Evaluation of the mandibular condylar bone microarchitecture in people living with HIV.

OBJECTIVES: People living with HIV (PLWH) have been shown to have lower bone density at the spine, hip, and radius. However, whether a similar bone phenotype is seen in craniofacial bones is not known. The goal of this study was to evaluate the bone microarchitecture of the mandibular condyle in PLWH. METHODS: We recruited 212 participants, which included 88 HIV-negative participants and 124 PLWH on combination antiretroviral therapy with virological suppression from a single academic center. Each participant filled out a validated temporomandibular disorder (TMD) pain screening questionnaire and had cone beam computed tomography (CBCT) of their mandibular condyles. Qualitative radiographic evidence of temporomandibular joint disorders-osteoarthritis (TMJD-OA) assessment and quantitative microarchitecture analysis of their mandibular condylar bones were conducted. RESULTS: There was no statistically significant difference in either self-reported TMD or in radiographic evidence of TMJD-OA in PLWH compared with HIV-negative controls. Linear regression analysis revealed that positive HIV status remained significantly associated with increased trabecular thickness, decreased cortical porosity, and increased cortical bone volume fraction after adjusting for race, diabetes, sex, and age. CONCLUSION: PLWH have increased mandibular condylar trabecular bone thickness and cortical bone volume fraction compared with HIV-negative controls.

Effectiveness of Machine Learning in Predicting Orthodontic Tooth Extractions: A Multi-Institutional Study.

The study aimed to evaluate the effectiveness of machine learning in predicting whether orthodontic patients would require extraction or non-extraction treatment using data from two university datasets. A total of 1135 patients, with 297 from University 1 and 838 from University 2, were included during consecutive enrollment periods. The study identified 20 inputs including 9 clinical features and 11 cephalometric measurements based on previous research. Random forest (RF) models were used to make predictions for both institutions. The performance of each model was assessed using sensitivity (SEN), specificity (SPE), accuracy (ACC), and feature ranking. The model trained on the combined data from two universities demonstrated the highest performance, achieving 50% sensitivity, 97% specificity, and 85% accuracy. When cross-predicting, where the University 1 (U1) model was applied to the University 2 (U2) data and vice versa, there was a slight decrease in performance metrics (ranging from 0% to 20%). Maxillary and mandibular crowding were identified as the most significant features influencing extraction decisions in both institutions. This study is among the first to utilize datasets from two United States institutions, marking progress toward developing an artificial intelligence model to support orthodontists in clinical practice.