Assessing the accuracy and completeness of artificial intelligence language models in providing information on methotrexate use

We aimed to assess Large Language Models (LLMs)-ChatGPT 3.5-4, BARD, and Bing-in their accuracy and completeness when answering Methotrexate (MTX) related questions for treating rheumatoid arthritis. We employed 23 questions from an earlier study related to MTX concerns. These questions were entered into the LLMs, and the responses generated by each model were evaluated by two reviewers using Likert scales to assess accuracy and completeness. The GPT models achieved a 100% correct answer rate, while BARD and Bing scored 73.91%. In terms of accuracy of the outputs (completely correct responses), GPT-4 achieved a score of 100%, GPT 3.5 secured 86.96%, and BARD and Bing each scored 60.87%. BARD produced 17.39% incorrect responses and 8.7% non-responses, while Bing recorded 13.04% incorrect and 13.04% non-responses. The ChatGPT models produced significantly more accurate responses than Bing for the "mechanism of action" category, and GPT-4 model showed significantly higher accuracy than BARD in the "side effects" category. There were no statistically significant differences among the models for the "lifestyle" category. GPT-4 achieved a comprehensive output of 100%, followed by GPT-3.5 at 86.96%, BARD at 60.86%, and Bing at 0%. In the "mechanism of action" category, both ChatGPT models and BARD produced significantly more comprehensive outputs than Bing. For the "side effects" and "lifestyle" categories, the ChatGPT models showed significantly higher completeness than Bing. The GPT models, particularly GPT 4, demonstrated superior performance in providing accurate and comprehensive patient information about MTX use. However, the study also identified inaccuracies and shortcomings in the generated responses.

[Position paper on medication-related osteonecrosis of the jaw (MRONJ)]

It is now 12 years since the first article on medication-related osteonecrosis of the jaw (MRONJ) was reported in 2003. The recognition of MRONJ is still inconsistent between physicians and dentists but it is without doubt a severe disease with impairment of oral health-related quality of life. This position paper was developed by three Austrian societies for dentists, oral surgeons and osteologists involved in this topic. This update contains amendments on the incidence, pathophysiology, diagnosis, staging and treatment and provides recommendations for management based on a multidisciplinary international consensus. The MRONJ can be a medication-related side effect of treatment of malignant and benign bone diseases with bisphosphonates (Bp), bevacizumab and denosumab (Dmab) as antiresorptive therapy. The incidence of MRONJ is highest in the oncology patient population (range 1-15 %), where high doses of these medications are used at frequent intervals. In the osteoporosis patient population, the incidence of MRONJ is estimated to be 0.001-0.01 %, marginally higher than the incidence in the general population (< 0.001 %). Other risk factors for MRONJ include glucocorticoid use, maxillary or mandibular bone surgery, poor oral hygiene, chronic inflammation, diabetes mellitus, ill-fitting dentures as well as other drugs, including antiangiogenic agents. Prevention strategies for MRONJ include elimination or stabilization of oral disease prior to initiation of antiresorptive agents, as well as maintenance of good oral hygiene. In those patients at high risk for the development of MRONJ, including cancer patients receiving high-dose BP or Dmab therapy, consideration should be given to withholding antiresorptive therapy following extensive oral surgery until the surgical site heals with mature mucosal coverage. Management of MRONJ is based on the stage of the disease, extent of the lesions and the presence of contributing drug therapy and comorbidity. Conservative therapy includes topical antibiotic oral rinses and systemic antibiotic therapy. Early data have suggested enhanced osseous wound healing with teriparatide in those patients without contraindications for its use. The MRONJ related to denosumab may resolve more quickly with a drug holiday than MRONJ related to bisphosphonates. Localized surgical debridement is indicated in advanced nonresponsive disease and has proven successful. More invasive surgical techniques are becoming increasingly more important. Prevention is the key for the management of MRONJ. This requires a close teamwork for the treating physician and the dentist. It is necessary that this information is disseminated to other relevant health care professionals and organizations.

Osteonecrosis of jaw beyond antiresorptive (bone-targeted) agents: new horizons in oncology

INTRODUCTION

Osteonecrosis of the jaw (ONJ) is a clinically important, potentially painful and debilitating condition, which can affect the quality of life of cancer patients. Since 2003, ONJ appeared as a Bisphosphonate(BP)-related class effect, and the term Bisphosphonate-Related Osteonecrosis of the Jaw (BRONJ) was widespread.

AREAS COVERED

Under discussion in this review is the fact that ONJ cases have been reported after treatment including antiangiogenic agents and other "targeted therapy", with and without BPs. Consequently, the comprehensive term Medication-Related Osteonecrosis of the Jaw (MRONJ) has been introduced. The clinical aspects and the prognosis of ONJ associated with these new drugs are still less reported, but basing on their pharmacodynamics, they could be different from the well-known BRONJ. Accordingly, recommendations largely in use for BRONJ should be extended to these new forms, but critically applied and with respect to the individual risk assessment.

EXPERT OPINION

There is a high risk of underdiagnoses for ONJ due to a lack of awareness, and too much restrictive or incomplete diagnostic criteria; at the same time, with regard to ONJ associated to the new non -antiresorptive agents, described here, we observe the strong need to improve the defining of any distinguished feature in their diagnosis, prevention and therapy.