Artificial Intelligence in Dentistry

Artificial Intelligence (AI) technologies have recently gained significant momentum in dentistry. For instance, AI may assist dental professionals with clinical documentation, guide with image analysis for diagnosis, and serve as an adjuvant for clinical decision-making, including treatment planning and execution.

The American Dental Association Standards Committee on Dental Informatics recently published a white paper on the potential applications of AI and augmented intelligence (AuI) in clinical practice.^1,2 AuI refers to using AI as a tool to assist clinicians in performing tasks as an adjuvant to human intelligence. This article discusses emerging trends to empower dentists to understand the potential of these powerful tools and their impact on clinical practice.

Clinical Documentation

AI-powered speech recognition software is a prime example of how AI can be integrated into electronic health records (EHRs). Today, technologies, such as conversational AI workflow assistant and documentation companion, provide secure, convenient, and comprehensive clinical documentation support from pre- to post-patient encounters.

This technology has proven helpful across various healthcare settings and will help dentists to generate accurate and detailed clinical documentation. Many details of periodontal examinations may need to be included when communicating between clinicians and their assistants documenting the periodontal chart.

In a multi-institutional study evaluating the quality of periodontal disease documentation in EHRs, one organization received a low score for having all necessary information in only one in five periodontal health evaluations.³ AI-powered charting software could alert the clinician and improve documentation.

Although anecdotes highlight AI’s utility, descriptive statistical analysis of its use in dentistry is forthcoming. A recent report in the Journal of American Medical Association reported up to a 7% error rate in clinical documentation due to several factors, highlighting the importance of provider review.⁴ This technology can improve the accuracy and efficiency of clinical documentation, save time, mitigate infection control and litigious risks, and enhance the patient experience by providing more accurate and timely information.⁵

Health Data Management

AI technology in dentistry provides information that aids clinical decision-making by interpreting big data quickly, within a single practice, or at much larger scales to make actionable analyses.⁶ This can help improve interprofessional coordination and collaboration, exchange patient data between dental and medical practices, and inform the nascent field of precision oral health.^7,8

Practice Management

Managing a busy dental practice is challenging. AI technologies can streamline practice management by simplifying and automating administrative tasks, including patient reminders, scheduling, billing, etc. Various tools are under development that read clinical notes to extract Current Dental Terminology (CDT) codes, automatically interface with insurance providers, and improve the workflow of reimbursement processes. This can save dental professionals time and enhance the patient experience by making the billing process more transparent and efficient.⁹

Diagnostic Image Analysis

Currently, the primary use of AI in dental practice is image analysis of two-dimensional radiographs (bitewing, periapical, panoramic), three-dimensional imaging (cone-beam computed tomography [CBCT], magnetic resonance imaging [MRI]), and intraoral scans to assist clinicians with the detection and diagnosis of oral diseases. Using AI tools in image analysis may increase diagnostic confidence and enable customized treatment plans, improving patient trust and enhancing clinical workflows. Following is a list of imaging application types.

Caries Diagnosis. A recent study demonstrated that dentists’ overall agreement on the presence and absence of dental caries is low.¹² AI tools assist clinicians by identifying radiographic evidence of possible neglect and alerting dentists to a more careful site-specific clinical evaluation.

Periodontal Diagnosis. Diagnosing periodontal diseases involves a combination of clinical and radiographic examination and assessing the patient’s risk factors and systemic health. AI tools can assist with quantifying bone level measurements and detect calculus, a secondary etiologic risk factor to periodontal disease development and progression.

Endodontic Diagnosis. Diagnosing endodontic pathologies involves both clinical and radiographic examination. Currently, AI tools can assist with the identification of periapical (PA) pathologies. Three-dimensional imaging, notably CBCT scans, provides a high-quality view with sufficient spatial resolutions for the PA region and is being increasingly adopted as an adjunct to endodontic diagnosis.¹⁰ Future AI tools may assist with analyzing CBCT scans for endodontic diagnosis, treatment guidance, and post-treatment follow-up.

Recently, the United States Food and Drug Administration granted 510K clearance to several AI technologies for the detection of caries and calculus, quantification of bone level measurement, and identification of periapical radiolucencies on bitewing and PA radiographs.¹¹ This represents a significant advancement in bringing these tools into the clinical arena to benefit patient care.

Surgical Planning

AI technologies apply to surgical planning via CBCT scan segmentation and analysis automation.¹² For instance, AI-assisted identification of anatomical landmarks (eg, maxillary sinus, inferior alveolar nerve, incisive canal, mental foramen, airways, teeth) and pathologies (eg, PA lesions, bone pathologies) contribute to improving the accuracy and efficiency in surgical planning, provide visual support for communication between clinicians and patients, and serve as educational tools in training settings.^13,14 Recently, an AI model with augmented reality was developed to assist with implant surgery planning.¹⁵ The technology segments CBCT to allow the clinician to plan the implant surgery (eg, verification of implant position, depth, position, and inclination) using hand gestures and a mixed reality headset. This allows for a more user-friendly user interface and shows promise as an educational tool.

Ethical and Regulatory Considerations

When integrating AI technologies into practice, ethical and regulatory factors must be considered. First, retaining the dentist’s independent clinical judgment is essential. Evidence-based dentistry is the gold standard for treatment planning, whereas AI models are developed from human expertise.¹⁶ While AI is a valuable diagnostic aid to enhance efficiency and reduce diagnostic errors potentially, the clinician’s diagnostic skills are critical.

Second, regulatory guidelines are necessary to ensure patient safety. Rigorous testing is required to validate the accuracy and reliability of AI technologies in assisting clinician decision-making.

Last, cybersecurity measures are crucial to protect patient confidentiality, privacy, and rights.

While AI technologies offer many tangible benefits, they also come with risks. One of the main concerns is data privacy and security. The sensitive nature of healthcare information requires strict adherence to regulations such as the Health Insurance Portability and Accountability Act of 1996.¹⁷ Dental professionals and technology companies must develop standardized data collection and sharing protocols to protect patient data. Similar concerns were expressed during the transition from paper to digital charts.¹⁸

The patient’s perspective on this emerging technology is important. For instance, a recent study reported significant patient-reported expected advantages of AI application in dentistry such as diagnostic confidence, time reduction, and more personalized and evidence-based disease management.¹⁹ Most patients expected AI to be part of the dental workflow in 1 to 5 years (42.3%) or 5 to 10 years (46.8%).

Conclusion

Recent advances in AI technologies and applications in dentistry — including clinical documentation, practice management, diagnostics and treatment planning — are paving the way for a rapid transformation of the field. While AI technologies may empower dentists with tools to further improve patient care while enhancing practice efficiency, there are challenges to AI integration. Key considerations are the maintenance of dentists’ independent judgement, adherence to regulatory guidelines to ensure patient safety, and protection of patient privacy and data security. With innovations in policies and standards, AI integration in dentistry will gain public trust and acceptance.

References

1. American Dental Association. ADA Releases Report on AI in Dentistry. Available at: adanews.ada.o/​g/​ada-news/떗/​february/​ada-releases-report-on-ai-in-dentistry. Accessed December 13, 2023.
2. American Dental Association. Artificial Intelligence and Dentistry. Available at: adanews.ada.org/​ada-news/떗/​june/​artificial-intelligence-and-dentistry. Accessed December 13, 2023.
3. Mullins J, Yansane A, Kumar SV, et al. Assessing the completeness of periodontal disease documentation in the EHR: a first step in measuring the quality of care. BMC Oral Health. 2021;21:282.
4. Zhou L, Blackley SV, Kowalski L, et al. Analysis of errors in dictated clinical documents assisted by speech recognition software and professional transcriptionists. JAMA Netw Open. 2018;1:e180530.
5. Yu YC, Yang CW, Chang YC. The perceptions of automated artificial intelligence-powered clinical documentation assisted in dentistryJ J Dent Sci. 2023;18:1421-1422.
6. Joda T, Waltimo T, Probst-Hensch N, Pauli-Magnus C, Zitzmann NU. Health data in dentistry: an attempt to master the digital challenge. Public Health Genomics. 2019;22:1-7.
7. Alanazi A, Alghamdi G, Aldosari B. Informational needs for dental-oriented electronic health records from dentists’ perspectives. Healthcare (Basel). 2023;11:266.
8. Finkelstein J, Zhang F, Levitin SA, Cappelli D. Using big data to promote precision oral health in the context of a learning healthcare system. J Public Health Dent. 2020;80(Suppl 1):S43-S58.
9. Zaidat B, Tang J, Arvind V, et al. Can a novel natural language processing model and artificial intelligence automatically generate billing codes from spine surgical operative notes? Global Spine J. 2023; 18:21925682231164935.
10. Scarfe WC, Levin MD, Gane D, Farman AG. Use of cone beam computed tomography in endodontics. Int J Dent. 2009;2009:634567
11. United States Food and Drug Administration. 510(k) Premarket Notification. Available at: accessdata.fda.gov/​scripts/​cdrh/​cfdocs/​cfpmn/​pmn.cfm. Accessed December 13, 2023.
12. Ezhov M, Gusarev M, Golitsyna M, et al. Clinically applicable artificial intelligence system for dental diagnosis with CBCT. Sci Rep. 2021;11:15006.
13. Gerhardt MDN, Fontenele RC, Leite AF, et al. Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks. J Dent. 2022:122:104139.
14. Orhan K, Shamshiev M, Ezhov M, et al. AI-based automatic segmentation of craniomaxillofacial anatomy from CBCT scans for automatic detection of pharyngeal airway evaluations in OSA patients. Sci Rep. 2022;12:11863.
15. Mangano FG, Admakin O, Lerner H, Mangano C. Artificial intelligence and augmented reality for guided implant surgery planning: a proof of concept. J Dent. 2023;133:104485.
16. Ding H, Wu J, Zhao W, Matinlinna JP, Burrow MF, Tsoi JKH. Artificial intelligence in dentistry — a review. Front Dent Med. 2023;4:1085251.
17. Marks M, Haupt CE. AI Chatbots, health privacy, and challenges to HIPAA compliance. JAMA. 2023;330:309.
18. Szekely D, Milam S, Khademi J. Legal issues of the electronic dental record: security and confidentiality. J Dent Educ. 1996;60:19-23.
19. Ayad N, Schwendicke F, Krois J, et al. Patients’ perspectives on the use of artificial intelligence in dentistry: a regional survey. Head Face Med. 2023;19:23.

From Decisions in Dentistry. January/February 2024; 10(1):18-20