Objectives: The objective of the study is to evaluate the information quality, reliability, and clinical utility of DeepSeek AI’s responses to frequently asked questions (FAQs) about orthodontic aligners. Material and Methods: Seventeen orthodontic aligner FAQs were systematically compiled from clinical expertise and public search analysis. Each question was presented twice to DeepSeek AI (version 3.1) with a 1-week interval. A blinded orthodontist evaluated all 34 responses using a modified 5-point Global Quality Scale (GQS). Intra-rater reliability was assessed through weighted Cohen’s kappa and intraclass correlation coefficient (ICC). AI performance was analyzed for proficiency (low/high-threshold criteria), test-retest reliability (ICC), and internal consistency (Cronbach’s alpha). Results: Expert intra-rater reliability was excellent (κ w = 0.89, ICC = 0.92). DeepSeek AI demonstrated exceptional performance: 100% of questions met low-threshold proficiency (GQS ≥4 both rounds), while 94.1% achieved high-threshold proficiency (GQS = 5 both rounds). Test-retest reliability was excellent (ICC = 0.98), and internal consistency was high (α = 0.96). Qualitative assessment revealed perfect scores in accuracy, clarity, and actionability, with minor reductions in completeness (4.97/5) and objectivity (4.94/5) for comparative questions. Conclusion: DeepSeek AI generates high-quality, reliable information for patient education about orthodontic aligners, demonstrating near-perfect proficiency and consistency. While it excels in factual content, minor limitations exist in balanced comparative analysis. These findings support the cautious integration of AI as a supplementary educational tool in orthodontic practice, with professional oversight recommended for clinical discussions.
Objectives: Facial anthropometry as a diagnostic and analytical tool has been increasingly popular in orthodontics. This project aims to find an alternative to the currently available high-cost imaging equipment that satisfies a strictly high standard of accuracy in producing a fully textured facial scan. Material and Methods: A set of 12 mannequin heads was anatomically landmarked and scanned using a verified industrial-level 3D scanner, followed by two budget mobile phone applications. The comparison includes 3D model surface analysis and assessment of the accuracy of image texture warping. Results: The results showed a comparable level of accuracy of one of the applications (EM3D) which showed a close 3D model topographical match with the model created by the industrial scanner (mean square root distance (0.175 mm ± 0.104). In addition to that, there was a low level of error average (0.243 ± 0.274 mm) associated with 3D image texture warping. Conclusion: The results of this project showed that mobile phone applications can be considered as alternative diagnostic and assessment tools in clinical and research environments.
Objectives: Precise estimation of the treatment duration and selection of proper appliances have always been a challenge clinically due to individual variables such as growth, compliance, and complexity of the case. At present, advances in artificial intelligence (AI) provide opportunities for improvement in diagnostic precision by integrating clinical and imaging data. This research assessed the development and validation of an ensemble learning-based AI model that could estimate with accuracy the duration of orthodontic treatment by integrating cephalometric measurements with standardized photographic data for the determination of appliance type between fixed appliances and clear aligners. Material and Methods: We conducted a retrospective observational research study using anonymized data of 450 orthodontic patients aged between 12 and 35 years. Each record included pre-treatment lateral cephalograms, intraoral and extraoral photographs, appliance type, and treatment duration. The dataset was further divided into two parts – an 80% training set and a 20% testing set – in a random manner. Four models have been trained and compared: Support vector machines, decision trees, convolutional neural networks, and ensemble (hybrid fusion of cephalometric and photographic features). Predictive performance was assessed for accuracy, precision, recall, F1 score, and area under the receiver operating characteristic (AUC-ROC). Model predictions were compared with expert consensus using Cohen’s κ statistic and Bland–Altman analysis. Results: The ensemble model performed best, with an accuracy of 89%, precision of 90%, recall of 88%, F1 score of 0.89, and AUC-ROC of 0.92. For treatment duration, the mean absolute error was 1.5 months (95% confidence interval: 1.2–1.8), which reflects about 7–8% deviation from the average clinical duration of 20.7 ± 4.9 months. Model–expert agreement was highly reliable (κ = 0.86), demonstrating clinically acceptable error margins. Conclusion: An ensemble AI model that integrates cephalometric and photographic features reliably predicts the duration of orthodontic treatment and appliance type, and perhaps in the future, an adjunctive tool for evidence-based treatment planning.
The use of photography has been incorporated into orthodontic practices since the early days of the specialty. Despite the absence of a universal standard, the most commonly used intraoral images are the following 5 photographic shots (frontal, buccal right and left, and maxillary and mandibular occlusal views). Interestingly, these intraoral photographs do not include the evaluation of the mandibular arch with the same detail as the maxillary arch. Therefore, the purpose of this article is to discuss the inclusion of another photograph in the series of five intraoral photographs, based on the arguments presented here. The incorporation of a frontal intraoral photograph taken with a semi-open mouth does not generate additional time or financial cost to orthodontists, but it enriches the photographic records, adding valuable information from the mandibular arch, such as the anatomy and leveling of the incisors, the real depth of the Curve of Spee, and the torque of the posterior teeth.
This paper highlights the critical role of digital workflows and decision flows in interdisciplinary dental treatment planning, emphasizing their integration into clinical practice. By incorporating tools such as intraoral scanning, cone-beam computed tomography, virtual model setups, and structured decision flows, digital workflows enhance precision, improve communication, and facilitate collaboration among orthodontic, periodontal, and prosthodontic specialties. Two clinical cases illustrate these benefits: the first involves an implant-first approach, where virtual setups guided implant placement and provided stable anchorage to address lower anterior crowding. The second case demonstrates full-mouth reconstruction, utilizing virtual simulations to evaluate treatment feasibility, guide space redistribution, and coordinate implant and prosthetic planning. These examples emphasize how digital workflows and structured decision flows enable seamless collaboration and achieve precise, patient-centered outcomes.
