Empowering Modern Dentistry: The Impact of Artificial Intelligence on Patient Care and Clinical Decision Making

Advancements in artificial intelligence (AI) are poised to catalyze a transformative shift across diverse dental disciplines including endodontics, oral radiology, orthodontics, pediatric dentistry, periodontology, prosthodontics, and restorative dentistry. This narrative review delineates the burgeoning role of AI in enhancing diagnostic precision, streamlining treatment planning, and potentially unveiling innovative therapeutic modalities, thereby elevating patient care standards. Recent analyses corroborate the superiority of AI-assisted methodologies over conventional techniques, affirming their capacity for personalization, accuracy, and efficiency in dental care. Central to these AI applications are convolutional neural networks and deep learning models, which have demonstrated efficacy in diagnosis, prognosis, and therapeutic decision making, in some instances surpassing traditional methods in complex cases. Despite these advancements, the integration of AI into clinical practice is accompanied by challenges, such as data security concerns, the demand for transparency in AI-generated outcomes, and the imperative for ongoing validation to establish the reliability and applicability of AI tools. This review underscores the prospective benefits of AI in dental practice, envisioning AI not as a replacement for dental professionals but as an adjunctive tool that fortifies the dental profession. While AI heralds improvements in diagnostics, treatment planning, and personalized care, ethical and practical considerations must be meticulously navigated to ensure responsible development of AI in dentistry.


Introduction
Artificial intelligence (AI) stands as a transformative power in today's digital revolution, affecting various economic sectors by performing tasks that typically require human intelligence.Its introduction to dentistry is particularly notable, offering new and improved ways to enhance diagnostic imaging, plan treatments, and manage patient care.This review aims to examine how AI is developing within dentistry and its significant influence on the dental profession.
Starting with the basics and moving to the latest advances, AI techniques like deep learning and neural networks are now used for identifying dental conditions, making treatment decisions, planning treatments, predicting outcomes, and forecasting the progression of diseases.These AI approaches are proving to be highly capable, in certain complex cases outperforming humans through the analysis of diverse data.This is especially apparent in AI's role in improving the accuracy of dental imaging and aiding in clinical decisions [1].
AI encompasses a broad range of technologies designed to simulate human intelligence, including natural language processing, computer vision, and machine learning.In dentistry, AI applications primarily involve machine learning (ML) and deep learning (DL) algorithms, which are capable of analyzing large datasets, recognizing patterns, and making predictions based on learned information.Key AI technologies used in dental applications include the following: supervised learning, unsupervised learning, reinforcement learning, and deep learning.Supervised learning approach involves training AI models on labeled datasets, enabling them to predict outcomes based on new, unseen data.Supervised learning is widely used in dental imaging for tasks such as detecting caries, identifying root fractures, and classifying dental restorations.Unlike supervised learning, unsupervised learning algorithms identify patterns in unlabeled data.While less common in dentistry, unsupervised learning can be valuable for discovering new insights from large datasets without predefined labels.Reinforcement learning involves training AI models to make decisions by rewarding desired outcomes.Although still emerging in dental applications, reinforcement learning holds potential for optimizing treatment plans and adaptive learning systems.A subset of ML, deep learning involves neural networks with multiple layers (deep neural networks).CNNs, a type of deep learning model, are particularly effective in image analysis and have been extensively applied in dental radiology and pathology.
In delving into the fusion of AI with various dental disciplines, this review illuminates its integration in applications such as dentition restoration detection, caries lesion identification, and periapical infection diagnosis, highlighting a promising horizon for AI's role in dentistry [2].Concurrently, the synergy between evidence-based dentistry (EBD) and intelligent technology is scrutinized.This necessitates ongoing research to surmount developmental challenges and fully harness AI's potential.By embracing both the innovations and the intricate challenges, this review endeavors to articulate a comprehensive perspective on the future of AI in dental medicine.
The motivation behind this research stems from the growing body of evidence suggesting that AI can outperform conventional diagnostic methods in several dental applications.AI algorithms, particularly those involving convolutional neural networks (CNNs) and deep learning frameworks, have demonstrated superior accuracy and efficiency in diagnosing dental conditions, planning treatments, and predicting outcomes.Despite these promising advancements, the integration of AI into routine dental practice faces numerous challenges, including methodological limitations, regulatory hurdles, and ethical considerations.
This review aims to provide a comprehensive overview of the current state of AI in dentistry, highlighting both the advancements and challenges associated with its application.By synthesizing findings from recent studies, this review seeks to elucidate the potential of AI to transform dental practice, identify the gaps and limitations in current methodologies, and propose directions for future research and clinical implementation.

Literature Search and Selection
In conducting this narrative review on the impact of artificial intelligence (AI) on patient care and clinical decision making in dentistry, a comprehensive literature search was performed to identify relevant studies and articles.The search strategy focused on three primary databases: PubMed, Scopus, and Google Scholar.The keywords used in the search included "artificial intelligence", "dentistry", "convolutional neural networks", "deep learning", "diagnostic accuracy", and "clinical decision-making".
The initial search yielded a substantial number of articles, which were then screened based on their titles and abstracts.
Inclusion criteria for the articles included the following: • Publications that discussed the role of artificial intelligence in various dental disciplines such as endodontics, oral radiology, orthodontics, pediatric dentistry, periodontology, prosthodontics, and restorative dentistry.

•
Studies that presented both quantitative and qualitative data on the effectiveness of AI in dental diagnostics and treatment.
• Articles published in English within the last two decades, given the rapid advancements in AI and its applications in medical imaging and diagnostics.

•
Exclusion criteria were as follows:

•
Studies that focused solely on non-dental applications of AI.

•
Articles that did not provide substantial information on the use of AI in dental practice.

•
Publications in languages other than English.
After the initial screening, full-text reviews of the selected articles were conducted to ensure their relevance and to extract detailed information about the methodologies, findings, and implications of AI applications in dentistry.The final selection included studies that highlighted significant advancements in AI technology, its integration into clinical practice, and its impact on improving diagnostic accuracy and patient outcomes.

AI in Endodontics
Recent studies harness sophisticated neural network frameworks to advance dental diagnostic capabilities through enhanced imaging techniques in endodontics (Table 1).Research conducted by Kirnbauer et al. and Pauwels et al. integrated Spatial Configuration-Net (SCN) and convolutional neural networks (CNNs) to achieve high precision in detecting periapical lesions and accurately locating teeth within cone beam computed tomography (CBCT) images [3,4].Similarly, Altındag et al. employed the Mask R-CNN model to detect pulp stones in dental radiographs with notable accuracy and sensitivity [5].Furthering this body of work, Johari et al. explored the application of probabilistic neural networks to identify vertical root fractures, yielding encouraging results in diagnostic efficacy [6].Comparative analyses, such as those by Hiraiwa et al. and Hu et al., have assessed AI's diagnostic competencies against human radiologists, frequently demonstrating AI's enhanced performance in tasks such as appraising root morphologies and diagnosing vertical root fractures [7,8].However, these studies have also brought to light several challenges, including issues with dataset balance, image noise, and the need for larger and more varied datasets to refine the AI models [9,10].-ANN model can be used to predict postoperative pain effectively.

AI in Oral Radiology
Recent studies have demonstrated the potential of AI and machine learning (ML) in revolutionizing dental diagnostics and treatment planning through advanced imaging technologies and algorithms (Table 2).Yılmaz et al. developed a computer-assisted detection system using CBCT images to classify periapical cysts and keratocystic odontogenic tumors, with an impressive 94% accuracy using SVM classifiers [11].Kuwada et al. evaluated deep learning models for detecting maxillary impacted supernumerary teeth in panoramic radiographs, with DetectNet showing superior diagnostic efficacy [12].Lee et al. utilized a pre-trained GoogLeNet Inception v3 for diagnosing dental caries from periapical radiographs, achieving high diagnostic performance with accuracy rates of up to 89.0% [13].Cantu et al. showed a deep learning neural network outperformed experienced dentists in detecting caries lesions on bitewing radiographs, indicating significant potential for AI in improving diagnostic standards [14].Shaheen et al. developed a deep learning-based AI framework for tooth segmentation on CBCT images, drastically reducing clinical workloads and enhancing diagnostic efficiency [15].Ariji et al. created a model to detect and classify mandibular radiolucent lesions with high sensitivity, especially for dentigerous cysts [16].Fukuda et al. explored the use of convolutional neural networks in classifying the relationship between the mandibular third molar and the canal, achieving diagnostic performance comparable to experienced radiologists [17].Tajima et al. developed an AI system for detecting cyst-like radiolucent lesions in the jaw with high accuracy, sensitivity, and specificity, underscoring the potential of AI in general dental clinics for lesion detection [18].Baydar et al. developed an AI model to evaluate bite-wing radiographs with high precision, suggesting its potential to improve diagnostic accuracy in dental practices [19].Mackie et al. explored machine learning and radiomics in diagnosing temporomandibular joint osteoarthritis using high-resolution CBCT scans, highlighting the significance of integrating machine learning with detailed imaging and biological data [20].Orhan et al. tested a CNN-based AI system for detecting periapical pathosis in CBCT images with 92.8% accuracy, emphasizing the effectiveness of CNNs in dental radiographic analysis [21].Kuwana et al. explored the effectiveness of deep learning in identifying lesions in the maxillary sinuses from panoramic radiographs, achieving a 100% detection rate for healthy sinuses [22].Minnema et al. compared a novel mixed-scale dense CNN architecture against traditional models for metal artifact reduction in CBCT scans, showing significant improvements in accuracy [23].Lee et al. used a deep CNN to diagnose odontogenic cystic lesions from dental images, significantly outperforming models using panoramic images [24].Basaran et al. developed an AI model to diagnose dental conditions using panoramic radiography, showing promise in detecting various dental conditions, albeit with limitations in caries and dental calculus detection [25].Mima et al. introduced a method utilizing Faster R-CNNs for detecting and classifying tooth regions in dental panoramic X-ray images with high precision and accuracy [26].Zhu et al. introduced an AI framework for diagnosing common dental diseases from panoramic radiographs, showing high specificity for all diseases except for caries, where it showed lower sensitivity and specificity, but overall, it demonstrated superior diagnostic performance compared to dentists in certain areas [27].

AI in Oral Surgery
Recent advancements in oral research have highlighted the significant impact of AI and deep learning technologies in improving diagnostic accuracy, treatment planning, and clinical outcomes in oral surgery (Table 3). Lee et al. evaluated an automated deep convolutional neural network (DCNN) for classifying dental implant systems from radiographic images, demonstrating high accuracy and surpassing most dental professionals [28].Matsuda et al. analyzed the anatomical aspects of horizontally impacted mandibular third molars in young Japanese patients, identifying predictors for lingual cortical bone perforation [29].The study provides valuable insights for treatments involving impacted mandibular third molars, underscoring the importance of considering specific factors such as gender, age, and available space.A recent study also investigated the use of ResNet models for diagnosing the need for orthognathic surgery based on cephalometric radiograph images.Their findings suggested that an AI model structure significantly impacts medical image predictions.This research is crucial for enhancing orthognathic surgery planning and highlights the effectiveness of AI in cephalometric analysis.Zhang et al. employed artificial neural networks to predict facial swelling after impacted mandibular third molar extraction with high accuracy.Their study demonstrates the potential of AI in predicting post-surgical outcomes, facilitating better patient care and clinical decision making [30,31].Tanikawa et al. explored AI's capability to predict 3-D facial morphology changes following orthognathic surgery and orthodontic treatment.Their systems demonstrated high accuracy in anticipating post-treatment facial topography, indicating the potential of AI in planning various facial treatments, including aging, cancer surgery, or cosmetic interventions [32].Choi et al. developed an AI model using a deep convolutional neural network to determine the spatial relationship between the mandibular third molar and the inferior alveolar nerve from panoramic radiographs.This model showed superior diagnostic accuracy compared to experienced oral and maxillofacial surgeons, suggesting AI could significantly aid surgical planning and reduce the need for CBCT scans [33].

AI in Orthodontics
Artificial intelligence can be utilized for different purposes in orthodontics, including diagnostic treatment analysis, the identification of anatomical landmarks, orthodontic treatment with or without extractions, skeletal classification, determination of growth and development phases, and orthognathic surgical planning (Table 4).Niño-Sandoval et al. explored mandibular morphology using artificial neural networks (ANNs) on lateral radiographs, demonstrating improved prediction accuracy for mandibular dimensions.According to their findings, for facial reconstruction and victim identification, ANNs can be utilized in orthodontic treatments and craniofacial studies [35].Recent studies have focused on cephalometric landmark identification using AI, with convolutional neural networks (CNNs) and fully automated AI-assisted analysis.According to Panesar et al., the precision and accuracy of the examiners with the aid of AI improved by 10.47% and 27.27%, respectively [36,37].Kochhar et al. assessed bone volume in CBCT scans of patients with a unilateral cleft lip and/or palate using OsiriX software.They found that OsiriX software provided good reliability in measurements of bone volume for evaluating alveolar cleft defects [38].Çoban et al. evaluated the reliability of digital manual versus AI-based automatic cephalometric analyses, finding significant discrepancies in measurements across different sagittal skeletal malocclusions.The study highlights AI's potential for preliminary orthodontic assessment and the need for further validation across malocclusion groups [39].Jiang introduced "CephNet", a highly accurate AI system for automating cephalometric analysis, achieving a classification accuracy of 89.33% [40].Li et al. developed artificial neural networks to predict orthodontic treatment plans including the determination of extraction/non-extraction, extraction patterns, and anchorage patterns.Their research suggests ANNs as a valuable tool for assisting less experienced orthodontists in treatment planning [41].Silva et al. assessed CEFBOT, an AI-based cephalometric software, comparing its performance to a trained human examiner.Despite some limitations, CEFBOT demonstrated high reliability in completing cephalometric measurements, indicating its potential as a tool to enhance radiologists' skill set [42].

AI in Pediatric Dentistry
Recent studies across various domains of pediatric dentistry have utilized advanced machine learning and AI techniques to improve diagnostic accuracy, predict dental conditions, and explore new biomarkers for early childhood caries (ECC) (Table 5).Ramos-Gómez et al. employed a random forest algorithm to predict active dental caries in children based on a parental oral health questionnaire.Key predictors included parent age, unmet dental needs, and the child's oral health status, demonstrating the machine learning approach's efficacy in caries risk prediction [43].Zhao et al. developed a deep learning model, HeadNet, for a non-invasive adenoid hypertrophy assessment using lateral cephalograms.The model's system achieved high sensitivity (0.906), specificity (0.938), and accuracy (0.919) for adenoid hypertrophy assessment and offers an efficient alternative to traditional invasive methods, potentially leading to earlier diagnoses in pediatric patients [44].Ahn et al. utilized deep convolutional neural networks to detect mesiodens in panoramic radiographs of children with mixed dentition.Their findings highlighted the potential of AI models for a more accurate and faster diagnosis, particularly ResNet-101 and Inception-ResNet-V2, with accuracy, precision, recall and F1 scores higher than 90% [45].Çalışkan et al. explored the effectiveness of a deep learning-based convolutional neural network in detecting and classifying submerged molars in panoramic radiographs.The AI system demonstrated superior accuracy compared to dental experts, indicating its potential to enhance diagnostic reliability in pediatric dentistry [46].Bilgir et al. utilized a R-CNN Inception v2 model to develop an AI system, (CranioCatch, Eskisehir, Turkey) for detecting and numbering teeth on panoramic radiographs.The system showed high sensitivity and precision (0.955 and 0.965, respectively), underlining AI's underutilized potential in dentistry for automated dental charting and diagnosis [47].You et al. presented a deep learning-based AI model for detecting dental plaque on primary teeth.The AI model presented clinically acceptable performance in detecting dental plaque on primary teeth compared to specialists [48].Koopaie et al. investigated salivary cystatin S levels as a biomarker for ECC, employing machine learning methods to analyze saliva samples.The findings indicated that incorporating measurements of cystatin S in saliva improved the performance of machine learning techniques in distinguishing between children with early tooth decay and those without any cavities [49].

AI in Periodontology
Numerous studies have been conducted in periodontology regarding the applications of AI and deep CNNs.The detection of alveolar bone loss and early changes in bone density can be identified using AI models (Table 6).Furthermore, it is considered that deep learning methods could be utilized in situations where early intervention may be necessary regarding implants and surrounding tissues.Chau et al. developed an AI system to detect gingivitis from intraoral photographs, achieving high accuracy and demonstrating the potential of AI in identifying gingival inflammation [51].Lin et al. introduced an automatic system for measuring alveolar bone loss in periodontitis patients using periapical radiographs.They concluded that the proposed automatic system can effectively estimate the grade of horizontal alveolar bone loss in periodontitis radiograph images [52].Chang et al. explored combining deep learning with computer-aided design (CAD) processing to diagnose and stage periodontitis from dental panoramic radiographs.The approach achieved high accuracy in detecting periodontal bone levels and classifying periodontal bone loss, showcasing the effectiveness of deep learning hybrid frameworks in automating the classification process of periodontitis [53].Thanathornwong et al. employed a deep learning-based faster regional convolutional neural network (faster R-CNN) to detect periodontally compromised teeth in digital panoramic radiographs.The model achieved a sensitivity of 0.84, a specificity of 0.88, and an F-measure of 0.81 [54].Lee et al. developed a computer-assisted detection system using deep CNNs for diagnosing and predicting periodontally compromised teeth (PCT) with promising accuracy.With the proposed deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars and the accuracy of predicting extraction was 82.8% for premolars and 73.4% for molars [55].

AI in Prosthodontics
The adoption of AI technology in all prosthetic procedures is still met with some hesitation.AI systems are particularly useful for classifying outcomes and processing and analyzing repetitive workflows.AI algorithms can also support decision making for less experienced practitioners and facilitate case analysis (Table 7).Despite prevailing misconceptions and some limitations related to AI, it continues to evolve due to its advantages in providing accurate diagnoses.The applications of AI in prosthetic treatment include prosthetic planning and design, CAD/CAM applications, digital smile design, color selection, temporomandibular joint disorders, and occlusion.Lee et al. demonstrated the use of deep CNN algorithms, specifically GoogLeNet Inception v3, in identifying and classifying dental implant systems from radiographs with high accuracy [57].Bayrakdar et al. evaluated an AI system's ability to analyze bone height and thickness for dental implant planning using CBCT images.The system indicated that the accuracy of correct detection was 72.2% for canals, 66.4% for sinuses/fossae, and 95.3% for regions with missing teeth, demonstrating the potential of deep learning to enhance diagnostic precision and treatment planning in dentistry, especially in the field of implantology [58].Lerner et al. explored the creation of implant-supported monolithic zirconia crowns through a fully digital procedure facilitated by AI.The study reported a high success rate in prosthetic rehabilitation, highlighting AI's narrow application in dental CAD processes but suggesting the need for broader research and validation [59].Takahashi et al. utilized the Yolov3 object detection algorithm to identify dental implant systems in panoramic radiographs.Despite achieving good accuracy, especially for specific implants, the study noted the requirement for more diverse implant system images to enhance clinical application [60].Yamaguchi et al. employed a CNN to predict the debonding of CAD/CAM composite resin crowns from 2D images of 3D models, achieving high accuracy, precision, recall, and F-measure values (98.5%, 97.0%, 100%, and 0.985, respectively) [61].

AI in Restorative Dentistry
Recently, increasing aesthetic expectations have significantly elevated the importance of diagnosis and treatment processes within the field of restorative dentistry.With the advancement of technology, the evaluation of artificial intelligence applications has commenced.In restorative dentistry, artificial intelligence applications can be enumerated as caries detection, dental plaque identification, the differentiation of developmental lesions, robotic cavity preparation, color matching, the assessment of restoration success, and material discrimination (Table 8).
Aslan et al. developed an AI algorithm for detecting and classifying dental restorations from panoramic radiographs with high accuracy, illustrating AI's potential to improve radiographic reports and dentist-patient communication.The algorithm was able to identify various restorations with an overall precision of 93.6% [62].Schwendicke et al. utilized CNNs to detect caries lesions in near-infrared light transillumination (NILT) images, aiming to refine caries detection and potentially expand dental examinations to non-traditional settings.Despite moderate accuracy, the combination of NILT and CNNs promises improvements in caries diagnosis comparable to traditional radiographic methods [63].Fontenele et al. investigated an AI-driven tool for automatic tooth segmentation in cone beam computed tomography images, highlighting how dental fillings affect performance.The study demonstrated the tool's high accuracy and speed, emphasizing its clinical acceptability and potential to enhance digital dental workflows [64].Zheng et al. compared three CNNs in analyzing the radiographic penetration depth of carious lesions, with ResNet18 showing superior accuracy.Integrating clinical parameters with ResNet18 further improved its diagnostic performance, suggesting the effectiveness of a multi-modal CNN approach in automating the diagnosis of deep caries and pulpitis [65].Güneç et al. compared the efficacy of an AI application against junior dentists in diagnosing dental caries and periapical infections.The AI system, which was trained using comprehensive datasets of panoramic dental X-rays, surpassed the performance of junior dentists by delivering results that were both more precise and quicker [66].

Discussion
The integration of artificial intelligence in various dental disciplines, as presented in this review, underscores its transformative potential to enhance diagnostic accuracy, treatment planning, and overall patient care.The AI methodologies and applications discussed across endodontics, oral radiology, orthodontics, pediatric dentistry, periodontology, prosthodontics, and restorative dentistry collectively demonstrate significant advancements.
In endodontics, AI has shown remarkable potential in enhancing diagnostic capabilities, particularly in identifying vertical root fractures and root morphology.Studies by Hu et al. and Fukuda et al. demonstrate the efficacy of deep learning models like ResNet50 and CNNs in diagnosing VRFs from CBCT and panoramic radiography images, often surpassing human radiologists in accuracy and sensitivity [7,9].The integration of AI in endodontics can lead to more precise and timely diagnoses, reducing the likelihood of missed fractures and improving treatment outcomes.However, the need for large annotated datasets and the potential for model overfitting remain challenges that must be addressed.Oral radiology has significantly benefited from AI applications, particularly in the detection and classification of dental diseases from radiographic images.The studies by Zhu et al. and Mima et al. illustrate the use of AI frameworks based on BDU-Net and faster R-CNNs for diagnosing dental diseases and detecting individual teeth with high specificity and efficiency [26,27].These advancements can streamline the diagnostic process, reduce diagnostic errors, and enable more personalized treatment plans.The main implication is the potential for AI to serve as an adjunctive tool, enhancing the capabilities of radiologists and improving patient outcomes.AI applications in orthodontics primarily focus on cephalometric analysis and treatment planning.The work by Panesar et al. and Alessandri-Bonetti et al. shows that AI-assisted cephalometric analysis can significantly improve precision and accuracy [36,37].AI can automate the labor-intensive process of landmark identification, making it faster and more reliable.This can free up valuable time for orthodontists, allowing them to focus more on patient care.In pediatric dentistry, AI has been employed to detect dental plaque, identify taurodontism, and classify mesiodens with high accuracy.Studies by You et  This can lead to more accurate diagnoses and effective treatment plans, ultimately improving patient outcomes [62,65].The challenge remains in ensuring the AI models are robust and can generalize well across diverse patient populations and varying clinical scenarios.
Despite the promising advancements of AI in dental practice, several limitations need to be addressed.Different methodological approaches in machine learning, such as supervised learning, unsupervised learning, and reinforcement learning, each have inherent strengths and weaknesses that impact their application in dentistry.For instance, supervised learning requires large, labeled datasets, which are often difficult to obtain in medical fields due to privacy concerns and the need for expert annotation.Unsupervised learning, while useful for discovering hidden patterns in data, may not always provide clinically actionable insights without additional validation.Moreover, the choice of AI models, such as convolutional neural networks for image analysis or recurrent neural networks for time-series data, significantly influences the outcomes.Each model type requires specific tuning and validation to ensure accuracy and reliability in different dental applications.Additionally, there is a lack of standardization in the methodologies used across studies, making it difficult to compare results and draw definitive conclusions about the best practices for AI in dentistry [67,68].
Regulatory approval is another critical factor that affects the deployment of AI in dental practice.AI systems must undergo rigorous testing and validation to meet the standards set by regulatory bodies such as the U.S. Food and Drug Administration (FDA), the European Medicines Agency (EMA), and other national health authorities.These approvals ensure that AI tools are safe, effective, and reliable for clinical use [69,70].However, the regulatory pathways for AI are still evolving, and navigating these requirements can be complex and time consuming.This regulatory landscape creates a barrier to the rapid adoption of AI technologies in clinical settings [71].
Several difficulties hinder the widespread application of AI in dental practice.These include the following: data privacy and security, interoperability, cost and accessibility, training, and expertise.Ensuring the confidentiality and security of patient data used to train AI models is paramount.The use of large datasets in AI development raises concerns about data breaches and the misuse of sensitive information.Integrating AI systems with existing dental practice management software and electronic health records requires seamless interoperability, which is often challenging due to varied data formats and standards.The high costs associated with developing and implementing AI technologies can be prohibitive for many dental practices, particularly smaller ones or those in resourcelimited settings.Dental professionals need adequate training to effectively use AI tools.There is also a need for interdisciplinary collaboration between dentists, data scientists, and engineers to develop and refine AI applications [72][73][74].
The development and use of AI in dentistry must adhere to established standards and guidelines to ensure consistency, accuracy, and safety.Organizations such as the American Dental Association (ADA) and the International Organization for Standardization (ISO) are working towards creating guidelines for the ethical and effective use of AI in dental practice.These standards encompass aspects such as data quality, model validation, and clinical integration, providing a framework for the responsible development and deployment of AI technologies.The ethical and legal challenges associated with AI in dentistry are significant and multifaceted.Determining who is responsible for errors or adverse outcomes associated with AI-generated decisions is a major concern.Legal frameworks need to address liability and accountability in the use of AI tools.Ensuring transparency in AI algorithms is crucial for building trust among dental professionals and patients.Black-box AI models, whose decision-making processes are not easily interpretable, pose challenges for clinical acceptance and regulatory approval.AI systems must be designed and tested to avoid biases that could lead to disparities in dental care.This includes ensuring diverse and representative datasets during the training phase to prevent skewed outcomes that favor certain populations over others [72,73].
This narrative review comprehensively covers AI applications across multiple dental disciplines, offering detailed methodological analysis and identifying future research directions.It emphasizes ethical considerations and interdisciplinary collaboration.However, the review relies on the existing literature, which may have biases and limitations, and the rapidly evolving nature of AI means some findings may become outdated.Further research should focus on conducting systematic reviews and meta-analyses to consolidate findings, as well as exploring practical implementation strategies and addressing gaps in data diversity and standardization.

Conclusions
The use of AI is both a significant change in itself and has the aim to improve patients' care by using a new technology that will improve diagnostic precision as well as change the workflow and the approach of treatment planning.This overview, however, has made us take a glance at the types of dentistry specialties that have been aided by AI such as endodontics, oral radiology, orthodontics, pediatric dentistry, periodontology, prosthodontics, and restorative dentistry.Recent studies clearly demonstrate that AI in dentistry is poised to significantly enhance the future by offering comprehensive conveniences.Despite the numerous benefits mentioned above, the absence of extensive studies on legal issues, such as who will be held accountable for errors associated with AI or who will verify the diagnoses, indicates that AI algorithms will remain as tools to assist clinicians rather than replace them.AI research already occupies a significant position in the literature.These algorithms aim to reduce errors in diagnosis and treatment planning for clinicians burdened with heavy workloads and to minimize human-induced mistakes.The systems are expected to provide significant benefits in terms of patient health, cost, and time, especially in healthcare centers facing clinician shortages.AI's capacity for analyzing raw data also provides the grounds for a new area of research and advances in treatment with potential for technology and scientific outbursts.Another characteristic of intelligence that calls for professionals having improvement learning is that intelligence is changing all the time; therefore, professionals need to aspire to be always motivated, informed, and in line with technology.In conclusion, AI is expected to change dentistry in a meaningful way, from current abilities, future precision, and most importantly, patients care, given that the place of AI in medicine is still the subject of discussion and patients should be included in the deliberation.

Table 1 .
Advanced AI applications in endodontics.

Table 2 .
Advanced AI applications in oral radiology.

Table 3 .
Advanced AI applications in oral surgery.

Table 4 .
Advanced AI applications in orthodontics.

Table 5 .
Advanced AI applications in pediatric dentistry.

Table 6 .
Advanced AI applications in periodontology.

Table 7 .
Advanced AI applications in prosthodontics.

Table 8 .
Advanced AI applications in restorative dentistry.
[57,61] Duman et al. highlight the effectiveness of AI models in these applications, demonstrating performance comparable to expert clinicians[48,50].The use of AI can improve early detection and intervention, which is particularly important in pediatric patients to prevent long-term dental issues.The implication here is the potential for AI to enhance preventive care and early diagnosis, ultimately improving oral health outcomes in children.Periodontology has seen the development of AI systems for detecting gingivitis, measuring alveolar bone loss, and diagnosing periodontitis.Research by Chau et al. and Lin et al. showcases AI's ability to accurately diagnose periodontal conditions from intraoral photographs and radiographs[51,52].These tools can aid in the early detection and monitoring of periodontal diseases, leading to more effective and timely interventions.In prosthodontics, AI applications include the identification and classification of dental implant systems, as well as the prediction of crown debonding probability.Studies by Lee et al. and Yamaguchi et al. demonstrate the high accuracy of AI models in these tasks, which can improve implant planning and maintenance[57,61].AI's ability to predict potential issues such as debonding can help in preventive maintenance and extend the lifespan of prosthetic devices.The implication is a potential reduction in prosthetic failures and enhanced patient satisfaction, though the initial setup and training of these AI systems may require significant investment.Restorative dentistry benefits from AI through enhanced caries detection, tooth segmentation, and restoration classification.Research by Zheng et al. and Abdalla-Aslan et al. highlights AI's capability to detect caries and classify dental restorations with high precision, outperforming traditional methods.