Artificial intelligence algorithm for real-time diagnostic assist in orofacial pain

• Published in: The Journal of the American Dental Association (1939) Vol. 156; no. 8; pp. 664 - 673
• Main Authors: Clark, Glenn Thomas, Vistoso Monreal, Anette, Veas, Nicolas, Loeb, Gerald E.
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.08.2025
• Subjects: Adult; algorithmic decision support; Algorithms; Artificial Intelligence; Bayes Theorem; Diagnosis, Computer-Assisted - methods; diagnostic accuracy; Electronic Health Records; electronic medical records; Facial Pain - diagnosis; Female; Humans; Machine Learning; Male; Medical History Taking; Middle Aged; Orofacial pain; structured note taking; diagnostic accuracy; structured note taking; electronic medical records; Orofacial pain; algorithmic decision support; artificial intelligence
• ISSN: 0002-8177; 1943-4723; 1943-4723
• DOI: 10.1016/j.adaj.2025.05.002

Misdiagnosis is prevalent in clinical practice due to incomplete and sometimes inconsistent data, which generate errors in the traditional diagnostic process. Orofacial pain, with its wide range of conditions, poses a considerable diagnostic challenge, particularly for inexperienced clinicians. A structured, machine learning–compatible note-taking system was used to document clinical history and examination features from 1,020 patients at an orofacial pain clinic. A naïve Bayesian inference algorithm was used to compute and display the probability of various diagnoses as data were added to the medical record during a clinical encounter. Its accuracy compared favorably with 5 machine learning algorithms for 5 new cases of each of 10 diagnoses varying in their prevalence in the database. The authors speculated that the key to achieving reasonable concordance was the highly structured electronic medical record, which included disease-defining or unique features of most diagnoses. Extension of these methods to broader clinical domains will require similar attention.