The potential of large language models (LLMs) in medical applications is significant, and Retrieval-augmented generation (RAG) can address the weaknesses of these models in terms of data transparency and scientific accuracy by incorporating current scientific knowledge into responses. In this study, RAG and GPT-4 by OpenAI were applied to develop GuideGPT, a context aware chatbot integrated with a knowledge database from 449 scientific publications designed to provide answers on the prevention, diagnosis, and treatment of medication-related osteonecrosis of the jaw (MRONJ). A comparison was made with a generic LLM ("PureGPT") across 30 MRONJ-related questions. Ten international experts in MRONJ evaluated the responses based on content, language, scientific explanation, and agreement using 5-point Likert scales. Statistical analysis using the Mann-Whitney U test showed significantly better ratings for GuideGPT than PureGPT regarding content (p = 0.006), scientific explanation (p = 0.032), and agreement (p = 0.008), though not for language (p = 0.407). Thus, this study demonstrates RAG to be a promising tool to improve response quality and reliability of LLMs by incorporating domain-specific knowledge. This approach addresses the limitations of generic chatbots and can provide traceable and up-to-date responses essential for clinical practice.
Stimulated Raman Histology (SRH) employs the stimulated Raman scattering (SRS) of photons at biomolecules in tissue samples to generate histological images. Subsequent pathological analysis allows for an intraoperative evaluation without the need for sectioning and staining. The objective of this study was to investigate a deep learning-based classification of oral squamous cell carcinoma (OSCC) and the sub-classification of non-malignant tissue types, as well as to compare the performances of the classifier between SRS and SRH images. Raman shifts were measured at wavenumbers k1 = 2845 cm−1 and k2 = 2930 cm−1. SRS images were transformed into SRH images resembling traditional H&E-stained frozen sections. The annotation of 6 tissue types was performed on images obtained from 80 tissue samples from eight OSCC patients. A VGG19-based convolutional neural network was then trained on 64 SRS images (and corresponding SRH images) and tested on 16. A balanced accuracy of 0.90 (0.87 for SRH images) and F1-scores of 0.91 (0.91 for SRH) for stroma, 0.98 (0.96 for SRH) for adipose tissue, 0.90 (0.87 for SRH) for squamous epithelium, 0.92 (0.76 for SRH) for muscle, 0.87 (0.90 for SRH) for glandular tissue, and 0.88 (0.87 for SRH) for tumor were achieved. The results of this study demonstrate the suitability of deep learning for the intraoperative identification of tissue types directly on SRS and SRH images.
X-linked hypophosphatemia is a rare, hereditary disorder that significant influences teeth and alveolar bone. The first clinical sign leading to the diagnosis of X-linked hypophosphatemia is often dental impairment with dental abscesses and dentin mineralization defects. Genetic analysis helped find the responsible gene and therefore opened up new ways of therapeutically managing X-linked hypophosphatemia. The human monoclonal antibody Burosumab represents a milestone in the targeted therapy of this hereditary disease by directly addressing its pathophysiology. Targeted therapy has been shown to improve skeletal impairment, pain, and phosphate metabolism. However, the influence of this new therapy on dental impairment has only been addressed in a few recent studies with varying results. Therefore, in this review, we aim to summarize the dental phenotype and analyze the different treatment modalities with a focus on dental impairment.
20 November 2025 in Journal of Cranio-Maxillofacial Surgery