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

Background
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.
Case Description
A structured, machine-learning-compatible note-taking system was created to document clinical history and examination findings for patients at the Orofacial Pain and Oral Medicine Center of USC. 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.
Practical Implications
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.
Clark GT, Vistoso Monreal A, Veas N, Loeb GE. Artificial intelligence algorithm for real-time diagnostic assist in orofacial pain. J Am Dent Assoc. 2025 Aug;156(8):664-673. doi: 10.1016/j.adaj.2025.05.002. Epub 2025 Jun 13. PMID: 40512111.

IRB
The following section is required and included in the informed consent to share data/specimen to a repository. This section is also required for any NIH-supported study.
FUTURE USE OF DATA
This study is collecting data and/or biospecimens from you. We will make your data and/or biospecimens available for other research studies that may be done in the future. The research may be about similar diseases or conditions to this study. However, research could also be about unrelated diseases, conditions, or other types of research. These studies may be done by researchers at this institution or other institutions, including commercial entities. Our goal is to make more research possible. We plan to keep your data and/or biospecimens indefinitely. All data will be transferred securely. If you are not comfortable with this, you should not participate in this study.

This is included in the USC informed consent template together with other addtions or modifications on use of data.