Evidence-based dentistry最新文献

{"title":"Adult tooth regeneration: can blood beat biomaterials?","authors":"Casper Jonker","doi":"10.1038/s41432-026-01239-7","DOIUrl":"10.1038/s41432-026-01239-7","url":null,"abstract":"Awawdeh L, Almesleh B, Hammouri H, Al-Qudah A. The outcome of pulp revascularization of necrotic mature permanent teeth with periapical lesions using platelet-rich fibrin versus induced bleeding: a prospective preliminary randomized clinical trial. Clinical Oral Investigations. 2026; https://doi.org/10.1007/s00784-026-06877-w . A single-centre, prospective, two-arm parallel randomised clinical trial presented as a preliminary (early-phase) investigation. Fifty adults presenting with mature permanent teeth where the pulpal status was diagnosed as necrotic with associated periapical lesions were included. The pool of patients was allocated to one of two regenerative endodontic treatment protocols, each containing 25 patients. In one group, 25 patients underwent a procedure where a canal scaffold was generated by deliberately provoking bleeding from the periapical tissues (induced bleeding, IB). In the second group of patients, an autologous platelet-rich fibrin (PRF) membrane was placed to serve as a biological barrier. A clinical and radiographic review was done at baseline, 6 months, and 12 months after treatment completion. Pre-specified endpoints were set to determine, firstly, tooth survival and overall treatment success and secondly, periradicular healing through radiographic evaluation. Within- and between-group comparisons were made using the appropriate statistical tests and statistical significance was set at p < 0.05. At the one-year mark, 98% of teeth had survived (47/48). Interestingly, survival did not differ meaningfully between the two treatment groups (p = 0.166). Both treatment options produced healing with a statistically significant reduction in periradicular pathology compared with baseline at the six- and twelve-month reviews (p < 0.001). Also, a statistically significant impact was found on the overall success rate at the endpoint (p = 0.022). In the IB group, a 100% success rate was achieved (23/23) compared to 75% in the PRF group (18/24), with a combined overall success of 85.4%. Whichever treatment pathway was followed, all teeth survived the chosen regenerative endodontic procedure after 12 months. The preliminary results indicated that results and clinical outcomes were comparable. Although the IB option showed a higher overall success rate, this finding should be interpreted with caution as the results fall within the early phase clinical evidence framework. Further investigations are required to determine the superiority of one method over the other.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"80-82"},"PeriodicalIF":2.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148653169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-designed fixed dental restorations show promise, but expert human oversight remains essential","authors":"Mojtaba Mehrabanian, Maaz Anwer Memon","doi":"10.1038/s41432-026-01243-x","DOIUrl":"10.1038/s41432-026-01243-x","url":null,"abstract":"Limpuangthip N, Hlaing NHMM, Lee SJ, Lee JH. Design quality and time efficiency of AI-based versus human-based design for tooth- and implant-supported fixed dental restorations: A systematic review. Journal of Dentistry, 170, 106644. https://doi.org/10.1016/j.jdent.2026.106644 This systematic review compared fully automated AI-based and human-based digital workflows for the design of fixed dental restorations. The authors conducted electronic searches in PubMed/MEDLINE, Embase, Scopus, and the Cochrane Library as well as a manual screening of relevant references. The review followed PRISMA guidelines and was based on a registered protocol. To ensure inclusion of the most current evidence, the literature search was performed initially and updated before final data extraction and manuscript preparation. Comparative studies evaluating AI-generated designs for tooth- or implant-supported single or multiunit fixed dental restorations were included when a human-designed restoration served as the comparator. Fifteen studies fulfilled the inclusion criteria. The evaluated restorations included single-unit anterior and posterior crowns, inlays, implant-supported crowns, and three-unit fixed dental prostheses. Two reviewers independently screened studies, extracted data, and assessed methodological quality using the Methodological Index for Non-Randomised Studies (MINORS). Outcomes included restoration morphology, occlusal relationships, proximal contacts, finish-line detection, marginal adaptation, internal fit, design efficiency, and design success rates. Due to considerable heterogeneity in restoration types, AI software platforms, outcome measures, and assessment methods, a meta-analysis was not feasible, and findings were synthesised narratively. Across most studies, AI-generated single-unit crowns demonstrated morphology, marginal adaptation, finish-line accuracy, and internal fit that were generally comparable with human-designed restorations. However, AI systems frequently produced less favourable proximal and occlusal contacts and often required refinement by experienced operators to achieve optimal clinical acceptability. AI-designed inlays and three-unit fixed dental prostheses showed greater deviations from human-designed restorations, particularly in occlusal relationships, connector design, and contact formation. Evidence for implant-supported crowns was limited but suggested performance comparable to human designs. AI-based workflows consistently reduced design time compared with conventional human-based workflows and appeared particularly beneficial for less experienced operators. Current evidence suggests that AI-assisted restoration design can generate clinically acceptable single-unit crown restorations while substantially improving workflow efficiency. Nevertheless, expert human verification and refinement remain necessary, particularly for occlusal function, proximal contacts, aesthetics, and more complex prosthodontic restorations. Cu","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"75-77"},"PeriodicalIF":2.9,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148600953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can smartphone cameras be a viable alternative to digital single-lens reflex (DSLR) cameras for dental shade assessment?","authors":"Mohammad Zakaria Nassani, Enass Shamsy, Giath Gazal","doi":"10.1038/s41432-026-01242-y","DOIUrl":"10.1038/s41432-026-01242-y","url":null,"abstract":"Alhumoud T, Zankawi A, Li KY, Yu O, Pow E, Lam W. Performance of smartphone cameras for measuring and analyzing dental shade: A systematic review. J Dent. 2026; 166:106506. https://doi.org/10.1016/j.jdent.2026.106506 . A systematic review evaluating the performance of digital single-lens reflex (DSLR) and smartphone-acquired photographs for dental shade assessment. The review followed PRISMA 2020 guidelines, was registered in PROSPERO (CRD42024580518), and searched five electronic databases: PubMed, Scopus, Embase, Web of Science, and the Cochrane Central Register of Controlled Trials (CENTRAL). Eligible studies comprised both in vivo and in vitro experimental designs evaluating dental shade assessment using smartphone cameras compared with DSLR cameras. Primary outcomes included colour difference (ΔE) relative to a reference standard (accuracy) and/or between devices (agreement). Studies evaluating three-dimensional imaging modalities, such as intraoral scanners, as well as teeth affected by bleaching, restoration discoloration, or carious lesions within the shade assessment area, were excluded. Only English-language full-text articles were eligible, while conference papers, case reports, and review articles were excluded. Risk of bias was assessed using a modified QUADAS-2 tool, and the certainty of evidence was evaluated using the GRADE framework. Due to extreme heterogeneity in study designs, imaging protocols, camera systems, and outcome assessment methods, meta-analysis was not considered appropriate. Findings were therefore synthesised narratively and presented using descriptive forest plots. Eight studies were included, comprising three in vivo, three in vitro, and two mixed-design studies. Findings regarding colour difference (ΔE) were highly inconsistent, with some studies favouring DSLR cameras and others favouring smartphones for dental shade assessment. Considerable clinical, methodological, and statistical heterogeneity (I2 = 100%) was observed across camera models, lighting conditions, calibration protocols, and reference standards. Overall, the evidence did not demonstrate a consistent superiority of either device, and the certainty of the evidence was judged to be very low. The available evidence comparing smartphone and DSLR photography for dental shade assessment is heterogeneous and inconclusive. Neither device has demonstrated consistent superiority, suggesting that standardised image acquisition, calibration, and image-processing protocols may be more important than the choice of camera system. Future research should adopt standardized methodologies and workflows to support evidence-based recommendations for device selection in dental shade matching.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"78-79"},"PeriodicalIF":2.9,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148600982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can artificial intelligence training improve clinical decision-making during deep caries excavation?","authors":"Malik Alkabazi, Melek Tassoker","doi":"10.1038/s41432-026-01240-0","DOIUrl":"10.1038/s41432-026-01240-0","url":null,"abstract":"Ramezanzade S, Dascalu TL, Bakhshandeh A, Uribe SE, Ibragimov B, Bjørndal L. The impact of training dental students to use an artificial intelligence-based platform for pulp exposure prediction prior to deep caries excavation: a proof-of-concept randomized controlled trial. Int Endod J. 2026;59:1248–56. https://doi.org/10.1111/iej.70046 This randomized controlled trial (RCT) evaluated whether a structured educational intervention could improve dental students’ interaction with an artificial intelligence (AI)-based decision-support system developed to predict pulp exposure before excavation of deep carious lesions. Eighteen dental students were randomly allocated to either an experimental group receiving a one-hour personalized training session on the use of the AI platform or a control group receiving a brief introductory video. Participants subsequently completed a case-based assessment involving radiographic evaluation of deep carious lesions and prediction of pulp exposure risk using the AI system. The primary outcome was agreement with AI recommendations (“agreeableness with AI”). Secondary outcomes included diagnostic accuracy, sensitivity, specificity, F1-score, and response time. Outcomes were compared between groups, and the findings were used to estimate the sample size required for a future definitive trial. Participants who received AI-focused training demonstrated greater agreement with AI recommendations than controls. However, improvements in agreement were not accompanied by meaningful differences in diagnostic accuracy, sensitivity, specificity, or F1-score. Response times were slightly shorter among trained participants. The findings suggest that targeted instruction may influence how users interact with AI systems, although objective diagnostic performance remained largely unchanged. A short, personalized training session may increase dental students’ agreement with AI-generated predictions of pulp exposure during deep caries excavation. However, the intervention did not substantially improve diagnostic performance, and no patient-centered outcomes were assessed. Larger studies are needed to determine whether AI training can enhance clinical decision-making and improve outcomes relevant to the management of deep carious lesions.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"72-74"},"PeriodicalIF":2.9,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148600973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resin infiltration or bioactive adhesive: which treatment provides better esthetic satisfaction for post-orthodontic white spot lesions?","authors":"Hisham Mohammed, Matthew Nangle, William Aung, Deborah Du","doi":"10.1038/s41432-026-01241-z","DOIUrl":"10.1038/s41432-026-01241-z","url":null,"abstract":"Albashaireh ZS, Altallaq MK. Assessment of patient satisfaction and esthetic outcomes following treatment of post-orthodontic white spot lesions using a bioactive adhesive and resin infiltrant: a randomized split-mouth clinical trial. Journal of Dentistry. 2026;167:106565. Split-mouth randomized clinical trial of 20 orthodontically treated patients (13 female, 7 male) involving 120 teeth with anterior white spot lesions (WSLs). Each participant received ICON resin infiltration or Hi-Bond Universal in contralateral quadrants. Esthetic changes were assessed by the patients and by two independent clinicians using a 100-point visual analogue scale (VAS) at one-month recall. Participants aged 16–30 years and who had completed fixed orthodontic treatment at least one month before enrollment were included. Eligible participants presented with at least one visible WSL on the labial surfaces of the anterior teeth or premolars on contralateral quadrants. All participants were required to have good oral hygiene, clinically healthy gingival tissues, and no evidence of active periodontal disease. Categorical outcome data were presented using descriptive summary measures including frequencies and percentages. The proportion of satisfactory vs. unsatisfactory outcomes (paired binary data) was compared between the Hi-Bond Universal and ICON treatments using the McNemar test. Overall patient satisfaction was equally high (80%) for both treatments, and there were no significant differences between patient or clinician ratings. Inter-assessor agreement was deemed “fair” for both groups (Cohen’s kappa 0.318–0.340). Thus, both ICON and Hi-Bond Universal effectively masked WSLs, as deemed by subjective esthetic evaluation. Both bioactive adhesives and resin infiltration achieve satisfactory esthetic outcomes in masking demineralized enamel, at least in the short-term. Further longitudinal studies comparing the outcomes of these materials would be beneficial to determine whether these effects are sustained over time.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"70-71"},"PeriodicalIF":2.9,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41432-026-01241-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148583870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Should chlorhexidine mouthwash be a concern for blood pressure in dental patients?","authors":"Mahdi Mutahar, Akram Alshirah, Essam Ahmed Al-Moraissi","doi":"10.1038/s41432-026-01233-z","DOIUrl":"10.1038/s41432-026-01233-z","url":null,"abstract":"Toonen LSJ, et al. The Effect of Chlorhexidine Mouthwash on Blood Pressure: A Systematic Review and Meta-Analysis. Int J Dent Hyg. 2026. https://doi.org/10.1111/idh.70035 . To evaluate whether current clinical evidence supports an association between chlorhexidine mouthwash (CHX-MW) use and changes in blood pressure in human populations. Evidence was derived from a systematic review and meta-analysis of studies identified through PubMed/MEDLINE and Cochrane CENTRAL up to December 2024. Randomised, controlled, and observational studies evaluating blood pressure following chlorhexidine mouthwash use were included. Evidence was synthesised through narrative review and meta-analysis, with methodological quality and risk of bias assessed using established appraisal frameworks. Five studies met the inclusion criteria. Although two studies reported small increases in blood pressure, the pooled analysis found no statistically or clinically significant effect of chlorhexidine mouthwash on systolic or diastolic blood pressure. Current evidence does not demonstrate a clinically meaningful effect of chlorhexidine mouthwash on blood pressure, but certainty remains low due to methodological limitations and indirectness of study populations.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"65-66"},"PeriodicalIF":2.9,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41432-026-01233-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148411126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can oral health education during pregnancy promote lasting behavioural changes?","authors":"Mayara da Costa Motta, Lucas Alves Jural, Andréa Fonseca-Gonçalves","doi":"10.1038/s41432-026-01236-w","DOIUrl":"10.1038/s41432-026-01236-w","url":null,"abstract":"Chen P, Li M, Zhang Q, Qiu M, Yu X. Effects of an oral health management program during pregnancy: a randomized controlled trial. Oral Dis. 2026 32:240-50. https://doi.org/10.1111/odi.70076 . A randomized, controlled, single-blinded clinical trial aimed to evaluate the effectiveness of an educational program based on the Health Belief Model on self-care, oral health behaviors, and periodontal clinical indicators in pregnant women. Pregnant women from a community health center in China were randomly assigned to two groups in a 1.5:1 ratio—intervention group (n = 39) and control group (n = 26). The control group received one face-to-face education, while the intervention group participated in a 4-week program with online follow-up, lectures, video calls, and ongoing support to encourage oral health care. Oral health self-efficacy, assessed by the Self-efficacy Scale for Self-care (SESS); three periodontal clinical indicators (gingival index - GI, plaque index—PLI, and periodontal index—PI); and oral health–related behaviors, assessed by a self-designed questionnaire, were evaluated at three time points: baseline (T0), post-intervention (T1), and after two months of follow-up (T2). Between-group comparisons used independent t-test or Mann–Whitney U test for continuous variables, and chi-square for categorical variables. Intervention effects were evaluated by repeated-measures one- way ANOVA; and a significance level was set at 5%. No statistically significant differences were observed between groups in sociodemographic or gestational characteristics observed in T0. The educational program improved pregnant women’s oral health SESS across all three domains relative to baseline (T0: 55.9 ± 8.3), with a significant immediate increase after the intervention (T1: 63.2 ± 7.8). There was a slight decline at two months (T2: 60.8 ± 8.2), but scores remained above baseline. Compared with the control group, the intervention group generally showed significantly higher scores at both T1 and T2. Both groups had significant increases in GI, PLI, and CPI versus baseline. At T1, the intervention group had significantly higher GI and PLI than the control; at T2, only PLI remained significantly higher in the intervention group. Regarding behaviors, the intervention group showed greater improvement at both post-baseline times, with relative maintenance at T2, notably longer brushing time per occasion and higher weekly flossing frequency at T1 and T2. No differences were found between groups in daily brushing frequency or brushing technique. The study concluded that the Health Belief Model–based educational program was effective in increasing oral health self-efficacy, promoting healthy habits, and improving clinical conditions in pregnant women. However, some outcomes regressed by the second month of follow-up.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"67-69"},"PeriodicalIF":2.9,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148404167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Soft tissue grafting at immediate implants: does it protect the buccal plate?","authors":"Sunkanmi Olaore, Pynadath George, Kathryn Taylor","doi":"10.1038/s41432-026-01234-y","DOIUrl":"10.1038/s41432-026-01234-y","url":null,"abstract":"Jung M, Tran D, Chang CC, Kim SK, Tsukiboshi Y, Min S, Ayilavarapu S, Lee CT. Volumetric buccal bone alterations at immediate implant sites with or without soft tissue augmentation: A 6-month assessment. J Periodontol. 2026;97:220–33. https://doi.org/10.1002/jper.11381 . This was a secondary analysis of cone-beam computed tomography (CBCT) and scanned model data from a registered randomised controlled trial evaluating immediate implant placement with or without soft tissue augmentation1. The study compared immediate implant placement with subepithelial connective tissue grafting, immediate implant placement with acellular dermal matrix, and immediate implant placement without soft tissue augmentation (control). Forty-five patients requiring extraction of a single maxillary anterior or premolar tooth followed by immediate implant placement were included. Participants were allocated to one of three groups: immediate implant with subepithelial connective tissue graft, immediate implant with acellular dermal matrix, or immediate implant alone. In all groups, the gap between the implant and the alveolar bone was filled with bovine bone material and a collagen dressing was placed. CBCT scans were taken before extraction and 6 months after immediate implant placement. The scans were superimposed to assess three-dimensional volumetric and two-dimensional linear buccal bone dimensional changes. The buccal region was divided into coronal, middle and apical thirds. Volumetric bone loss was calculated in absolute and relative terms. Linear horizontal and vertical bone changes were also assessed. Measurements were carried out by a calibrated blinded examiner. Statistical analysis included ANOVA or Kruskal–Wallis tests, linear regression analysis to explore associations between clinical factors and volumetric bone change, and Pearson correlation coefficients to compare 3D and 2D measurements. There was no statistically significant difference in volumetric buccal bone loss between the three groups at 6 months. The greatest loss occurred in the coronal third, with mean volumetric reductions of −14.99 ± 4.29 mm³ in the connective tissue graft group, −13.60 ± 3.97 mm³ in the acellular dermal matrix group, and −12.58 ± 4.09 mm³ in the control group (p = 0.286). Thick bone morphotype was associated with greater absolute volumetric bone loss. Correlations between 3D and 2D measurements varied between anatomical segments. Soft tissue augmentation using either a subepithelial connective tissue graft or acellular dermal matrix did not significantly reduce buccal bone dimensional loss at immediate implant sites after 6 months. Linear measurements may not represent fully volumetric buccal bone changes.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"63-64"},"PeriodicalIF":2.9,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41432-026-01234-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148404085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Selective caries removal or pulpotomy: which approach is better for ‘deep’ carious lesions?","authors":"Neeraj Gugnani, Shalini Gugnani","doi":"10.1038/s41432-026-01235-x","DOIUrl":"10.1038/s41432-026-01235-x","url":null,"abstract":"Chew JJR, Tan SHX, Chua SKX, Lui JN, Sim YF, Yu VSH. Three-Year Clinical and Economic Evaluation of Selective Caries Removal and Full Pulpotomy for Extensive Caries: An Exploratory Randomised Controlled Trial. Int Endod J. 2026;59:439–53. Epub 2025 Nov 25. PMID: 41288117; PMCID: PMC12884239. The aim of the study was to compare selective caries removal (SCR) with full pulpotomy for managing deeply carious vital permanent teeth. The primary objective was to evaluate pulp survival and the need for further intervention over a 3-year period, and to assess the cost-effectiveness of both interventions. This was an exploratory, two-arm, randomized clinical trial conducted on mature permanent teeth with deep or extremely deep carious lesions. A total of 120 vital teeth with no signs of symptomatic irreversible pulpitis or apical pathology were selected from 101 patients. They were randomly assigned to receive either SCR or a full pulpotomy. Clinical and radiographic evaluations were performed at 6 months, 1 year, and 3 years. Survival analysis was performed using Kaplan-Meier plots, while Cox proportional hazards regression was used to evaluate the effect of treatment on survival over time. Economic evaluation was also conducted from both healthcare and societal perspectives. At the 3-year follow-up, 44/58 teeth in the SCR group and 37/55 teeth in the pulpotomy group were available for analysis. At the end of the study period, overall, 79% of treated teeth did not require further intervention. Failures were higher in the SCR group than in the pulpotomy group (29.5% vs 10.8%; p = 0.039), and survival rates were lower in the SCR group (74.1% vs 89.1%; p = 0.041 adjusted rates). Time-to-event analysis suggested a higher hazard of failure with SCR, although this was not statistically significant (adjusted HR = 2.58; 95% CI 0.80–8.30). Full pulpotomy, despite higher initial costs, was more cost-effective, becoming favorable at willingness-to-pay thresholds of approximately US$917 and US$928 per RCT/extraction avoided, from healthcare and societal perspectives, respectively. Full pulpotomy appears more effective than SCR in extremely deep lesions, while outcomes in deep lesions remain comparable. However, a large proportion of lesions were extremely deep, which may have influenced these findings.","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"61-62"},"PeriodicalIF":2.9,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of deep machine learning in dental education: a systematic review of effectiveness in dental students' teaching learning outcomes","authors":"Kirti Buva, Ajinkya Deshmukh, Mrinal Shete, Anagha Shete, Parag Gangurde","doi":"10.1038/s41432-026-01226-y","DOIUrl":"10.1038/s41432-026-01226-y","url":null,"abstract":"Deep machine learning (DML) technologies, including convolutional neural networks (CNN) and transformer-based models, are increasingly used to support teaching and diagnostic reasoning in dental education. However, the evidence regarding their effectiveness in improving cognitive learning outcomes among dental students remains fragmented and highly heterogeneous. To systematically evaluate the impact of DML-based educational and diagnostic interventions on cognitive learning outcomes among dental students, compared with conventional or non-artificial intelligence methods. PRISMA 2020 guidelines were followed strictly. Comprehensive searches were conducted across PubMed/MEDLINE, Scopus, Web of Science, Cochrane CENTRAL, IEEE Xplore, Google Scholar, and preprint servers like medRxiv, bioRxiv and arXiv. Eligible studies included randomized trials, quasi-experimental designs, and controlled pre–post studies involving dental students, evaluating DML interventions with at least one measurable cognitive outcome like diagnostic accuracy, reasoning, and cognitive load. Two reviewers independently screened records and extracted data; inter-reviewer agreement exceeded κ > 0.80. Risk of bias was assessed using RoB 2.0, ROBINS-I, and AXIS tools. Certainty of evidence was appraised using GRADE. Due to marked heterogeneity in outcomes and model types, meta-analysis was not feasible. Of 145 records, 16 studies met the inclusion criteria. Interventions consisted primarily of CNN-based radiographic systems, AI-assisted diagnostic tools, and transformer-based large language models. Across diagnostic accuracy outcomes, most studies reported improvements in sensitivity, F1 scores, and pattern recognition when using DML tools compared with traditional methods. Evidence for improvements in cognitive reasoning, assignment quality, or cognitive load was mixed and often limited by small samples, subjective evaluations, and nonrandomized designs. One study reported lower post-test scores among students using LLM-generated assistance compared with conventional teaching. No study assessed long-term learning retention. Overall risk of bias ranged from low to moderate, and the certainty of evidence was moderate for diagnostic accuracy and low for all other cognitive outcomes. Heterogeneity in interventions, outcomes, and assessment methods precluded meta-analysis. Some outcomes were subjective, and long-term retention was rarely assessed. DML-assisted interventions show promising but preliminary potential to enhance specific cognitive domains, particularly diagnostic accuracy in dental education. However, the overall evidence remains limited by study heterogeneity, small samples, and methodological weaknesses. Current findings support the adjunctive, not substitutive, use of DML tools in dental curricula. High-quality multicenter RCTs with standardized cognitive outcome measures and longitudinal follow-up are needed to determine the sustained educational value and practical","PeriodicalId":12234,"journal":{"name":"Evidence-based dentistry","volume":"27 3","pages":"83-83"},"PeriodicalIF":2.9,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148396472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}