Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Statement Of Problem: Healthcare-related information provided by artificial intelligence (AI) chatbots may pose challenges such as inaccuracies, lack of empathy, biases, over-reliance, limited scope, and ethical concerns.
Purpose: The purpose of this study was to evaluate and compare the validity and consistency of responses to prosthodontics-related frequently asked questions (FAQ) generated by 4 different chatbot systems.
Material And Methods: Four prosthodontics domains were evaluated: implant, fixed prosthodontics, complete denture (CD), and removable partial denture (RPD). Within each domain, 10 questions were prepared by full-time prosthodontic faculty members, and 10 questions were generated by GPT-3.5, representing its top frequently asked questions in each domain. The validity and consistency of responses provided by 4 chatbots: GPT-3.5, GPT-4, Gemini, and Bing were evaluated. The chi-squared test with the Yates correction was used to compare the validity of responses between different chatbots (α=.05). The Cronbach alpha was calculated for 3 sets of responses collected in the morning, afternoon, and evening to evaluate the consistency of the responses.
Results: According to the low threshold validity test, the chatbots' answers to ChatGPT's implant-related, ChatGPT's RPD-related, and prosthodontists' CD-related FAQs were statistically different (P<.001, P<.001, and P=.004, respectively), with Bing being the lowest. At the high threshold validity test, the chatbots' answers to ChatGPT's implant-related and RPD-related FAQs and ChatGPT's and prosthodontists' fixed prosthetics-related and CD-related FAQs were statistically different (P<.001, P<.001, P=.004, P=.002, and P=.003, respectively), with Bing being the lowest. Overall, all 4 chatbots demonstrated lower validity at the high threshold than the low threshold. Bing, Gemini, and ChatGPT-4 chatbots displayed an acceptable level of consistency, while ChatGPT-3.5 did not.
Conclusions: Currently, AI chatbots show limitations in delivering answers to patients' prosthodontic-related FAQs with high validity and consistency.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.prosdent.2025.03.009 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Integrating opinion dynamics and differential game modeling for sustainable groundwater management.
Water Res
September 2025
College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China. Electronic address:
Groundwater overextraction presents persistent challenges due to strategic interdependence among decentralized users. While game-theoretic models have advanced the analysis of individual incentives and collective outcomes, most frameworks assume fully rational agents and neglect the role of cognitive and social factors. This study proposes a coupled model that integrates opinion dynamics with a differential game of groundwater extraction, capturing the interaction between institutional authority and evolving stakeholder preferences.
View Article and Find Full Text PDFThe reliability and validity study of the Turkish version of Brief Measure of Eating Compulsivity (MEC) among adolescents.
Turk J Pediatr
September 2025
Division of Adolescent Health, Department of Pediatrics, University of Ottawa, Children's Hospital of Eastern Ontario (CHEO), Ottawa, Ontario, Canada.
Background: Food addiction has been increasingly recognized as a contributing factor to obesity and eating disorders. Compulsive eating, characterized by an uncontrollable urge to consume food despite adverse consequences, shares behavioral similarities with substance addiction. This study aims to adapt the Brief Measure of Eating Compulsivity (MEC) into Turkish and evaluate its validity and reliability in the adolescent population.
View Article and Find Full Text PDFTranslation, Adaptation, and Validation of the Young Spine Questionnaire for the Italian Children.
Pediatr Phys Ther
September 2025
Department of Medicine and Health Science, University of Trieste, 34100 Trieste, Italy (Dr Policastro and Goos); Institute for Maternal and Child Health IRCCS Burlo Garofolo, 34137 Trieste, Italy (Casalaz and Sartori); Departmental Faculty of Medicine and Surgery, Saint Camillus International Univer
Purpose: Low back and neck pain are increasing worldwide, even in children. However, Italy lacks validated tools for the assessment of children and adolescents with spine disorders. The Young Spine Questionnaire (YSQ) seems to be an appropriate option.
View Article and Find Full Text PDFThe Influence of Single-Stranded or Double-Stranded DNA Tags on Ligand Binding Affinity in DNA-Encoded Libraries.
Anal Chem
September 2025
Laboratory of Organic Chemistry, Department of Chemistry and Applied Biosciences, ETH Zurich, 8093 Zurich, Switzerland.
DNA-encoded libraries have become widely used in drug discovery, and several different setups to link chemical compounds to DNA have been employed in the field, including single-stranded and double-stranded DNA tags as well as a variety of linker chemistries. In our previous study, we observed distinct differences in binding affinities between ligands coupled either to single-stranded or double-stranded DNA; however, the molecular basis for these differences remained unclear. Here, we present a native ion mobility mass spectrometry approach that incorporates gas- and solution-phase activation techniques to systematically investigate these differences, specifically the impact of DNA tags on binding performance in protein-ligand interactions.
View Article and Find Full Text PDFSPACE: STRING proteins as complementary embeddings.
Bioinformatics
September 2025
Novo Nordisk Foundation Center for Protein Research, Department of Cellular and Molecular Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, 2200, Denmark.
Motivation: Representation learning has revolutionized sequence-based prediction of protein function and subcellular localization. Protein networks are an important source of information complementary to sequences, but the use of protein networks has proven to be challenging in the context of machine learning, especially in a cross-species setting.
Results: We leveraged the STRING database of protein networks and orthology relations for 1,322 eukaryotes to generate network-based cross-species protein embeddings.