ABSTRACT
Artificial intelligence (AI) holds the promise of mimicking human intelligence to enhance prediction and complex decision-making in healthcare, carving out a significant role in dentistry tasks, notably endodontics. It has shown remarkable accuracy in detecting and predicting diseases within this field, potentially refining diagnostics and treatments to boost endodontic success rates. However, there’s a need to validate the reliability, practicality, and cost-effectiveness of AI before fully integrating it into everyday clinical settings. This review aims to explore AI’s current applications in endodontics and possible future developments.
KEYWORDS: AI, endodontics, future of AI in endodontics
INTRODUCTION
John McCarthy introduced the term “Artificial Intelligence” in 1955, later hosting a significant conference at Dartmouth in 1956.[1] Artificial intelligence (AI) has since revolutionized many fields, including healthcare. In dentistry, and specifically in endodontics, AI enhances diagnostic accuracy and treatment outcomes. AI applications automate diagnosis, predict treatment outcomes, and support clinical decisions by analyzing large datasets to identify patterns unnoticed by humans. This facilitates earlier disease detection, tailored treatment plan, and improved patient care. However, challenges remain in integrating AI into clinical settings, such as ensuring reliability, efficiency, and cost-effectiveness.[1,2,3]
This review explores AI’s current role in endodontics, its impact on practice, and the future of AI-driven dental care, helping practitioners, and researchers adapt to ongoing changes in dental healthcare.
WORKING PRINCIPLE OF AI IN ENDODONTICS
In endodontics, AI operates by analyzing large datasets of dental images and patient records to enhance diagnosis and treatment planning. Machine learning algorithms process X-rays and cone beam computed tomography (CBCT) scans, identifying patterns and anomalies indicative of dental pulp diseases or root canal issues. Neural networks can assist in detecting fractures, lesions, and other intricacies that might be unnoticed by the human eye. AI systems also predict treatment outcomes and recommend tailored interventions. By continuously learning from new data, AI improves accuracy in identifying problems and aids endodontists in making informed decisions, leading to more precise and effective patient care.[1,2,3]
VARIOUS APPLICATION OF AI IN ENDODONTICS
AI in endodontics offers numerous applications, enhancing both diagnostic accuracy and treatment efficiency.
COMPREHENSIVE AI-BASED PATIENT MANAGEMENT
AI predicts potential complications or treatment outcomes using patient history and data analysis. It streamlines the documentation process to maintain accurate and up-to-date patient records, while AI chatbots enhance patient communication by providing information and follow-up care instructions to improve patient engagement and education.
This integrated approach ensures personalized care, enabling healthcare providers to focus more on clinical tasks while reducing administrative burdens. Ultimately, such advancements lead to improved patient satisfaction and more efficient healthcare delivery.[3]
DIAGNOSIS
AI-powered tools analyze dental X-rays and 3D scans with advanced algorithms, enabling a more accurate identification of pulp infections, tooth fractures, and periapical lesions. These systems learn from vast datasets, reducing the incidence of misdiagnosis and ensuring that clinicians can detect issues that might be overlooked by traditional methods. In a comprehensive approach, Lee et al.[4] adopted a thorough method by training, validating, and testing a deep learning model with 4,129 periapical radiographs. Their results highlighted deep learning’s potential to boost both the accuracy and reliability of assessing dental caries and periapical periodontitis in these images. This progress in AI applications demonstrates the profound impact that technology can have on enhancing diagnostic abilities and elevating overall results in dental care.
ASSESSMENT OF ROOT CANAL MORPHOLOGY
For effective non-surgical root canal therapy, dentists must understand root canal anatomy and morphology. AI aids in detecting irregularities and locating new canals correctly. In their research, Albitar L and colleagues analyzed 57 deidentified CBCT studies that concentrated on maxillary molars with clinically verified unobturated MB2 canals. The objective was to investigate the capability of AI in identifying and pinpointing these unobturated second mesial buccal (MB2) canals. Their results indicated that AI shows potential in recognizing both obturated and unobturated canals in teeth that have undergone endodontic treatment. However, it is important to bear in mind that the current AI algorithm is somewhat vulnerable to issues like metallic artifacts, variations in canal calcifications, and certain configurations.[5]
DETERMINATION OF WORKING LENGTH
Determining the right working length (WL) is crucial for the success of root canal treatments. Inaccurate WL determination can lead to issues such as instrumenting beyond the apical foramen, flare-ups, periapical foreign body reactions, and inadequate microbiological control. Methods for locating the apical foramen and estimating WL include radiography, tactile feedback, and patient responses to a file or paper point. While digital technology offers advantages in locating the apical foramen, it can also lead to errors. Therefore, studies have explored the use of Artificial Neural Networks (ANN) for estimating the correct WL. Saghiri et al.[6] research showed that ANN can be a useful adjunct in pinpointing the apical foramen on radiographs, which improves the accuracy of WL determination through radiographic methods.
DIAGNOSIS OF VERTICAL ROOT FRACTURES
Vertical root fractures (VRFs) are quite rare in teeth that have undergone endodontic treatment, occurring in only 3.7% to 30.8% of such cases, according to research. Identifying VRFs on radiographs poses a significant challenge and might require more sophisticated technological aids. Notably, Johari et al.[7] conducted a study that developed an AI-based model employing a PNN framework for detecting VRFs in both untreated and endodontically treated teeth using periapical radiographs and CBCT images. The study found that the model was exceptionally effective at diagnosing VRFs on CBCT images, achieving an impressive accuracy of 96.6%, compared to periapical radiographs.
ADVANTAGES OF AI
AI technology offers significant advancements in endodontics, primarily through enhanced diagnostic accuracy and improved treatment efficiency. By leveraging AI’s ability to analyze radiographs and CBCT images with precision, endodontists can minimize human error, ultimately reducing the frequency of misdiagnoses. This consistent accuracy leads to faster diagnoses, which not only speeds up the treatment planning process but also significantly reduces patient wait times. Furthermore, AI’s capacity to analyze extensive datasets facilitates the development of optimal treatment plans based on historical outcomes, thereby improving success rates. In the context of education, AI serves as a formidable tool for dental students and professionals, helping them interpret a broad range of pathological cases, thus enriching their learning and diagnostic processes.[1,2,3]
LIMITATIONS OF AI
The deployment of AI in dentistry faces several challenges. Key issues include reliance on comprehensive, high-quality datasets; insufficient or biased data leading to inaccuracies; and substantial initial investments, which can be prohibitive for smaller practices. AI’s technological limitations, requiring regular updates and monitoring, can impede its capabilities. Its proficiency in pattern recognition may fall short in complex cases needing human judgment. Ethical concerns regarding data privacy and patient consent also arise due to medical data processing. Although there is debate over AI replacing dental professionals, it is more likely AI will augment, not replace, human expertise in dentistry.[1,2,3]
IMPACT OF AI ON ENDODONTIST
AI significantly impacts endodontists by enhancing diagnostic precision, optimizing treatment planning, and improving patient outcomes. It automates routine tasks, allowing endodontists to focus on complex cases, reduces human error, and provides decision support through data analysis. Consequently, AI elevates efficiency, effectiveness, and the overall quality of endodontic care.
FUTURE PROSPECTIVE OF AI
AI is set to revolutionize endodontics by enhancing precision and personalization in dental care. It enables more accurate diagnostics, catching anomalies undetectable to the human eye, thus improving patient outcomes. AI personalizes treatment by analyzing individual data like medical history and lifestyle, recommending tailored treatment options, enhancing effectiveness and patient satisfaction. As an educational tool, AI offers simulations for skill refinement and integrates with AR and 3D printing for minimally invasive procedures. It automates routine tasks, streamlining workflows. Addressing ethical concerns like data privacy is crucial to maintain patient trust and adhere to standards.
CONCLUSION
AI in endodontics enhances precision and personalization, improves diagnostics, and streamlines workflows, offering transformative benefits while addressing ethical concerns to ensure trust and adherence to standards.
Conflicts of interest
There are no conflicts of interest.
Funding Statement
Nil.
REFERENCES
- 1.Ahmed ZH, Almuharib AM, Abdulkarim AA, Alhassoon AH, Alanazi AF, Alhaqbani MA, et al. Artificial intelligence and its application in endodontics: A review. J Contemp Dent Pract. 2023;24:912–7. doi: 10.5005/jp-journals-10024-3593. [DOI] [PubMed] [Google Scholar]
- 2.Sudeep P, Gehlot PM, Murali B, Mariswamy AB. Artificial intelligence in endodontics: A narrative review. J Int Oral Health. 2023;15:134–41. [Google Scholar]
- 3.Shan T, Tay FR, Gu L. Application of artificial intelligence in dentistry. J Dent Res. 2021;100:232–44. doi: 10.1177/0022034520969115. [DOI] [PubMed] [Google Scholar]
- 4.Lee SJ, Chung D, Asano A, Sasaki D, Maeno M, Ishida Y, et al. Diagnosis of tooth prognosis using artificial intelligence. Diagnostics. 2022;12:1422. doi: 10.3390/diagnostics12061422. doi: 10.3390/diagnostics12061422. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5.Albitar L, Zhao T, Huang C, Mahdian M. Artificial intelligence (AI) for detection and localization of unobturated second mesial buccal (MB2) canals in cone-beam computed tomography (CBCT) Diagnostics (Basel) 2022;12:3214. doi: 10.3390/diagnostics12123214. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 6.Saghiri MA, Asgar K, Boukani KK, Lotfi M, Aghili H, Delvarani A, et al. A new approach for locating the minor apical foramen using an artificial neural network. Int Endod J. 2012;45:257–65. doi: 10.1111/j.1365-2591.2011.01970.x. [DOI] [PubMed] [Google Scholar]
- 7.Johari M, Esmaeili F, Andalib A, Garjani S, Saberkari H. Detection of vertical root fractures in intact and endodontically treated premolar teeth by designing a probabilistic neural network: An ex vivo study. Dentomaxillofac Radiol. 2017;46:20160107. doi: 10.1259/dmfr.20160107. [DOI] [PMC free article] [PubMed] [Google Scholar]