Background: Dental caries is the most prevalent chronic, noncommunicable condition affecting individuals of all ages and socio-economic status. The recent technological advancements in artificial intelligence (AI), digital diagnostics, and teledentistry have been genuinely promising in revolutionizing the future of early caries detection and preventive care. However, an integrated understanding of these advancements and their clinical readiness remains limited.
Aim: To systematically map and synthesize the current evidence on the use of AI, digital diagnostic technologies, and teledentistry for the early diagnosis in dental caries.
Method: This scoping review followed the Arksey and O'Malley framework and adhered to PRISMA-ScR guidelines. Studies published between 1997 and 2025 were identified through PubMed, Scopus, Web of Science, and manual searches. Articles with AI, digital diagnostic tools, or teledentistry for caries detection were selected, with a specific focus on early caries detection. Data extraction was performed using a standardized charting form and narration across three topics: AI-assisted diagnostics, digital tools, and remote detection through teledentistry.
Results: Thirty studies were considered after screening and evaluation of eligibility as they met the selection criteria out of 1000 initial records. The studies included retrospective (n = 10), prospective (n = 7), diagnostic accuracy (n = 6), in-vitro (n = 5), and feasibility studies (n = 2). AI-supported studies showed excellent diagnostic accuracy ranging from well over 90% for the more performing AI to sensitivity and specificity values of 80-95%. However, digital methods, including near-infrared light transillumination, laser fluorescence, photothermal imaging, and ultrasonic technology yielded mixed but positive results in early lesion identification.
Conclusion: This scoping review highlights the increasing role of AI, digital diagnostics, and teledentistry in the early detection of dental caries. These technologies augment diagnostic precision, improve preventive care, and provide greater access, particularly for underserved areas. However, regarding real-world validation, standardization and ethical integration remain challenges. Future work needed in clinical trials, data quality, and regulatory harmonization to support safe, effective, and equitable implementation in dental practice.
A commentary on: Abbott LP, Saikia A, Anthonappa RP. Artificial intelligence platforms in dental caries detection: a systematic review and meta-analysis. J Evid Based Dent Pract. 2025; https://doi.org/10.1016/j.jebdp.2024.102077 .
Data sources: The search strategy for this review aimed to identify published articles that have used either clinical or X-ray images for AI model development. The search was carried out in eight electronic databases, including Scopus, Web of Science, MEDLINE, Educational Resources Information Centre, Institute of Electrical and Electronics, Science Direct, Directory of Open Access Journals, and JSTOR. Studies published in English from January 2000 to March were selected.
Study selection: Based on predefined criteria, 2538 articles were retrieved from the search; after deduplication and exclusion of articles that did not meet the inclusion/exclusion criteria, 45 articles were included in the review. Of these, 33 studies had used dental radiographs and 12 had used clinical images.
Data extraction and synthesis: All the included articles were assessed for quality using QUADAS-2 and the CLAIM checklist. The results from all included studies were narratively summarized, reporting on various parameters, ranges, and mean accuracy achieved, as well as details of the annotation tool, AI platform, etc. In addition, a meta-analysis was conducted that included seven studies.
Results: The mean accuracy was 78.2% (95% CI: 72-84.4%) for clinical image studies and 81.5% (95% CI: 72.7-90.3%) for studies that included X-ray images. Based on a meta-analysis, the overall sensitivity and specificity were 76% (95% CI: 65-85%) and 91% (95% CI: 86-95%), respectively. An HSROC curve was also generated, indicating an AUC of 92% (95% CI: 89-94%).
Conclusions: AI models exhibited high sensitivity and specificity for caries detection.
A commentary on: Sabeti M, Harouni A, Gabbay J. Comparing Ultrasonically Activated Irrigation and Laser-Activated Irrigation for Postoperative Pain Reduction in Endodontics: A Systematic Review and Meta-analysis of Randomized Controlled Trials. Journal of Endodontics 20251.
Objective: A recent systematic review and meta-analysis evaluated whether laser-activated irrigation offers a measurable benefit over ultrasonic activation in reducing postoperative endodontic pain. Seven randomized controlled trials involving 490 teeth were included. Across multiple time points (6 h to 7 days), LAI demonstrated a consistently greater reduction in patient-reported pain than UAI, with the effect most pronounced at 24-48 h post-treatment. Pulsed Er:YAG laser modalities-particularly PIPS and SWEEPS-showed the highest analgesic effect, while diode lasers showed little to no added benefit. Despite moderate to high heterogeneity and some concerns regarding allocation concealment in several trials, the overall certainty of evidence was rated low-to-moderate. The findings suggest that LAI, especially advanced Er:YAG-based protocols, may provide short-term pain.
Clinical significance: While LAI-particularly Er:YAG systems-may enhance short-term patient comfort, UAI remains an effective and pragmatic standard in typical dental practice.
Design: Systematic review and meta-analysis (PRISMA-compliant), prospectively registered on PROSPERO.
Case selection: Adult patients undergoing primary non-surgical root canal treatment for irreversible pulpitis, necrotic pulp, or apical periodontitis. Only RCTs comparing LAI vs UAI with postoperative VAS pain measurements were included.
Data analysis: Random-effects modeling, subgroup analyses by laser type and timepoint, sensitivity analyses excluding imputed data, and GRADE certainty assessment.
Results: LAI demonstrated superior postoperative pain reduction compared to UAI. Er:YAG-based systems (PIPS, SWEEPS) showed the strongest effects. Diode lasers showed minimal benefit. Heterogeneity remained high.
Conclusions: LAI provides measurable short-term postoperative pain benefits but should not be recommended as a replacement for UAI in routine practice due to cost and accessibility challenges.
A commentary on: Chaple Gil A, Díaz L, Von Marttens A, Sotomayor C, Basualdo J, Beltrán V, Jorquera G, Caviedes R, Fernández E. The efficacy of low-level laser therapy in oral surgery: a systematic review of randomized controlled trials. Photodiagnosis Photodyn Ther 2025; https://doi.org/10.1016/j.pdpdt.2025.104594 .
Design: This systematic review followed PRISMA 2020 guidelines and evaluated randomised controlled trials investigating the effect of low-level laser therapy on postoperative healing and comfort following oral surgery. The protocol was registered in PROSPERO. The Cochrane RoB 2 tool was used for quality assessment, and the PROPS framework was applied to interpret the clinical relevance of outcomes such as pain and wound healing.
Case selection: Eighteen randomised controlled trials involving 771 participants were included. The surgical procedures comprised third molar extraction, implant placement and a range of periodontal and mucogingival procedures. Most participants were healthy adults. Laser parameters ranged from 660 to 1064 nm in wavelength and from 3 to 35 J/cm² in fluence.
Data analysis: Because of variability in laser parameters, timing of therapy and outcome measures, meta-analysis was not feasible. The authors therefore synthesised the findings narratively, focusing on postoperative pain, inflammation and tissue healing.
Results: Low-level laser therapy significantly improved early epithelialisation and soft tissue healing in the included trials, particularly when wavelengths between 660 and 810 nm and fluences between 3 and 12 J/cm² were used. Several studies reported reductions in inflammatory cytokines such as tumour necrosis factor alpha and interleukin-6, together with increased vascular endothelial growth factor expression. Pain scores decreased by ~30-55% within the first postoperative week, and several trials reported fewer postoperative complications, including delayed healing and local infection, in laser-treated groups. Twelve studies were judged to be at low risk of bias, five had some concerns and one was at high risk. Follow-up was predominantly short term (7-14 days) for soft-tissue outcomes, although a minority of implant-related studies extended observation to several months to assess bone and peri-implant parameters.
Conclusions: Low-level laser therapy appears to accelerate early healing and reduce postoperative pain after oral surgery, with no significant adverse effects reported and some evidence of reduced postoperative complication rates. However, heterogeneity in dosimetry, protocols and outcome assessment, together with generally small sample sizes and limited long-term follow-up, reduces confidence in the precision and durability of these effects, and the overall certainty of evidence remains low.
Objectives: This scoping review aims to systematically identify and theoretically categorise barriers and facilitators affecting access to dental care in LMICs.
Methods: This scoping review employed the Theoretical Domains Framework (TDF) to synthesise the findings thematically. A comprehensive search of literature published up to May 2025 in MEDLINE (PubMed), Embase, Scopus, and Web of Science, as well as grey literature sources, was conducted to identify relevant articles. Screening was performed using Rayyan, and data were extracted and categorised into the TDF domains.
Results: From the 15,140 initial hits, 214 articles were found eligible for final analysis. The maximum number of studies was published in India, Brazil, Nigeria and Iran. Eleven TDF domains were identified, and 'environmental context and resources' (n = 452, 41.5%) emerged as the most frequent domain, followed by 'beliefs about consequences' (n = 251, 23.1%) and 'knowledge' (n = 144, 13.2%). Barriers were more frequently reported than facilitators across all domains. Distinct domain patterns were observed across population subgroups and income categories, with structural barriers dominating in all contexts.
Conclusion: Findings from this review underscore the need for integrated, context-sensitive interventions that combine system-level reforms with behaviour change strategies to improve dental care utilisation and reduce inequalities in oral health access across LMICs. There is also a need for more research on this health issue in low-income countries.
A commentary on: Charoenniwassakul, R., S. Aruncharoensuk, K. Subbalekha, N. Mattheos, S. Jiaranuchart, A. Pimkhaokham. "Effect of Dental Implant Design on Stability During Early Healing: A Randomised Controlled Trial." J Clil Periodontol 2025; https://doi.org/10.1111/jcpe.70052 .
Design: Randomized clinical trial with two parallel groups, conducted to compare the primary and secondary stability of tapered and cylindrical dental implants during six weeks of healing. Stability was assessed using maximum insertion torque, also known as Maximum Insertion Torque (MIT), the Implant Stability Quotient obtained through resonance frequency analysis (ISQ), and the Implant Stability Test obtained through percussion analysis (IST).
Case selection: Healthy adults were included, with posterior edentulous areas healed for at least two months and with no need for bone grafting. Smokers and patients with uncontrolled systemic diseases, conditions affecting bone metabolism, or maxillomandibular pathologies were excluded. This selection favors experimental control but limits applicability to more complex clinical scenarios.
Data analysis: The study used repeated-measures analysis of variance and multiple imputation for missing follow-up data. Correlations between under-preparation, torque, and secondary stability were evaluated. Mechanical stability was interpreted separately from biological stability to characterize the transition throughout healing.
Results: Tapered implants demonstrated significantly higher MIT. Cylindrical implants presented higher ISQ and IST values at the end of six weeks. Both implant types exhibited the physiological pattern of transient stability reduction. The lack of standardization in osteotomy preparation between groups prevents differences from being attributed exclusively to implant design.
Conclusions: Both implant types achieved adequate stability for early loading protocols in healed bone of good quality. Surgical technique had a greater impact on primary stability than implant macrogeometry. The findings are not applicable to immediate loading, regenerated bone, or low-density bone sites.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：