Background/Objectives: Generative artificial intelligence (AI) such as ChatGPT has developed rapidly in recent years, and in the medical field, its usefulness for diagnostic assistance has been reported. However, there are few reports of AI use in dental fields. Methods: We created 20 questions that we had encountered in clinical pediatric dentistry, and collected the responses to these questions from three types of generative AI. The responses were evaluated on a 5-point scale by six pediatric dental specialists using the Global Quality Scale. Results: The average scores were >3 for the three types of generated AI tools that we tested; the overall average was 3.34. Although the responses for questions related to “consultations from guardians” or “systemic diseases” had high scores (>3.5), the score for questions related to “dental abnormalities” was 2.99, which was the lowest among the four categories. Conclusions: Our results show the usefulness of generative AI tools in clinical pediatric dentistry, indicating that these tools will be useful assistants in the dental field.

The presence of a supernumerary tooth is one of the most common dental anomalies, and surgical treatment is often required to address this anomaly. Moreover, it may lead to malocclusion, and long-term follow-up is important to monitor its status. A 4-year-and-11-month-old boy was referred to our hospital for dental caries treatment. At 5 years and 5 months of age, a radiographic examination showed a supernumerary tooth (first supernumerary tooth) near the permanent maxillary left central incisor, and it was extracted 6 months later. Eighteen months after the extraction of the first supernumerary tooth, a new supernumerary tooth (second supernumerary tooth) was detected in the same region, which was extracted when the patient was aged seven years and seven months. Seven months later, another supernumerary tooth (third supernumerary tooth) was detected and extracted immediately. However, the permanent maxillary left central incisor did not erupt spontaneously even after 6 months. Therefore, surgical exposure was performed, and the central incisor erupted into the oral cavity. This report describes our experience with this patient with three metachronous supernumerary teeth and their management until the eruption of the permanent tooth. This report highlights the importance of long-term follow-up after supernumerary tooth extraction until the permanent teeth in that region have erupted completely.

Background: Congenital absence of teeth is a major dental abnormality in pediatric dentistry and the absence of six or more teeth is defined as oligodontia. Few reports of patients with non-syndromic oligodontia without systemic disease have continued dental follow-up from an early age. Methods: We performed the five-year follow-up from before the eruption of the primary dentition of a Japanese child with non-syndromic oligodontia and analyzed changes in dental arch growth. Results: At the oral examination at the age of 1 year and 2 months, eight primary incisors were congenitally absent. Therefore, we made dentures for the patient at the age of 3 years and 4 months. From the age of 5 years and 1 month, the child received articulation training for dysarthria from a speech therapist to improve the function and appearance of the oral cavity. Measurement of the patient’s dental models revealed a particularly narrow dental arch, especially between the primary canines. Conclusions: Our findings highlight the importance of treatment for patients with non-syndromic oligodontia from an early age by multiple medical professionals, recognizing that the missing teeth affect the growth of the maxillofacial region.

Transfer learning (TL) is an alternative approach to the full training of deep learning (DL) models from scratch and can transfer knowledge gained from large-scale data to solve different problems. ImageNet, which is a publicly available large-scale dataset, is a commonly used dataset for TL-based image analysis; many studies have applied pre-trained models from ImageNet to clinical prediction tasks and have reported promising results. However, some have questioned the effectiveness of using ImageNet, which consists solely of natural images, for medical image analysis. The aim of this study was to evaluate whether pre-trained models using RadImageNet, which is a large-scale medical image dataset, could achieve superior performance in classification tasks in dental imaging modalities compared with ImageNet pre-trained models. To evaluate the classification performance of RadImageNet and ImageNet pre-trained models for TL, two dental imaging datasets were used. The tasks were (1) classifying the presence or absence of supernumerary teeth from a dataset of panoramic radiographs and (2) classifying sex from a dataset of lateral cephalometric radiographs. Performance was evaluated by comparing the area under the curve (AUC). On the panoramic radiograph dataset, the RadImageNet models gave average AUCs of 0.68 ± 0.15 (p < 0.01), and the ImageNet models had values of 0.74 ± 0.19. In contrast, on the lateral cephalometric dataset, the RadImageNet models demonstrated average AUCs of 0.76 ± 0.09, and the ImageNet models achieved values of 0.75 ± 0.17. The difference in performance between RadImageNet and ImageNet models in TL depends on the dental image dataset used.

Hemophilia is a congenital disorder associated with impaired blood clotting. Routine dental intervention to prevent oral bleeding in patients with hemophilia is considered important, but its effectiveness remains unknown. In the present study, we evaluated the effect of continual dental support on periodontal status and oral health habits in young patients with hemophilia. Of the 168 young patients with hemophilia who visited our clinic for 5 years, we selected subjects who had visited annually since 2015 and were in the mixed and permanent dentitions. To evaluate the periodontal status of these subjects, Community Periodontal Index (CPI) values in the molars and anterior teeth were measured. In addition, a questionnaire regarding oral health habits, including floss use, frequency of brushing by parents, and attending a family dentist, was administered to the subjects and their parents. In the patients with mixed dentition, the CPI values for the upper right molars and lower left central incisor decreased significantly in later years compared with the first year (p < 0.05). In the patients with permanent dentition, only one year recorded a significant decrease in CPI values compared with the first year (p < 0.05), localized in the upper right molars. The results of the questionnaire revealed that continual dental support improved dental floss use and the frequency of brushing by parents only in the mixed dentition group. Furthermore, these oral health habits significantly affected CPI values only in the mixed dentition group (p < 0.01). These results suggest that continual dental support improves the periodontal condition and oral health habits of hemophilic patients, especially those with mixed dentition.