Search

Orofacial pain is a worldwide pain problem, with many patients unable to find appropriate diagnosis and treatment. Orofacial pain includes pain arising from the odontogenic and nonodontogenic structures in the head and neck region. Dental clinicians need to have a thorough knowledge and skill to diagnose, manage, and treat patients with odontogenic pain or refer patients for treatment of nonodontogenic pain to specialists such as orofacial pain specialists, neurologists, otolaryngologists, and rheumatologists. More often, dental practitioners diagnose patients with a temporomandibular disorder (TMD), and when treatment is ineffective, term it "atypical facial pain." The first requirement for effective treatment is an accurate diagnosis. Dental clinicians must be aware of giant cell arteritis (GCA), a chronic large-vessel vasculitis, primarily affecting adults over the age of 50 years, as it frequently mimics and is misdiagnosed as TMD. GCA is associated with loss of vision, and stroke and can be a life-threatening disorder. Therefore, diagnostic testing for GCA and differential diagnosis should be common knowledge in the armamentarium of all dental clinicians. Historically, temporal artery biopsy was considered the definitive diagnostic test for GCA. Temporal artery ultrasound (TAUSG), a safe and noninvasive imaging modality, has replaced the previous diagnostic gold standard for GCA, the temporal artery biopsy, owing to its enhanced diagnostic capabilities and safety profile. The present case report describes a patient with GCA, and the role TAUSG played in the diagnosis. Case report: A 72-year-old woman presented with left-sided facial pain, jaw claudication, dysesthesia of the tongue, and episodic loss of vision of 2 years' duration. She was diagnosed with and treated for a myriad of dental conditions including endodontia and temporomandibular joint therapy with no benefit. A thorough history and physical examination, combined with serologic analysis, led to the diagnosis of GCA and TAUSG, which confirmed the diagnosis. Conclusion: This report underscores the responsibility of differential diagnosis and early recognition of GCA facilitated by TAUSG in optimizing treatment outcomes as a viable, noninvasive diagnostic tool. [ABSTRACT FROM AUTHOR]

Purpose To assess the performance of a local open-source large language model (LLM) in various information extraction tasks from real-life emergency brain MRI reports. Materials and Methods All consecutive emergency brain MRI reports written in 2022 from a French quaternary center were retrospectively reviewed. Two radiologists identified MRI scans that were performed in the emergency department for headaches. Four radiologists scored the reports conclusions as either normal or abnormal. Abnormalities were labeled as either headache-causing or incidental. Vicuna (LMSYS Org), an open-source LLM, performed the same tasks. Vicunas performance metrics were evaluated using the radiologists consensus as the reference standard. Results Among the 2398 reports during the study period, radiologists identified 595 that included headaches in the indication (median age of patients, 35 years [IQR, 26-51 years]; 68% [403 of 595] women). A positive finding was reported in 227 of 595 (38%) cases, 136 of which could explain the headache. The LLM had a sensitivity of 98.0% (95% CI: 96.5, 99.0) and specificity of 99.3% (95% CI: 98.8, 99.7) for detecting the presence of headache in the clinical context, a sensitivity of 99.4% (95% CI: 98.3, 99.9) and specificity of 98.6% (95% CI: 92.2, 100.0) for the use of contrast medium injection, a sensitivity of 96.0% (95% CI: 92.5, 98.2) and specificity of 98.9% (95% CI: 97.2, 99.7) for study categorization as either normal or abnormal, and a sensitivity of 88.2% (95% CI: 81.6, 93.1) and specificity of 73% (95% CI: 62, 81) for causal inference between MRI findings and headache. Conclusion An open-source LLM was able to extract information from free-text radiology reports with excellent accuracy without requiring further training. Keywords: Large Language Model (LLM), Generative Pretrained Transformers (GPT), Open Source, Information Extraction, Report, Brain, MRI Supplemental material is available for this article. Published under a CC BY 4.0 license. See also the commentary by Akinci DAntonoli and Bluethgen in this issue.