Journal Of Clinical Periodontology, Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 26, 2024
Artificial intelligence (AI) has the potential to enhance healthcare practices, including periodontology, by improving diagnostics, treatment planning and patient care. This study introduces 'PerioGPT', a specialized AI model designed provide up-to-date periodontal knowledge using GPT-4o novel retrieval-augmented generation (RAG) system.
Language: Английский
Journal of Prosthetic Dentistry, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 1, 2025
Language: Английский
Citations
2
Cureus, Journal Year: 2024, Volume and Issue: unknown
Published: May 8, 2024
Introduction: ChatGPT has been tested in many disciplines, but only a few have involved hearing diagnosis and none to physiology or audiology more generally. The consistency of the chatbot's responses same question posed multiple times not well investigated either. This study aimed assess accuracy repeatability 3.5 4 on test questions concerning objective measures hearing. Of particular interest was short-term which here four separate days extended over one week. Methods: We used 30 single-answer, multiple-choice exam from one-year course methods testing were five both (the free version) paid each (two week two following week). evaluated terms response key. To evaluate time, percent agreement Cohen's Kappa calculated. Results: overall 48-49%, while that 65-69%. consistently failed pass threshold 50% correct responses. Within single day, 76-79% for 87-88% (Cohen's 0.67-0.71 0.81-0.84 respectively). between different 75-79% 85-88% 0.65-0.69 0.80-0.85 Conclusion: outperforms higher time. However, great variability casts doubt possible professional applications versions.
Language: Английский
Citations
11
Journal of Periodontal Research, Journal Year: 2024, Volume and Issue: unknown
Published: July 18, 2024
Abstract Introduction The emerging rise in novel computer technologies and automated data analytics has the potential to change course of dental education. In line with our long‐term goal harnessing power AI augment didactic teaching, objective this study was quantify compare accuracy responses provided by ChatGPT (GPT‐4 GPT‐3.5) Google Gemini, three primary large language models (LLMs), human graduate students (control group) annual in‐service examination questions posed American Academy Periodontology (AAP). Methods Under a comparative cross‐sectional design, corpus 1312 from AAP administered between 2020 2023 were presented LLMs. Their analyzed using chi‐square tests, performance juxtaposed scores periodontal residents corresponding years, as control group. Additionally, two sub‐analyses performed: one on LLMs each section exam; answering most difficult questions. Results ChatGPT‐4 (total average: 79.57%) outperformed all groups well GPT‐3.5 Gemini exam years ( p < .001). This chatbot showed an range 78.80% 80.98% across various years. consistently recorded superior 70.65% = .01), 73.29% .02), 75.73% 72.18% .0008) for exams compared ChatGPT‐3.5, which achieved 62.5%, 68.24%, 69.83%, 59.27% respectively. (72.86%) surpassed average first‐ (63.48% ± 31.67) second‐year (66.25% 31.61) when combined. However, it could not surpass that third‐year (69.06% 30.45). Conclusions Within confines analysis, exhibited robust capability terms reliability while ChatGPT‐3.5 weaker performance. These findings underscore deploying educational tool periodontics oral implantology domains. current limitations these such inability effectively process image‐based inquiries, propensity generating inconsistent same prompts, achieving high (80% GPT‐4) but absolute rates should be considered. An comparison their versus capacity is required further develop field study.
Language: Английский
Citations
11
Brain Sciences, Journal Year: 2024, Volume and Issue: 14(5), P. 465 - 465
Published: May 7, 2024
Testing of ChatGPT has recently been performed over a diverse range topics. However, most these assessments have based on broad domains knowledge. Here, we test ChatGPT’s knowledge tinnitus, an important but specialized aspect audiology and otolaryngology. involved evaluating answers to defined set 10 questions tinnitus. Furthermore, given the technology is advancing quickly, re-evaluated responses same 3 6 months later. The accuracy was rated by experts (the authors) using Likert scale ranging from 1 5. Most were as satisfactory or better. did detect few instances where not accurate might be considered somewhat misleading. Over first months, ratings generally improved, there no more significant improvement at months. In our judgment, provided unexpectedly good responses, that quite specific. Although potentially harmful errors identified, some mistakes could seen shows great potential if further developed in specific areas, for now, it yet ready serious application.
Language: Английский
Citations
9
Frontiers in Dental Medicine, Journal Year: 2025, Volume and Issue: 5
Published: Jan. 6, 2025
Artificial intelligence has dramatically reshaped our interaction with digital technologies, ushering in an era where advancements AI algorithms and Large Language Models (LLMs) have natural language processing (NLP) systems like ChatGPT. This study delves into the impact of cutting-edge LLMs, notably OpenAI's ChatGPT, on medical diagnostics, a keen focus dental sector. Leveraging publicly accessible datasets, these models augment diagnostic capabilities professionals, streamline communication between patients healthcare providers, enhance efficiency clinical procedures. The advent ChatGPT-4 is poised to make substantial inroads practices, especially realm oral surgery. paper sheds light current landscape explores potential future research directions burgeoning field offering valuable insights for both practitioners developers. Furthermore, it critically assesses broad implications challenges within various sectors, including academia healthcare, thus mapping out overview AI's role transforming diagnostics enhanced patient care.
Language: Английский
Citations
1
BMC Oral Health, Journal Year: 2024, Volume and Issue: 24(1)
Published: May 24, 2024
Abstract Background The use of artificial intelligence in the field health sciences is becoming widespread. It known that patients benefit from applications on various issues, especially after pandemic period. One most important issues this regard accuracy information provided by applications. Objective purpose study was to frequently asked questions about dental amalgam, as determined United States Food and Drug Administration (FDA), which one these resources, Chat Generative Pre-trained Transformer version 4 (ChatGPT-4) compare content answers given application with FDA. Methods were directed ChatGPT-4 May 8th 16th, 2023, responses recorded compared at word meaning levels using ChatGPT. FDA webpage also recorded. for similarity “Main Idea”, “Quality Analysis”, “Common Ideas”, “Inconsistent Ideas” between ChatGPT-4’s FDA’s responses. Results similar one-week intervals. In comparison guidance, it questions. However, although there some similarities general aspects recommendation regarding amalgam removal question, two texts are not same, they offered different perspectives replacement fillings. Conclusions findings indicate ChatGPT-4, an based application, encompasses current accurate its removal, providing individuals seeking access such information. Nevertheless, we believe numerous studies required assess validity reliability across diverse subjects.
Language: Английский
Citations
8
Dental Traumatology, Journal Year: 2024, Volume and Issue: unknown
Published: Nov. 22, 2024
ABSTRACT Background/Aim Artificial intelligence (AI) chatbots have become increasingly prevalent in recent years as potential sources of online healthcare information for patients when making medical/dental decisions. This study assessed the readability, quality, and accuracy responses provided by three AI to questions related traumatic dental injuries (TDIs), either retrieved from popular question‐answer sites or manually created based on hypothetical case scenarios. Materials Methods A total 59 injury queries were directed at ChatGPT 3.5, 4.0, Google Gemini. Readability was evaluated using Flesch Reading Ease (FRE) Flesch–Kincaid Grade Level (FKGL) scores. To assess response quality accuracy, DISCERN tool, Global Quality Score (GQS), misinformation scores used. The understandability actionability analyzed Patient Education Assessment Tool Printed (PEMAT‐P) tool. Statistical analysis included Kruskal–Wallis with Dunn's post hoc test non‐normal variables, one‐way ANOVA Tukey's normal variables ( p < 0.05). Results mean FKGL FRE Gemini 11.2 49.25, 11.8 46.42, 10.1 51.91, respectively, indicating that difficult read required a college‐level reading ability. 3.5 had lowest PEMAT‐P among 0.001). 4.0 rated higher (GQS score 5) compared Conclusions In this study, although widely used, some misleading inaccurate about TDIs. contrast, generated more accurate comprehensive answers, them reliable auxiliary sources. However, complex issues like TDIs, no chatbot can replace dentist diagnosis, treatment, follow‐up care.
Language: Английский
Citations
5
Journal of the World Federation of Orthodontists, Journal Year: 2024, Volume and Issue: unknown
Published: Oct. 1, 2024
Language: Английский
Citations
4
Journal of Oral Rehabilitation, Journal Year: 2025, Volume and Issue: unknown
Published: Feb. 6, 2025
ABSTRACT Background Artificial Intelligence (AI) has been widely used in health research, but the effectiveness of large language models (LLMs) providing accurate information on bruxism not yet evaluated. Objectives To assess readability, accuracy and consistency three LLMs responding to frequently asked questions about bruxism. Methods This cross‐sectional observational study utilised Google Trends tool identify 10 most frequent topics Thirty were selected, which submitted ChatGPT‐3.5, ChatGPT‐4 Gemini at two different times (T1 T2). The readability was measured using Flesch Reading Ease (FRE) Flesch–Kincaid Grade Level (FKG) metrics. responses evaluated for a three‐point scale, verified by comparing between T1 T2. Statistical analysis included ANOVA, chi‐squared tests Cohen's kappa coefficient considering p value 0.5. Results In terms there no difference FRE. model showed lower FKG scores than Generative Pretrained Transformer (GPT)‐3.5 GPT‐4 models. average 68.33% GPT‐3.5, 65% 55% Gemini, with significant differences ( = 0.290). Consistency substantial all models, highest being GPT‐3.5 (95%). demonstrated agreement Conclusion Gemini's potentially more accessible broader patient population. moderate accuracy, indicating that these tools should replace professional dental guidance.
Language: Английский
Citations
0
International Dental Journal, Journal Year: 2025, Volume and Issue: unknown
Published: Feb. 1, 2025
In the final part of this two article on artificial intelligence (AI) in dentistry we review its transformative role, focusing AI dental education, patient communications, challenges integration, strategies to overcome barriers, ethical considerations, and finally, recently released International Dental Federation (FDI) Communique (white paper) Dentistry. education is highlighted for potential enhancing theoretical practical dimensions, including telemonitoring virtual training ecosystems. Challenges integration are outlined, such as data availability, bias, human accountability. Strategies these include promoting literacy, establishing regulations, specific implementations. Ethical considerations within dentistry, privacy algorithm emphasized. The need clear guidelines ongoing evaluation systems crucial. FDI White Paper Dentistry provides insights into significance oral care, research, along with standards governance. It discusses AI's impact individual patients, community health, research. paper addresses biases, limited generalizability, accessibility, regulatory requirements practice. conclusion, plays a significant role modern offering benefits diagnosis, treatment planning, decision-making. While facing challenges, strategic initiatives targeted implementations can help barriers maximize dentistry. essential ensuring responsible, effective efficacious deployment technologies ecosystem.
Language: Английский
Citations
0