Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 30 appraisals
International dental journal
Deep Learning Based on Swin-Transformer and 3D U-Net: Implant Three-Dimensional Position Planning
INTRODUCTION AND AIMS: This study aimed to devise a deep learning-based model for the automated identification of anatomical mandibular lingual concavities in the posterior mandible and the prediction of biologically guided three-dimensional implant positions. METHODS: Cone-beam computed tomography (CBCT) images with single-tooth posterior mandibular edentulism were included. A deep learning framework was constructed utilizing 3D U-Net and Swin-Transformer. This framework was designed to perform automated segmentation of teeth, mandible, and the mandibular nerve canal; to classify morphological types of lingual concavities; and to identify implant key points with coordinate prediction. Model performance was assessed via five-fold cross-validation. RESULTS: The proposed model achieved Dice similarity coefficients ranging from 0.87 to 0.91 for dental segmentation. In the classification of mandibular lingual concavities, an accuracy of 0.92 to 0.97 was attained. Regarding the prediction of three-dimensional implant positions, the automatically generated plans maintained a safety margin of 3.20 to 3.89 mm from the mandibular nerve canal. Furthermore, sufficient bone volume was preserved at both cervical and apical implant levels, with buccal/lingual cervical bone widths averaging 4.94 to 5.78 mm. CONCLUSION: The deep learning model in this experiment performed well across different views and learning tasks in a retrospective internal validation setting. Furthermore, it demonstrated the ability to accurately identify relevant anatomical structures, and the predicted three-dimensional implant positions showed clinically acceptable safety margins in the internal validation cohort. CLINICAL RELEVANCE: This model provides a preliminary AI-assisted framework for identifying critical mandibular anatomical structures and generating biologically guided preliminary implant position suggestions, thereby helping to mitigate intraoperative complications and reduce the risk of postoperative mechanical and biological complications in preclinical evaluation.
2 Aug 2026
Read appraisal →Acta odontologica Scandinavica
Predicting gingival embrasure risk after invisible orthodontics using multimodal data and machine learning
OBJECTIVE: To develop and validate a risk prediction model for gingival embrasures after clear aligner therapy using multimodal oral data. METHODS: A retrospective study of 340 patients (December 2022-June 2025) was randomly divided into training (n = 238) and validation (n = 102) sets (7:3). Univariate analysis, multivariate logistic regression, and least absolute shrinkage and selection operator regression were applied to identify independent risk factors. Three machine learning models - random forest (RF), logistic regression, and support vector machine - were constructed based on seven core variables. Model performance was assessed using area under the receiver operating characteristic curve (AUC), calibration curves, decision curve analysis, and Shapley Additive Explanations (SHAP) values for interpretability. RESULTS: No significant baseline differences existed between sets (p > 0.05). Seven indicators were identified (p < 0.05). Multivariate analysis confirmed percentage of bleeding on probing-positive sites, interproximal alveolar bone height, and relative movement of adjacent teeth at target site as independent risk factors, while gingival thickness, proximal contact area, interdental papilla height, and buccal/lingual bone plate thickness were protective factors (p < 0.05). The RF model performed best: training AUC = 0.849 (95% CI: 0.786-0.912), validation AUC = 0.815 (95% CI: 0.720-0.910), with good calibration and net benefit. SHAP analysis highlighted gingival thickness and interproximal alveolar bone height as key predictors. CONCLUSION: A risk prediction model for post-clear aligner gingival embrasures was successfully developed and validated using multimodal oral data, with RF as the optimal algorithm. The model exhibits good discrimination, calibration, and clinical utility, which can be used as an objective auxiliary tool for individualized risk prediction following clear aligner therapy and supplement traditional clinical empirical judgment.
23 July 2026
Read appraisal →Acta odontologica Scandinavica
Obstructive sleep apnea and periodontitis: a systematic review with considerations on CPAP therapy
OBJECTIVE: To evaluate the association between obstructive sleep apnoea (OSA) and periodontitis and to assess the available evidence on the effects of continuous positive airway pressure (CPAP) therapy on periodontal status. MATERIALS AND METHODS: This review was conducted in accordance with Preferred Reporting Items for Systematic reviews and Meta-Analyses 2020 guidelines. Comprehensive literature searches were performed in Cochrane, PubMed, Scopus, and Web of Science. Study selection and data extraction were carried out independently by two reviewers. A total of 20 original studies met the inclusion criteria. Methodological quality was assessed using the Joanna Briggs Institute critical appraisal tool. RESULTS: Fourteen of the 20 studies (70%) reported a significant association between OSA and periodontitis. However, only two studies fulfilled all methodological quality criteria, indicating an overall moderate to low quality of evidence. Data on the effects of CPAP therapy on periodontal outcomes were limited, and the available studies generally showed no significant impact. CONCLUSIONS: Current evidence supports an association between OSA and periodontitis, suggesting that OSA may contribute to periodontitis. Robust, well-designed studies with larger sample sizes and rigorous methodology are needed to clarify the nature of this relationship and to determine whether CPAP therapy influences periodontal health.
17 July 2026
Read appraisal →Clinical oral investigations
Predicting occlusal force distribution from intraoral scans using deep learning: a pilot study
OBJECTIVES: This pilot study investigated whether occlusal force distribution measured by T-Scan can be predicted from intraoral scan images using deep learning. METHODS: Paired intraoral scan and T-Scan images from 26 subjects were analyzed. Following quality control, data were randomly partitioned at the subject level into training (n = 18), validation (n = 4), and independent test (n = 4; 8 image pairs) sets. Five deep learning architectures (U-Net, ResNet-UNet, Vision Transformer, CNN-Attention, and Pix2Pix) were trained to predict T-Scan force maps from occlusal scan images. Structural Similarity Index (SSIM) was predefined as the primary endpoint. Nonparametric statistical comparisons (Friedman test with Holm-corrected Wilcoxon post hoc analysis) and bootstrap confidence intervals were used. RESULTS: A significant difference in SSIM was observed among models (χ² = 19.3, p = 0.00069). CNN-Attention achieved the highest structural similarity (mean SSIM 0.501 ± 0.030), significantly outperforming U-Net, Vision Transformer, and ResNet-UNet (adjusted p < 0.05), while not differing significantly from Pix2Pix. Pix2Pix demonstrated the lowest mean absolute error (0.237 ± 0.018), indicating superior pixel-level intensity approximation. Validation curves revealed distinct optimization behaviors, with adversarial training showing late-stage improvements in SSIM. CONCLUSIONS: Deep learning models approximated T-Scan occlusal force maps from intraoral scan images in this pilot dataset. These findings suggest that artificial intelligence may help estimate functional occlusal force distribution from morphological intraoral scan data. Further studies with larger datasets are required to validate clinical applicability. CLINICAL SIGNIFICANCE: Computational prediction of functional occlusal force maps from intraoral scans may represent a future step toward integrating morphological and functional data within digital dentistry workflows; however, larger validation studies are required before clinical application.
7 July 2026
Read appraisal →Operative dentistry
Color Match of Single-Shade and Group-Shade Resin Composites: A Visual and Instrumental Analysis
OBJECTIVE: Single-shade materials are favored for simplifying clinical workflows without compromising the esthetics of restorations, although evidence supporting their use remains limited. Therefore, this laboratory evaluated color match of single-shade versus group-shade resin composites. METHODS: Sixty sound human molars were divided into three subgroups (n = 20), based on the tooth-shade correspondence for the tested group-shade resin composite: L (light) including A1, B1, B2, C1 and D2; M (medium) including A2, A3, C2, D3 and D4, and D (dark) including A3.5, A4, B3, B4, C3 and C4 shaded teeth. Standardized class V cavities (4 × 4 × 2 mm) were prepared. Half of the specimens within each subgroup were restored with single-shade (Omnichroma), while the other half was restored with group-shade resin composite (SimpliShade). Tooth/restoration ΔE00 color differences were calculated at 24 hours (T1), and after seven days (T2) by a spectrophotometer (VITA Easyshade V). A visual analysis was performed after 14 days (T3). Also, a novel computer vision algorithm (CVA) analysis, was employed to evaluate color match at three weeks (T4). Student's t-test was used to compare the two groups within each subgroup and time point and one-way ANOVA was used to compare the values between subgroups, within each group and time point. RESULTS: Instrumental analysis at T1 showed higher mean ΔE00 for single-shade compared to group-shade resin composites (p < 0.05), within each subgroup. Within single-shade specimens, significantly higher mean ΔE00 differences were found at T2 between D (8.24 ± 1.85) vs L (5.65 ± 2.24) (p = 0.007) and M (6.49 ± 2.5) (p = 0.03). Within group-shade specimens, a significant difference was found between L (4.16 ± 2.19) and M (2.17 ± 1.05) at T1 (p = 0.034). Visual analysis reported a significant difference (p = 0.0153) between L-group shade (1.03 ± 1.04) and L-single shade (1.97 ± 0.78) restorations (p = 0.0153). No significant differences were detected when CVA analysis was employed. CONCLUSIONS: Overall, group-shade showed better color match than single-shade resin composites, especially when spectrophotometric and visual evaluation were employed.
11 June 2026
Read appraisal →The International journal of prosthodontics
A Systematic Review and Meta-analysis Evaluating the Survival, Failure, and Complication Rates of Metal-Ceramic, Veneered, and Monolithic All-Ceramic Tooth-Supported Single Crowns-Part 1
PURPOSE: To evaluate five-year survival rates of metal-ceramic, veneered all-ceramic, and monolithic all-ceramic tooth-supported single crowns (SCs) and assess biological and technical complications. MATERIALS AND METHODS: A systematic search of Medline (PubMed), Embase, and CENTRAL (2014-2024) identified clinical studies on tooth-supported fixed dental prostheses (≥3 years mean follow-up). Manual screening and 30 studies from previous reviews were added. Sixty-four studies met inclusion, reporting on 3,509 metal-ceramic and 8,051 all-ceramic SCs. Robust Poisson regression models were used to estimate pooled five-year survival rates. RESULTS: Twelve studies investigated metal-ceramic crowns, 49 all-ceramic crowns, and three both. Five-year survival rates were: 98.5% for monolithic lithium-disilicate reinforced glass-ceramic, 97.3% for veneered densely-sintered zirconia, 97.1% for metal-ceramic, 96.8% for monolithic densely-sintered zirconia, 95.7% for veneered leucite/lithium-disilicate reinforced glass-ceramic, 94.5% for densely-sintered alumina, 94.3% for glass-infiltrated alumina, 90.4% for feldspathic/silica-based ceramic. Survival rates of feldspathic/silica-based ceramic (P<0.0001), glass-infiltrated alumina (P=0.019), densely sintered alumina (P=0.002), and veneered leucite/lithium-disilicate reinforced glass-ceramic (P=0.021) were significantly lower than monolithic lithium-disilicate SCs. Except for feldspathic/silica-based ceramic and metal-ceramic crowns, material/design types performed similarly in anterior and posterior regions. Monolithic lithium-disilicate and monolithic zirconia crowns showed significantly fewer ceramic fractures and chipping compared to veneered alternatives. CONCLUSIONS: Lithium-disilicate and zirconia-based all-ceramic SCs achieve five-year survival rates comparable to metal-ceramic crowns. Monolithic designs reduce fracture and chipping risk, improving long-term clinical outcomes.
28 May 2026
Read appraisal →Dental materials journal
Domain shift analysis of deep learning models for tooth detection in pediatric panoramic radiographs
The aim of this study was to externally validate object detection models for comprehensive tooth detection on pediatric panoramic radiographs, quantify the impact of domain shift across institutions and imaging protocols, and compare YOLOv8 and YOLOv10. Two datasets were used: an internal set of 200 images of early mixed dentition without bite blocks, and an external, open-source set of 192 images acquired with bite blocks. Performance was assessed using mean average precision (mAP), per‑class AP, precision‑recall curves, and confusion matrix. Overall performance was high but domain dependent. mAP was 0.958/0.941 (YOLOv8/v10) in Experiment 1; 0.910/0.906 in Experiment 2; and 0.906/0.901 in Experiment 3. Error analysis revealed domain‑specific failure modes: bite blocks were occasionally mistaken for the primary central incisor. Deep learning enables accurate and comprehensive detection of teeth on pediatric panoramic radiographs. However, domain shift alters error patterns and impairs the detection of rare yet clinically important classes.
25 May 2026
Read appraisal →Clinical oral investigations
Three-dimensional stability during orthodontic retention: A comparative analysis of conventional, CAD/CAM-fabricated, and robotically bent fixed retainers versus removable appliances
OBJECTIVES: To evaluate three-dimensional anterior tooth position changes during orthodontic retention and to compare the effectiveness of three distinct fixed retainer fabrication designs including robotically bent retainers alongside with removable retainers. MATERIALS AND METHODS: This retrospective cohort study included 113 patients (226 dental arches; mean retention period 1.3 ± 0.6 years). Combined fixed lingual plus removable retention (group 1, n = 148 arches) comprised CAD/CAM Memotain, conventional multistranded stainless-steel (Twistflex), and robotically bent retainers; group 2 (n = 78 arches) received removable retention only. Digital model superimposition using a three-dimensional tooth-specific coordinate system quantified rotational and translational tooth movements, Little's Irregularity Index (LII), transverse arch widths, and bonding failures. RESULTS: Combined fixed and removable retention showed higher stability than removable-only retention (55% vs. 33% stable arches). Removable retention increased the odds of moderate-to-severe instability (maxilla OR 4.37, 95% CI 1.74-10.98; mandible OR 14.35, 95% CI 3.24-63.56), whereas fixed lingual retention was protective (maxilla OR 0.23, 95% CI 0.09-0.58; mandible OR 0.07, 95% CI 0.02-0.31). Instability mainly involved canine rotations and vertical translations. Robotically bent and CAD/CAM Memotain retainers showed the lowest movement magnitudes and variability, with minimal LII increases. Intercanine and intermolar widths remained stable across fixed retainers. Bonding failures (25%) strongly predicted severe instability. CONCLUSIONS: Three-dimensional tooth movements during retention mainly involve canine rotations and vertical translations. All fixed retainer designs (Twistflex, CAD/CAM-fabricated, and robotically bent) provided greater stability than removable-only retention. CLINICAL RELEVANCE: All fixed retainer designs require regular monitoring of bonding integrity; digitally fabricated and robotically bent retainers demonstrated marginally lower dimensional variability, which may be clinically relevant over longer observation periods.
25 May 2026
Read appraisal →Quintessence international (Berlin, Germany : 1985)
Mapping sequential patterns of periodontal breakdown using longitudinal electronic health records data
OBJECTIVE: To identify probabilistic, sequential patterns of periodontal breakdown using sequential pattern mining (SPM) on a large longitudinal cohort. METHOD AND MATERIALS: Electronic health records from 19,428 patients with periodontitis (2011-2022) were analyzed. A custom SPM algorithm was developed to identify frequent temporal subsequences of tooth mobility and furcation involvement, enforcing strict temporal precedence. 'High-risk' states (eg, generalized clinical attachment loss [CAL] > 3.0 mm) were evaluated as precursors to localized failure. Association rules were ranked by confidence (conditional probability). RESULTS: The analysis revealed distinct biomechanical cascading patterns. In the mandibular anterior sextant, mobility in the central incisors was a strong probabilistic precursor to subsequent failure in the lateral incisors and canines (confidence 7.3%). A significant 'antagonistic cascade' was identified, where mandibular incisor mobility preceded maxillary incisor instability (confidence 8.1%). For molars, furcation involvement acted as a specific temporal sentinel for future mobility (confidence ~5% to 6%). Generalized high CAL was the strongest predictor of localized failure (confidence 18.9%), significantly outperforming active inflammation (bleeding on probing) as a driver of mechanical instability. CONCLUSION: Progressive biomechanical compromise (such as tooth mobility and advanced furcation involvement) follows predictable, probabilistic sequential patterns. The identification of specific 'sentinel events,' such as mandibular incisor mobility and molar furcation involvement, allows for a shift from reactive site-by-site management to predictive intervention. CLINICAL RELEVANCE: These findings underscore the critical role of generalized attachment loss in driving localized mechanical failure cascades.
22 May 2026
Read appraisal →Clinical oral investigations
Evaluation of a novel dual-headed toothbrush design for periodontal health: split-mouth randomized blind clinical trial
BACKGROUND: Optimal oral health largely depends on the successful removal of plaque through effective brushing, but success typically relies on user technique, time, and adherence. The aim was to compare the effectiveness of a newly introduced dual-headed toothbrush with a conventional single-headed toothbrush in control of plaque and gingival health using a split-mouth design. METHODS: In the study, 37 dental professionals used two types of toothbrushes: a dual-headed toothbrush on one side of the mouth (Test side) and a conventional single-headed toothbrush on the other side (Control side). The study compared plaque removal, gingival status, and brushing time, assessing clinical outcomes using plaque index (PI), gingival index (GI), and modified sulcus bleeding index (mSBI) at baseline, 2 weeks, and 4 weeks. At the end, participants completed a Likert scale questionnaire. RESULTS: Both types of toothbrushes were effective in enhancing oral hygiene over time; however, dual-headed toothbrush group showed significant short-term reductions in plaque accumulation, gingival inflammation, and bleeding, particularly at the 2-week interval. A significant majority of participants (89.2%) rated dual-headed brush as "very easy" to use. Using a dual-headed toothbrush significantly reduces the brushing time (0.54 ± 0.17 vs. 0.99 ± 0.05 min for a conventional single-headed toothbrush), suggesting enhanced time efficiency. CONCLUSION: A dual-headed toothbrush would be more effective, faster, and easier to use than a single-headed brush. It would be a convenient alternative, especially for individuals with time constraints.
21 May 2026
Read appraisal →Brazilian oral research
Effect of strict oral hygiene on self-rated halitosis and quality of life in patients with periodontitis: a secondary randomized controlled trial analysis
This single-blind, randomized clinical trial evaluated the impact of a strict oral hygiene (OH) phase on self-reported halitosis and quality of life (QoL) in patients with periodontitis. This study reports a secondary analysis of a single-blind randomized controlled trial (parallel, 1:1), registered at RBR-5jmx32v. The study included 24 individuals diagnosed with periodontitis who were randomly assigned to the intervention group (IG; n = 12) and the no-intervention group (NIG; n = 12). After receiving personalized OH instructions, the IG participants followed a rigorous OH phase for 45 days, whereas the NIG participants received no guidance during this period. The halitosis-associated QoL test (HALT) was administered at baseline and after 45 days. Data were analyzed using t-tests, chi-square tests, and multilevel linear regression, with significance set at p < 0.05. The average age of the study participants was 47.2 years, with a balanced sex distribution and no differences in income or education. Self-reported halitosis decreased from 100% to 50% in the IG after 45 days, whereas it remained at 91.6% in the NIG (p = 0.034). The IG also showed a mean HALT score reduction of 11.9 points (-11.88; 95% CI: -19.40 to -4.36), with significant improvements in social impact and self-esteem (p < 0.05). Clinically, BOP (p < 0.001) and VPI (p = 0.03) improved significantly in the IG, with no significant changes in NIG. This exploratory trial demonstrates that implementing a strict OH phase in patients with periodontitis may help reduce self-reported halitosis, improve HALT scores, and improve clinical outcomes, supporting its role as an adjunctive strategy in periodontal care.
21 May 2026
Read appraisal →Molecular biology reports
Oral mucosal microbiome alterations in recurrent aphthous stomatitis: a systematic review of 16 S rRNA gene sequencing studies
Recurrent aphthous stomatitis (RAS) is a prevalent inflammatory disorder of the oral mucosa characterized by recurrent painful ulcerations in otherwise healthy individuals. This systematic review aimed to evaluate alterations in the oral mucosal microbiome of patients with RAS based on studies using 16 S rRNA sequencing. A systematic search of PubMed, Scopus, and Web of Science was conducted on April 14, 2026. Eligible studies included human case-control investigations evaluating oral mucosal swab samples from patients with clinically diagnosed RAS and healthy controls using 16 S rRNA sequencing. Studies based solely on saliva, culture methods, PCR-only analyses, or lacking controls were excluded. Joanna Briggs Institute Critical Appraisal Checklist for Case-Control Studies was used for the evaluation of selected articles. Six studies met the inclusion criteria. Considerable heterogeneity was observed in alpha and beta diversity outcomes. Most studies reported reduced microbial richness in RAS lesions, whereas others found increased or unchanged diversity. Ulcerated sites frequently demonstrated reduced abundance of health-associated taxa such as Streptococcus and Firmicutes, with increased levels of Proteobacteria and inflammation-associated genera including Neisseria, Haemophilus, Prevotella, and Fusobacterium. Microbial alterations were most pronounced at active ulcer sites, while non-ulcerated or healed mucosa more closely resembled healthy controls. Current evidence suggests that RAS is associated with localized, site-specific microbial dysbiosis rather than generalized oral microbiome disruption. However, methodological heterogeneity and small sample sizes limit definitive conclusions. Future standardized longitudinal studies integrating functional metagenomics are warranted to clarify the role of the microbiome in RAS pathogenesis.
16 May 2026
Read appraisal →Clinical oral investigations
Efficacy of subgingival irrigation with chemical agents as adjuvants to non-surgical periodontal therapy: systematic review and meta-analysis
OBJECTIVE: This systematic review aims to assess the efficacy of chemical agents (CA) in subgingival irrigation as an adjunct to non-surgical periodontal treatment (NSPT) in the treatment of periodontitis. METHODS: Search strategies were developed for MEDLINE via PubMed, Web of Science, and LILACS databases for publications up to March 2025. Risk of bias was assessed according to the RoB 2.0 tool. Random-effects meta-analyses were conducted for clinical attachment level (CAL), probing pocket depth (PPD), and bleeding on probing (BOP). RESULTS: From 1244 studies initially screened, 16 randomized clinical trials were included for qualitative and quantitative analyses. Studies assessed the effects of the following chemical agents: Povidone-iodine (PVP-I), Essential Oils (EOs); Chlorhexidine (CHX), Ozonated water (OW) and Boric Acid (BA). Overall, the meta-analysis showed that the adjunctive use of CA as subgingival irrigation did not provide additional benefit in PPD reduction, CAL gain, and BOP compared with controls (P > 0.05). Most studies raised some concerns with risk of bias, and 2 showed a high risk of bias. CONCLUSION: Adjunctive use of chemical agents in subgingival irrigation during NSPT for periodontitis patients does not appear to provide additional benefit over NSPT alone, although evidence levels are low to very low. CLINICAL RELEVANCE: CA are frequently used as adjuncts to NSPT, despite uncertainty regarding their real clinical contribution. The findings of this study help clinicians make more evidence-based decisions and avoid unnecessary use of adjunctive subgingival irrigation strategies during periodontal treatment.
14 May 2026
Read appraisal →International journal of oral science
Machine learning-driven discovery of therapeutic nucleoside hydrogels for periodontitis
Supramolecular hydrogels hold significant potential in drug delivery and tissue engineering, with standing out for their unique properties. Despite their promise, predicting nucleoside bioactivity remains challenging. This study aims to predict the biological activity of nucleosides to guide the rational synthesis of hydrogels. Specifically, nine predictive models and databases for various biological activities were built with feature-selected machine learning methods including decision trees, logistic regression, random forest, and extreme gradient boosting. Then, the Molecular Bioactivity Specificity Index (MBSI) was introduced to gauge the primary bioactivity of nucleoside derivatives, and the Composite Molecular Attribute Score (CMAS) was devised to measure the overall performance of nucleoside derivatives. Subsequently, screening strategies for bioactive nucleoside hydrogels were established, and two candidate hydrogels (GMP and dGMP) with high hydrogel-forming ability, biocompatibility, and antibacterial activity were identified. Finally, two hydrogels were validated for antibacterial treatment of periodontitis. This study highlights the feasibility of ML-based strategies and MBSI/CMAS in rationally designing bioactive nucleoside hydrogels for biomedical applications. The discovery of GMP and dGMP hydrogels and their successful validation in periodontitis models highlight the potential of this strategy for developing targeted therapies for oral diseases.
14 May 2026
Read appraisal →Medical science monitor : international medical journal of experimental and clinical research
Preliminary Evaluation of Large Language Models in Kennedy Classification and Removable Partial Denture Planning: An In Silico Study
BACKGROUND This study evaluated text-based large language models for Kennedy classification and removable partial denture planning in partially edentulous cases, where comparative evidence on accuracy remains limited. MATERIAL AND METHODS Twenty-six partially edentulous cases, defined according to the Federation Dentaire Internationale tooth numbering system and classified as Kennedy Classes I to IV, were included. Case scenarios were constructed by an experienced prosthodontist. Questions were independently submitted to 4 large language models without prior training or prompting: ChatGPT-5.2, Claude Sonnet 4.6, Gemini 3 Flash, and Perplexity. Responses were evaluated by 2 independent prosthodontists (different from the case developer) - blinded to the identity of each model - using predefined criteria for Kennedy classification accuracy and prosthetic planning consistency. Statistical analyses included intergroup comparisons and effect size estimation. RESULTS Statistically significant differences were identified among the models in both tasks (P<0.001). For Kennedy classification, the effect size was moderate (Kendall's W=0.402). Gemini 3 Flash achieved the highest mean score, followed by ChatGPT-5.2, Perplexity, and Claude Sonnet 4.6. Similarly, significant differences were observed in removable partial denture planning performance (Kendall's W=0.424); Gemini 3 Flash scored significantly higher than the other models (P≤0.001). CONCLUSIONS Large language models showed variable performance under zero-shot conditions. Although Gemini 3 Flash achieved higher scores, the moderate effect sizes warrant cautious interpretation. These models may serve as adjunctive decision-support tools in prosthodontics but cannot replace clinical judgment.
12 May 2026
Read appraisal →Clinical oral investigations
Treatment of gingival recession type 1 using coronally advanced flap with leucocytes-platelet rich fibrin: a randomized controlled trial
OBJECTIVE: This study aimed to evaluate the clinical outcomes of gingival recession Type 1 (RT1) treatment using a coronally advanced flap (CAF) alone and in combination with L-PRF at 6 months. MATERIALS AND METHODS: A total of 70 RT1 from 19 patients were included. Participants were randomly assigned to the test group (TG, CAF + L-PRF, n = 42) and the control group (CG) (CAF alone, n = 28). Clinical parameters were assessed at baseline and at 6 months: the primary outcomes were percentage of root coverage (%RC) and complete root coverage (CRC); and the secondary outcomes included mean root coverage (MRC), changes in gingival thickness (GT) and volumetric tissue gain, recession area reduction, analgesic consumption, healing quality (the Inflammatory Proliferative Remodeling [IPR] score), and patient-reported outcome measures (PROMs). Statistical analyses were performed to determine differences between groups; a random-intercept mixed-effects model was used for all site-level outcomes. RESULTS: At six months, %RC was 89.30% ± 20.33% (TG) and 81.60% ± 27.93% (CG) (p > 0.05). For the TG and CG, respectively, %CRC was 73.81% and 57.14%; the mean GT gain was 0.16 ± 0.10 mm and 0.11 ± 0.10 mm (p = 0.08); the mean volume gain was 1.13 ± 1.25 mm3 and 0.86 ± 0.84 mm3 (p = 0.32); the mean number of pills taken was 1.67 ± 0.98 and 2.25 ± 1.02 (p = 0.04); the esthetic satisfaction was 95% ± 5% and 90% ± 7% (p = 0.31); willingness to undergo the procedure again: 93% ± 4% and 88% ± 6% (p = 0.22); sensitivity reduction: 85% ± 6% and 80% ± 8% (p = 0.19). There was no statistically significant difference in healing quality and PROMs. CONCLUSION: Both CAF alone and CAF combined with L-PRF yielded comparable clinical and volumetric outcomes in RT1 treatments. No statistically significant advantages were observed with the adjunctive use of L-PRF. CLINICAL RELEVANCE: Because CAF alone achieves high predictability for RT1 defects, the routine adjunctive use of L-PRF provides limited additional clinical benefits.
11 May 2026
Read appraisal →Calcified tissue international
Diagnostic Indices for Epidemiological Assessment of Molar Incisor Hypomineralization: A Systematic Review
Molar incisor hypomineralization (MIH) is a qualitative developmental defect of enamel and one of the most prevalent oral health conditions in childhood. Over the last two decades, increasing attention has been given to its prevalence and etiology; however, marked heterogeneity in diagnostic criteria and indices has limited the comparability of epidemiological findings. This systematic review aimed to identify and describe the diagnostic indices used for the epidemiological assessment of MIH in the general pediatric population. A systematic literature search was conducted in PubMed, Scopus, and Google Scholar to identify epidemiological studies published between January 2001 and December 2024 reporting MIH prevalence in children. Study selection, data extraction, and methodological quality assessment were performed independently by two reviewers in accordance with PRISMA guidelines. The review protocol was registered in PROSPERO (CRD42022345224). A total of 198 articles were included, corresponding to 201 independent epidemiological studies, as three articles reported results from two distinct study populations. The European Academy of Paediatric Dentistry (EAPD) criteria were used in 171 studies (75.7%), representing the most widely adopted diagnostic index. Other indices, including the modified Developmental Defects of Enamel index (mDDE), Mathu-Muju and Wright, Wetzel and Reckel, MIH Severity Scoring System (MIH-SSS), the MIH Treatment Need Index (MIH TNI) criteria, and FDI criteria, were used infrequently. Studies using EAPD criteria accounted for the largest cumulative sample size and showed a descriptively aggregated MIH prevalence of 12.9%, whereas prevalence estimates varied across alternative diagnostic indices. In conclusion, the lack of uniform diagnostic standards and nomenclature hampers global surveillance and limits the comparability of prevalence data. The adoption of MIH-specific diagnostic criteria, supported by adequate examiner calibration and transparent reporting, is essential to improve the quality, consistency, and interpretability of future epidemiological research.
11 May 2026
Read appraisal →Clinical oral investigations
Clinical performance of alkasite and glass-hybrid restorations compared with resin composite in class II cavities: a randomized clinical trial
OBJECTIVES: The aim of this randomized clinical trial was to evaluate the 18-month clinical performance of alkasite and glass-hybrid restorations compared with resin composite in Class II restorations. MATERIALS AND METHODS: A total of 50 patients requiring at least three Class II restorations in premolar and molar teeth were recruited. Each patient received three restorations, which were randomly assigned to one of the following materials: an alkasite (Cention N, Ivoclar Vivadent), a glass-hybrid (Equia Forte HT, GC Corp.), or a resin composite (Gradia Direct Posterior, GC Corp.). Alkasite and glass-hybrid served as test groups while resin composite served as the control group. During the 18-month follow-up, restorations were scored at baseline, 6, 12, and 18 months using the FDI criteria. Data were analyzed using the Chi-square and Cochran's Q tests (α = 0.05). RESULTS: No significant differences were detected among the groups for esthetic, functional, or biological criteria over 18 months (p > 0.05). Regarding esthetic properties, the control group showed 100% success for all esthetic criteria at all recall visits, while the alkasite group maintained a 96% success rate at all time points, and glass-hybrid showed 98% success at 6 and 12 months and 92% at 18 months. Minor score-2 changes in color match and gloss were detected in the glass-hybrid and alkasite groups but were not significant (p > 0.05). For functional and biological outcomes, all groups achieved 100% success rates for all evaluated parameters. CONCLUSIONS: Alkasite and glass-hybrid groups exhibited clinical performance comparable to resin composite over the 18-month follow-up in Class II cavities. All materials demonstrated excellent functional and biological stability while achieving clinically acceptable aesthetic results.
10 May 2026
Read appraisal →Clinical oral investigations
Does endodontic treatment modify serum inflammatory markers of cardiovascular risk in individuals with asymptomatic apical periodontitis? a systematic review and meta-analysis.
OBJECTIVE: Plasma inflammatory biomarkers linked to cardiovascular risk have been associated with asymptomatic apical periodontitis. However, it remains unclear whether endodontic treatment can reverse these alterations. This review evaluated the effect of endodontic treatment on inflammatory markers in individuals with asymptomatic apical periodontitis. MATERIALS AND METHODS: A comprehensive search was conducted in PubMed/Medline, Embase, Web of Science, Scopus, VHL, gray literature, and reference lists between October and November 2022, with an update in September 2025. Risk of bias was assessed using the Newcastle-Ottawa Scale, and the certainty of evidence using the GRADE approach. Random-effects meta-analysis estimated pooled mean differences (MD) and 95% confidence intervals (95%CI) for serum inflammatory markers concentrations between treated individuals and controls (α = 5%). RESULTS: The search identified 6,295 records; sixteen studies were assessed and eight included in the quantitative synthesis. All studies showed moderate risk of bias, and evidence certainty was very low. Meta-analysis suggested possible reductions in C-reactive protein (CRP) [MD = 0.76 (95% CI: - 0.15, 1.67)] , interleukin-6 (IL-6) [MD = 0.81 (95% CI:-0.27, 1.90)], and tumor necrosis factor-alpha (TNF-α) [MD = 1.04 (95% CI:-0.38, 2.46)] after endodontic treatment, with levels similar to control groups. CONCLUSION: Evidence, although limited, suggests endodontic treatment may lower serum CRP, IL-6, and TNF-α levels in asymptomatic apical periodontitis patients. CLINICAL RELEVANCE: Endodontic treatment of asymptomatic apical periodontitis may help reduce systemic inflammatory biomarkers associated with cardiovascular risk, reinforcing its potential role beyond local infection control.
10 May 2026
Read appraisal →Medical image analysis
MICCAI STS 2024 challenge: Semi-supervised instance-level tooth segmentation in panoramic X-ray and CBCT images
Orthopantomogram (OPGs) and Cone-Beam Computed Tomography (CBCT) are vital for dentistry, but creating large datasets for automated tooth segmentation is hindered by the labor-intensive process of manual instance-level annotation. This research aimed to benchmark and advance semi-supervised learning (SSL) as a solution for this data scarcity problem. We organized the 2nd Semi-supervised Teeth Segmentation (STS 2024) Challenge at MICCAI 2024. We provided a large-scale dataset comprising over 90,000 2D images and 3D axial slices, which includes 2380 OPG images and 330 CBCT scans, all featuring detailed instance-level FDI annotations on part of the data. The challenge attracted 114 (OPG) and 106 (CBCT) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid, open-source submissions from the top 10 (OPG) and top 5 (CBCT) teams, respectively. All successful submissions were deep learning-based SSL methods. The winning semi-supervised models demonstrated impressive performance gains over a fully-supervised nnU-Net baseline trained only on the labeled data. For the 2D OPG track, the top method improved the Instance Affinity (IA) score by over 44 percentage points. For the 3D CBCT track, the winning approach boosted the Instance Dice score by 61 percentage points. This challenge demonstrates the potential benefit benefit of SSL for complex, instance-level medical image segmentation tasks where labeled data is scarce. The most effective approaches consistently leveraged hybrid semi-supervised frameworks that combined knowledge from foundational models like SAM with multi-stage, coarse-to-fine refinement pipelines. Both the challenge dataset and the participants' submitted code have been made publicly available on GitHub (https://github.com/ricoleehduu/STS-Challenge-2024), ensuring transparency and reproducibility.
9 May 2026
Read appraisal →Medical science monitor : international medical journal of experimental and clinical research
Influence of Operative Techniques on Clinical and Laboratory Outcomes in Class II Resin-Based Composite Restorations: A Systematic Review
BACKGROUND Operative technique is a major determinant of the long-term success of Class II resin-based composite restorations. Variations in adhesive strategy, layering approach, matrix system, and curing protocol influence marginal integrity, polymerization stress, postoperative sensitivity, and secondary caries. Because resin-based composite placement is technique-sensitive, synthesizing evidence on how specific operative steps affect outcomes is essential. This systematic review evaluated the influence of operative techniques on the clinical and laboratory performance of Class II resin-based composite restorations. MATERIAL AND METHODS A comprehensive search of PubMed, Cochrane Library, and Embase identified 57 records. After duplicate removal and screening, 21 studies were included (11 randomized controlled trials and 10 in vitro investigations). Techniques assessed were adhesive protocols, layering strategies, matrix systems, and curing methods. Data extraction focused on restoration longevity, marginal adaptation, postoperative sensitivity, and secondary caries. Risk of bias was evaluated using the Cochrane tool for randomized trials and modified CONSORT/Joanna Briggs Institute criteria for in vitro studies. Meta-analysis was not feasible because of heterogeneity. RESULTS Multi-step adhesive approaches showed the highest 5-year survival (up to 91%) and lower secondary caries rates. Incremental layering reduced postoperative sensitivity and improved marginal adaptation. Sectional matrices produced tighter proximal contacts (76% vs 42%), while soft-start curing reduced marginal gap formation (112 µm to 45 µm). One-step adhesives and uncontrolled bulk-fill placement showed higher failure and hypersensitivity. CONCLUSIONS Multi-step adhesives, incremental layering, sectional matrices, and soft-start curing provide the most favorable outcomes and support technique standardization in clinical practice.
1 May 2026
Read appraisal →Scientific reports
Effectiveness of intracanal cryotherapy in reducing post-endodontic pain in irreversible pulpitis: a systematic review and meta-analysis
Irreversible pulpitis is characterized by persistent inflammation and moderate to severe pain, often requiring pharmacological or adjunctive strategies for postoperative management. Intracanal cryotherapy has emerged as a simple, cost-effective technique to mitigate this pain by utilizing cold-induced physiological responses. This systematic review and meta-analysis aimed to evaluate the clinical evidence regarding the effectiveness of intracanal cryotherapy in reducing postoperative pain in teeth with irreversible pulpitis. Electronic searches were conducted in PubMed, Web of Science, Cochrane, and Scopus up to October 2025. Randomized controlled trials (RCTs) comparing intracanal cryotherapy to conventional endodontic treatment. Two reviewers independently screened studies, extracted data, and assessed risk of bias using RoB 2. Random-effects meta-analysis was performed using SMD for pain levels at 6, 12, 24, 48, and 72 h. Twelve RCTs were included; nine were meta-analyzed. Cryotherapy significantly reduced pain at 6 and 12 h but not later time points. Intracanal cryotherapy appears to be a safe and inexpensive adjunct that is associated with reduced early postoperative pain, with the most consistent effect observed within the first 6-12 h. Heterogeneity and short follow-up periods. Cryotherapy reduces early postoperative pain only.Registration: PROSPERO CRD420261295239.
27 Apr 2026
Read appraisal →Journal of prosthodontic research
The clinical performance of CAD/CAM-fabricated hybrid ceramic restorations in cases with severe wear: A 3-year clinical trial
PURPOSE: To evaluate the clinical use of CAD/CAM hybrid ceramics in patients with severe tooth wear. METHODS: Forty-nine patients with severe tooth wear underwent prosthetic management with 116 hybrid ceramic restorations. The restorations were evaluated at 1 week and at 3, 6, 12, 18, 24, 30, and 36 months after placement. The amount of wear on the restorations, antagonist teeth, and opposite teeth was compared using digital superimposition analysis. A questionnaire was used to evaluate participants' satisfaction with the restorations. Complications were recorded, and survival rates were estimated using Kaplan-Meier analysis. RESULTS: The clinical performance of the restorations was stable for esthetic, functional, and biological parameters up to 3 years, except for greater changes in "surface and margin staining" and "fracture and retention." There was no significant difference in the amount of progressive wear among the restorations, antagonist teeth, and opposite side teeth until 18 months; however, the wear on the restorations increased gradually up to 36 months. Higher scores and identical satisfaction results were obtained for the chewing efficiency and cleanability during the observation period. The most common complications were restoration dislodgement (5.2%) and partial marginal chipping (4.3%), which were clinically repaired. Four restorations (3.4%) were extensively fractured and replaced. The estimated survival rate of the hybrid ceramic restorations at 3 years was 88.0%. CONCLUSIONS: The clinical use of hybrid ceramic restorations in patients with severe tooth wear improved chewing efficiency and esthetics, provided adequate resistance for load-bearing, and delivered a stable treatment outcome after functional use.
13 Apr 2026
Read appraisal →Journal of prosthodontic research
Cleaning methods of contaminated lithium disilicate ceramics: A systematic review and network meta-analysis
PURPOSE: To evaluate the effects of various cleaning methods on the bond strength between lithium disilicate (LS2) ceramics and resin cement under short- and long-term aging conditions using network meta-analysis (NMA) and pairwise meta-analysis (PMA). STUDY SELECTION: An electronic search of seven databases (PubMed, Scopus, Embase, Web of Science, Google Scholar, Defense Technical Information Center, and LILACS) with a manual search of the reference lists was conducted for articles published up to March 10, 2025. Eligible studies included those that assessed the bond strength of LS2, either uncontaminated or contaminated with human saliva, fit-checking materials, try-in paste, or their combinations, using different cleaning methods. Risk of bias was evaluated using the RoBDEMAT tool. A frequentist multivariable random-effects model was used to calculate the effect sizes. RESULTS: Fifteen studies met the inclusion criteria. Under short-term aging conditions, NMA showed higher bond strengths in the uncontaminated LS2 group and the contaminated groups cleaned with hydrofluoric acid etching, commercial ceramic cleaning agents, or phosphoric acid etching than those uncleaned or cleaned with water or alcohol. In long-term aging, PMA and NMA exhibited higher bond strengths in the uncontaminated LS2 group and contaminated group cleaned with phosphoric acid etching than those contaminated groups cleaned with water or alcohol. CONCLUSIONS: Phosphoric acid etching effectively eliminates contaminants, whereas the application of water or alcohol is ineffective. Although ceramic cleaning agents effectively decontaminate surfaces under short-term aging conditions, their performance deteriorates over time, potentially compromising long-term bond durability.
13 Apr 2026
Read appraisal →JMIR formative research
Evaluation of GPT-5 in Periodontitis Staging and Grading: Retrospective Observational Study
BACKGROUND: Periodontitis is a chronic gum disease affecting approximately 42% of adults aged 30 years and older in the United States. Training dental students to accurately diagnose and manage periodontitis is a critical component of dental education and clinical care. Recent advances in large language models offer new opportunities to support both domains, yet their performance in periodontal diagnosis remains largely unexplored, particularly for newer models such as GPT-5. OBJECTIVE: This study conducted an exploratory evaluation of GPT-5's ability to stage and grade periodontitis. METHODS: A total of 25 publicly available clinical cases explicitly reporting periodontitis stage and grade were identified through Google and PubMed searches. Each case description was entered into GPT-5 using a zero-shot prompting approach to assess guideline-based reasoning without exemplar conditioning. The model's predictions were compared with the published reference diagnoses. Performance was measured using accuracy, 95% CI, unweighted Cohen κ, and weighted Cohen κ. RESULTS: Across these cases, GPT-5 showed marked class-dependent performance and a tendency to overestimate disease severity. Grading performance was notably imbalanced, with high recall for grade C but substantially lower discrimination for grade B. GPT-5 achieved a staging accuracy of 68% (95% CI 48.4%-82.8%) and a grading accuracy of 77.3% (95% CI 56.6%-89.9%), with corresponding Cohen κ values of 0.454 (95% CI 11.0%-75.6%) and 0.179 (95% CI -15.8% to 63.8%), respectively. While staging performance showed fair agreement beyond chance, the low κ for grading indicates poor agreement and limited reliability in distinguishing periodontal disease severity. CONCLUSIONS: These findings suggest that although GPT-5 demonstrates potential for guideline-based periodontitis staging and grading, its current diagnostic performance, particularly for periodontitis grading, limits its use in clinical assessment and educational training. Meaningful application in periodontal diagnosis and training will require substantial improvements in reliability and rigorous validation in larger, more diverse, and prospectively collected datasets.
7 Apr 2026
Read appraisal →The International journal of oral & maxillofacial implants
Histologic and Immunohistochemical Analysis of Peri-implant Tissue Regeneration at the Interface of Prosthetic Abutments Treated with Anodizing: A Prospective, Randomized Controlled Clinical Trial on the Early Postoperative Period
PURPOSE: To assess the effects of anodized prosthetic abutments versus machined abutments on peri-implant connective tissue. MATERIALS AND METHODS: Following dental implant placement and osseointegration, custom healing abutments with machined surfaces (G1) and anodized surface treatment (G2) were attached to 28 dental implants. After a soft tissue healing period of approximately 30 days (± 7 days), 5-mm circular biopsy samples were taken from the peri-implant tissue and the area adjacent to the prosthetic abutment. Histologic analysis was conducted on the stained specimens using hematoxylin-eosin (H&E), focusing on parameters such as vascular proliferation as well as the presence of polymorphonuclear and mononuclear cells, collagen fibrils, and reepithelialization. A grading scale from 0 to 3 evaluated the extent of the inflammatory response. Masson's trichrome staining was used to analyze collagen fiber presence and organization, while immunohistochemical staining assessed the expression of beta-catenin (β-catenin) and Cluster of Differentiation 34 (CD34). The prosthetic abutments were evaluated through scanning electron microscopy and 3D roughness analysis. RESULTS: Histologic findings revealed that peri-implant tissue adjacent to anodized surfaces exhibited epithelial stratification and a parakeratin layer in the lamina propria. Both groups displayed a typical mononuclear lymphocytic inflammatory infiltrate, but the intensity was significantly higher adjacent to the machined abutment (P < .05). Quantification of blood vessels indicated increased immunopositivity for CD34 in G2 compared to G1 (P < .05). Immunolabeling of β-catenin was detected in the epithelial tissue, showing weak intensity in G1 and strong intensity in G2. The average surface roughness measurements were determined to be 0.097 ± 0.006 μm for G1 and 0.182 ± 0.008 μm for G2. CONCLUSIONS: Anodized surfaces are a promising treatment option and exhibit beneficial effects on peri-implant tissue healing. They play an important role in preserving the epithelial mucosal integrity and functionality near the prosthetic abutment, thereby potentially minimizing the risks of mucositis, peri-implantitis, and implant failure.
5 Apr 2026
Read appraisal →The International journal of oral & maxillofacial implants
Dimensional Changes of the Alveolar Ridge After Tooth Extraction Using the Socket Shield Technique Without Immediate Implant Placement: A Randomized Controlled Study
PURPOSE: To compare radiographic dimensional changes in postextraction sites treated with spontaneous healing versus the modified socket shield technique (mSST) without immediate placement using CBCT scans. MATERIALS AND METHODS: This randomized clinical study included 80 patients with a single maxillary anterior tooth that was not restorable. Patients were divided into two equal groups: (1) the test group, which used the mSST, and (2) the control group, which used the atraumatic extraction technique with spontaneous healing. CBCT scans were performed at baseline (before or immediately after extraction) and 6 months postsurgery. Measurements included alveolar ridge width at 1-mm, 3-mm, and 5-mm levels and buccal and palatal bone plate heights. Following this, implants were placed, and their primary stability was assessed. The main intervention was the use of the mSST compared to the atraumatic tooth extraction technique. The primary outcome was the change in buccal bone plate height over a 6-month follow-up period. In addition, covariates included patient age and sex. Paired t tests and independent t tests were used to evaluate intra- and intergroup differences, respectively. Statistical significance was set at P < .05. RESULTS: In the test group, a significant reduction in palatal wall height was observed (P < .001), while no significant changes were noted in other parameters (P ≥ .05). In the control group, significant decreases were observed in buccal and palatal plate heights as well as ridge width (P < .05). When comparing the groups, the test group demonstrated significantly less buccal wall height and ridge width resorption than the control group (P < .05). However, no significant difference was observed in palatal plate height resorption between the two groups (P = .507). The test group exhibited significantly higher primary stability rates compared to the control group (P = .001). CONCLUSIONS: The mSST with delayed implant placement demonstrated superior maintenance of buccal bone plate height and ridge width, along with significantly greater primary implant stability, compared to spontaneously healed sockets. This approach is beneficial for maintaining ridge integrity when immediate implant placement is not planned.
4 Apr 2026
Read appraisal →The International journal of oral & maxillofacial implants
Accuracy and Reliability of Artificial Intelligence Chatbots as Public Information Sources in Implant Dentistry
PURPOSE: To evaluate the accuracy, completeness, comprehensibility, and reliability of widely available artificial intelligence (AI) chatbots when addressing clinically significant queries pertaining to implant dentistry. MATERIALS AND METHODS: A total of 20 questions were devised based on a compiled list that were most frequently asked or encountered during patient consultations by three experienced prosthodontists. These questions were asked to ChatGPT-3.5, Gemini, and Copilot AI chatbots on three separate occasions in 12-day intervals. A three-point Likert scale (0 = incorrect; 1 = incomplete or partially correct; 2 = correct) and a two-point scale (true and false) were employed by the authors to grade the accuracy of the responses independently. Completeness and comprehensibility were also evaluated using a three-point Likert scale (scored 1, 2, or 3, with lower scores indicating a worse result). In addition to the questions generated by the specialists, AI chatbots were asked to provide five frequently asked questions and responses regarding dental implant prostheses. A comparison of total scores obtained from the chatbots was made with one-way analysis of variance (ANOVA). Twopoint scale data were analyzed via chi-square test. The reliability of the responses for each chatbot was analyzed by assessing the consistency of repeated responses via calculating Cronbach's alpha (α) coefficients. RESULTS: When the total accuracy scores of the chatbots were analyzed out of a 40-point total score (ChatGPT-3.5 = 28.78 ± 4.06; Gemini = 30.89 ± 4.08; Copilot = 29.11 ± 3.22), one-way ANOVA revealed no statistically significant differences (P = .461). For the evaluation of two-point accuracy scale data, which were analyzed via chi-square test, no statistical differences were revealed among the chatbots (P = .336). Gemini showed a higher completeness level than ChatGPT-3.5 (P = .011). There was no statistically significant difference among AI chatbots in terms of comprehensibility. Copilot demonstrated the greatest overall consistency among the three chatbots, with a Cronbach's α value of .863. This was followed by ChatGPT-3.5 with a Cronbach's α value of .779 and Gemini with a Cronbach's α value of .636. CONCLUSIONS: The accuracy of all three chatbots were found to be similar. All three chatbots demonstrated an acceptable level of consistency. However, given the low accuracy rate of chatbots in answering questions, it is clear that they should not be relied upon as a decision-maker, and the clinician's opinion must be given priority.
4 Apr 2026
Read appraisal →Dental clinics of North America
Artificial Intelligence in Diagnostic Oral and Maxillofacial Imaging, Surgical Applications, and Teledentistry
The article deals with the utilization of artificial intelligence (AI) and related technologies for the diagnosis of oral and maxillofacial anatomic variants and pathologic entities. The diagnosis of dental caries and periodontal disease is the most common aspect of dental diagnosis in a general dental setting and so, there was a subsection for this topic. There are dedicated portions within this article on applications of AI for oral and maxillofacial surgery.
4 Apr 2026
Read appraisal →Journal of dentistry
A deep learning method for diagnosis of oral potentially malignant disorders
OBJECTIVES: This study aimed to develop and validate a two-stage deep learning method for diagnosing oral potentially malignant disorders (OPMDs). We also compared its diagnostic performance with that of clinicians at different levels of seniority and evaluated its utility as a clinical decision support tool. METHODS: A two-stage deep learning method was developed. CLA OPMD-OOML was designed to differentiate OPMDs from other oral mucosal lesions (OOML), while CLA OPMDs was designed to classify specific OPMD subtypes. The method was trained on an internal dataset (ZJUSS, n = 3305), and its generalizability was evaluated on two external multicenter datasets (WCHS and CS-SJTU, n = 1756). In a blinded, two-step comparative study, nine clinicians (junior, intermediate, and senior groups) performed diagnoses independently and then with AI assistance. RESULTS: The method significantly outperformed all clinician groups, achieving higher F1 scores in both CLA OPMD-OOML (89.9 % vs. 78.4-82.6 % for clinicians) and CLA OPMDs (92.2 % vs. 77.7-80.0 % for clinicians). It showed robust generalizability on the two external datasets, with F1 scores of 87.3 % and 86.9 % for CLA OPMD-OOML and 75.9-83.0 % for CLA OPMDs. With AI assistance, the diagnostic precision of junior and intermediate clinicians increased by 10.8 % and 5.9 %, respectively, raising the junior group's performance to the level of senior clinicians. CONCLUSIONS: The developed two-stage deep learning method demonstrated diagnostic performance comparable to or exceeding that of experienced clinicians in classifying OPMDs from clinical images. It functions as a powerful assistive tool that substantially enhances the diagnostic capabilities of junior and intermediate clinicians. CLINICAL SIGNIFICANCE: This AI method has the potential to serve as a reliable tool for large-scale early screening of OPMDs, particularly in regions with limited access to specialist dental care. It can also serve as a valuable training and decision support system for junior clinicians, helping to standardize diagnostic accuracy and improve patient outcomes through timely and accurate detection. A supplemental appendix to this article is available online.
4 Apr 2026
Read appraisal →