2-activating compound, stabilizing the intracellular NRF2 level and its nuclear translocation. DMC increases the expression levels of NRF2 downstream genes, thereby restricting the accumulation of reactive oxygen species and performing anti-inflammatory functions. The local administration of DMC effectively alleviates periodontal destruction in a ligation-induced periodontitis mouse model, elevating the NRF2 levels and downstream antioxidant enzymes. Moreover, the protective effect of DMC against periodontitis is absent in <jats:italic> Nfe2l2 <jats:sup>-/-</jats:sup> </jats:italic> mice. Mechanically, DMC prolongs the half-life of NRF2 and facilitates its dissociation from KEAP1 (Kelch-like ECH-associated protein 1), which suggests that DMC interrupts the crosstalk between KEAP1 and NRF2. Collectively, our findings illustrate the role of DMC in activating NRF2 and ameliorating periodontal inflammation, suggesting its therapeutic potential for inflammation-related diseases.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"31 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Caries Is the Hub of a Complex Network of Chronic Diseases across the Life Decades","authors":"S. Alves-Costa, F.A. Rodrigues, A.A. Ferraro, G.G. Nascimento, F.R.M. Leite, B.F. Souza, C.C.C. Ribeiro","doi":"10.1177/00220345251317487","DOIUrl":"https://doi.org/10.1177/00220345251317487","url":null,"abstract":"Caries precedes periodontitis; both may predict fatal noncommunicable diseases (NCDs) decades in advance. However, the complex network of relationships between these and other NCDs remains unclear. Understanding the intricate nonlinear connections among NCDs from the early life stages holds profound significance for public health management strategies to prevent NCDs. Accordingly, we modeled the connections among NCDs and identified the underlying patterns in the US population from childhood to elderhood. Indicators of metabolic risks, diabetes, and cancer, as well as cardiovascular, autoimmune, mental, respiratory, and oral diseases, were collected from National Health and Nutrition Examination Survey data (2011–2012 and 2013–2014 cycles), encompassing 4 age groups of Americans aged 1 to ≥60 y. Diseases were represented as nodes in the complex network analysis, and edges indicated their co-occurrences. To characterize the networks, we computed degree, betweenness, eigenvector, local transitivity, assortative mixing, Shannon entropy, and cluster coefficients. Caries was the central hub in all models. Caries and obesity were linked since the first years of life, and with age, new diseases became connected, increasing network complexity with Shannon entropy from −2.79 to −4.07. Depression plays an essential role in adult life; however, episodes of forgetting and mental confusion surpass depression’s significance in elderhood. The centrality of diabetes, cardiovascular disease, and cancer increases with age, peaking at ≥60 y, with diabetes being the most prominent. All groups had coefficients indicating that NCDs were highly connected, with cluster coefficients of 0.85 to 0.98 and assortativity mixing of −0.23 to −0.06. Caries was the central element over the decades, with the other diseases orbiting around it. It was mainly linked to overweight/obesity from early childhood. Integrated strategies targeting shared risk factors for caries and obesity can boost childhood health and potentially affect the development of other NCDs later.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"8 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Splicing Defects and Cell Death Cause SF3B2 -Linked Craniofacial Microsomia","authors":"S. Rao, K.E.N. Watt, L. Maili, M. Lamb, E. Farrow, H. Hassan, K. Weaver, B. Miller, S. Dash, L.L. Cox, L. Gallacher, S.G. Kant, M. Gibson, T. Pastinen, D. Li, E.J.K. Bhoj, H. Zhu, J. Zhang, Y.-B. Zhang, T.Y. Tan, P.A. Trainor, T.C. Cox","doi":"10.1177/00220345251325818","DOIUrl":"https://doi.org/10.1177/00220345251325818","url":null,"abstract":"Craniofacial microsomia (CFM) is a genetically and phenotypically heterogeneous disorder characterized by hypoplasia of facial tissue that is often asymmetric. Affected tissues typically include the ears (external and internal), mandible, and maxilla, but various extracranial anomalies have also been reported. Loss-of-function variants in the <jats:italic>SF3B2</jats:italic> gene have recently been reported in 8 cases of CFM, representing one of the more common genetic causes identified to date. To better define the full phenotypic spectrum associated with variants in <jats:italic>SF3B2</jats:italic> , we report novel loss-of-function variants in <jats:italic>SF3B2</jats:italic> in 5 new families with CFM. Furthermore, to determine the mechanism by which <jats:italic>SF3B2</jats:italic> loss-of-function perturbs craniofacial development, we established <jats:italic>sf3b2</jats:italic> -null mutant zebrafish, which exhibited severe deficiencies in craniofacial cartilage and bone progenitors due to elevated apoptosis and reduced proliferation of cranial neural crest cells. In addition, we generated a heterozygous truncating variant of <jats:italic>SF3B2</jats:italic> in human induced pluripotent stem cells using CRISPR/Cas9 gene editing. Differentiation of these cells into neural crest cells was accompanied by increased cell death and reduced proliferation. RNA sequencing of <jats:italic>sf3b2</jats:italic> mutant zebrafish revealed widespread disruption of mRNA splicing, including <jats:italic>mdm2</jats:italic> , a key regulator of Tp53-mediated apoptosis. Genetic inhibition of <jats:italic>tp53</jats:italic> in <jats:italic>sf3b2</jats:italic> mutants demonstrated that <jats:italic>tp53</jats:italic> inhibition reduces early cell death but does not improve proliferation or craniofacial cartilage development. Therefore, our functional studies indicate that widespread mRNA splicing disruption, in addition to Tp53-dependent cell death, contributes to the craniofacial features observed in <jats:italic>SF3B2</jats:italic> -related CFM.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"53 1","pages":""},"PeriodicalIF":7.6,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143876005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Diagnosis of Cervical Lymph Node Metastasis Using a CNN Model.","authors":"X Xu,L Xi,J Zhu,C Feng,P Zhou,K Liu,Z Shang,Z Shao","doi":"10.1177/00220345251322508","DOIUrl":"https://doi.org/10.1177/00220345251322508","url":null,"abstract":"Lymph node (LN) metastasis is a prevalent cause of recurrence in oral squamous cell carcinoma (OSCC). However, accurately identifying metastatic LNs (LNs+) remains challenging. This prospective clinical study aims to test the effectiveness of our convolutional neural network (CNN) model for identifying OSCC cervical LN+ in contrast-enhanced computed tomography (CECT) in clinical practice. A CNN model was developed and trained using a dataset of 8,380 CECT images from previous OSCC patients. It was then prospectively validated on 17,777 preoperative CECT images from 354 OSCC patients between October 17, 2023, and August 31, 2024. The model's predicted LN results were provided to the surgical team without influencing surgical or treatment plans. During surgery, the predicted LN+ were identified and sent for separate pathological examination. The accuracy of the model's predictions was compared with those of human experts and verified against pathology reports. The capacity of the model to assist radiologists in LN+ diagnosis was also assessed. The CNN model was trained over 40 epochs and successfully validated after each. Compared with human experts (2 radiologists, 2 surgeons, and 2 students), the CNN model achieved higher sensitivity (81.89% vs. 81.48%, 46.91%, 50.62%), specificity (99.31% vs. 99.15%, 98.36%, 96.27%), LN+ accuracy (76.19% vs. 75.43%, P = 0.854; 40.64%, P < 0.001; 37.44%, P < 0.001), and clinical accuracy (86.16% vs. 83%, 61%, 56%). With the model's assistance, the radiologists surpassed both the previous predictive results without the model's support and the model's performance alone. The CNN model demonstrated an accuracy comparable to that of radiologists in identifying, locating, and predicting cervical LN+ in OSCC patients. Furthermore, the model has the potential to assist radiologists in making more accurate diagnoses.","PeriodicalId":15596,"journal":{"name":"Journal of Dental Research","volume":"11 1","pages":"220345251322508"},"PeriodicalIF":7.6,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}