Assessment of Artificial Intelligence Chatbots' Information Quality on Home Dental Bleaching: A Comparative Study.

Introduction: The purpose of this research was to compare how artificial intelligence chatbots (ChatGPT-3.5, ChatGPT-4, Gemini, and DeepSeek) responded to common patient inquiries regarding home dental bleaching, with an emphasis on quality, accuracy, clarity, and practical applicability. Methods: F...

Descripción completa

Detalles Bibliográficos
Publicado en:Lokman Hekim Health Sciences Vol. 6; no. 2; pp. 246 - 255
Autores principales: Özişçi, Özlem, Gökmen, Elif Irmak
Formato: research tables/charts Journal Article
Publicado: KARE Publishing Jun2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194639950&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 194639950
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        27917835
        N1MV
      jtl: Lokman Hekim Health Sciences
      issn: 27917835
      maglogo: N
    pubinfo:
      dt: Jun2026
      vid: 6
      iid: 2
      pid: 62027
      pub: KARE Publishing
    artinfo:
      ui:
        194639950
        194639950
        194639950
        10.14744/lhhs.2026.25363
        194639950
      ppf: 246
      ppct: 9
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Assessment of Artificial Intelligence Chatbots' Information Quality on Home Dental Bleaching: A Comparative Study.
      aug:
        au:
          Özişçi, Özlem
          Gökmen, Elif Irmak
        affil: Department of Prosthodontics, Süleyman Demirel University Faculty of Dentistry, Isparta, Türkiye
      sug:
        subj:
          Tooth Bleaching
          Quality Assessment
          Health Information
          Artificial Intelligence, Generative Methods
          Chatbot Utilization
          Dental Devices, Home Care
          Human
          Female
          Male
          Comparative Studies
          Cross Sectional Studies
          Descriptive Research
          Scales
          Interrater Reliability
          Patient Education
          Multiple Linear Regression
          Kruskal-Wallis Test
          Post Hoc Analysis
          Spearman's Rank Correlation Coefficient
          Data Analysis Software
          Descriptive Statistics
          Female
          Male
      ab: Introduction: The purpose of this research was to compare how artificial intelligence chatbots (ChatGPT-3.5, ChatGPT-4, Gemini, and DeepSeek) responded to common patient inquiries regarding home dental bleaching, with an emphasis on quality, accuracy, clarity, and practical applicability. Methods: Forty patient-oriented questions identified using the AlsoAsked tool, which extracts Google "People Also Ask" data, were categorized into seven thematic domains and submitted individually to each chatbot in separate sessions. Responses were independently scored by two evaluators using the global quality scale (GQS), accuracy of information index (AOI), and patient education materials assessment tool for printed materials. Response times were recorded in seconds. Statistical analyses included the Kruskal--Wallis test, Bonferroni-adjusted pairwise comparisons, and Spearman correlation (p<0.05). Results: ChatGPT-4 and DeepSeek achieved the highest GQS and AOI scores. DeepSeek had the highest actionability score but the longest response time. ChatGPT-3.5 demonstrated moderate performance, while Gemini had the lowest intelligibility and actionability scores. Discussion and Conclusion: Advanced artificial intelligence chatbots can provide high-quality and accurate information on at-home dental bleaching. However, unsupervised use may pose patient safety risks; thus, their deployment should be limited to validated, monitored, and task-specific applications.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N