Journals / Haliç Üniversitesi Sağlık Bilimleri Dergisi / 2026 / Cilt: 9 Sayı: 3

Conceptual and Methodological Recommendations for Large Language Model (LLM)–Assisted Patient Education and Appointment Triage in Teledentistry

Telediş Hekimliğinde Büyük Dil Modeli (BDM) Destekli Hasta Bilgilendirme ve Randevu Yönlendirme Uygulamalarına İlişkin Kavramsal ve Yöntemsel Öneriler

Mesut Tuzlalı(INONU UNIVERSITY, FACULTY OF DENTISTRY, DEPARTMENT OF CLINICAL SCIENCES, DEPARTMENT OF PROSTHETIC DENTISTRY THERAPY)0000-0002-7602-8101
Nagehan Baki(INONU UNIVERSITY, FACULTY OF DENTISTRY, DEPARTMENT OF CLINICAL SCIENCES, DEPARTMENT OF PROSTHETIC DENTISTRY THERAPY)0000-0002-3221-4543
Pages
1–3
Publication Date
2026-09-11
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Adoption of this framework may improve comparability across studies and support patient safety–oriented quality assurance in teledentistry.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This letter highlights conceptual and methodological requirements for the use of large language model (LLM)–based chatbots in patient education and appointment triage within teledentistry.
📊
Key Findings & Data:Existing studies demonstrate the potential of these systems to respond to oral health–related questions; however, substantial variation remains in the definition of intended use, evaluation metrics, safety boundaries, and reporting practices.
💡
Conclusion & Impact:Adoption of this framework may improve comparability across studies and support patient safety–oriented quality assurance in teledentistry.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Büyük dil modeli · diş hekimliği · telediş hekimliği

Abstract

This letter highlights conceptual and methodological requirements for the use of large language model (LLM)–based chatbots in patient education and appointment triage within teledentistry. Existing studies demonstrate the potential of these systems to respond to oral health–related questions; however, substantial variation remains in the definition of intended use, evaluation metrics, safety boundaries, and reporting practices. Clear identification of red flags and escalation pathways is particularly important for time-sensitive conditions such as dental infection, facial or neck swelling, trismus, dysphagia, dyspnea, and systemic symptoms. Therefore, we propose a minimum reporting dataset for LLM-assisted patient education and appointment triage in teledentistry. The proposed dataset includes model information, intended use, input scenarios, safety and escalation rules, evaluation metrics, human evaluator characteristics, reporting transparency, and data privacy considerations. Adoption of this framework may improve comparability across studies and support patient safety–oriented quality assurance in teledentistry.

Özet

Bu editöre mektup, telediş hekimliğinde büyük dil modeli (BDM) tabanlı sohbet botlarının hasta bilgilendirme ve randevu yönlendirme süreçlerinde kullanımına ilişkin kavramsal ve yöntemsel gerekliliklere dikkat çekmektedir. Mevcut çalışmalar, bu sistemlerin ağız-diş sağlığı sorularına yanıt üretme potansiyelini göstermekte; ancak kullanım amacı, değerlendirme metrikleri, güvenlik sınırları ve raporlama biçimleri açısından belirgin farklılıklar bulunmaktadır. Özellikle dental enfeksiyon, yüz-boyun şişliği, trismus, disfaji, dispne ve sistemik bulgular gibi zaman-duyarlı klinik durumlarda kırmızı bayrakların ve eskalasyon protokollerinin açık biçimde tanımlanması hasta güvenliği açısından kritik önemdedir. Bu nedenle, BDM destekli hasta bilgilendirme ve randevu yönlendirme uygulamaları için model bilgisi, kullanım amacı, girdi senaryoları, güvenlik/eskalasyon kuralları, değerlendirme metrikleri, insan değerlendirici özellikleri, raporlama şeffaflığı ve veri gizliliği başlıklarını içeren bir asgari raporlama veri seti önerilmektedir. Bu çerçevenin, telediş hekimliği alanındaki çalışmaların karşılaştırılabilirliğini artıracağı ve hasta güvenliği odaklı kalite güvencesine katkı sağlayacağı düşünülmektedir.

🔖

Cite This Article

Tuzlalı, M., Baki, N. (2026). Conceptual and Methodological Recommendations for Large Language Model (LLM)–Assisted Patient Education and Appointment Triage in Teledentistry. Haliç Üniversitesi Sağlık Bilimleri Dergisi, Cilt: 9 Sayı: 3, 1–3. https://doi.org/10.48124/husagbilder.1858351

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (8)

  1. Tuzlalı M, Baki N, Aral K, Aral CA, Bahçe E. Evaluating the performance of AI chatbots in responding to dental implant FAQs: A comparative study. BMC Oral Health. 2025;25(1):1548.
  2. Çoban E, Altay B. ChatGPT May Help Inform Patients in Dental Implantology. International Journal of Oral & Maxillofacial Implants. 2024;39(5).
  3. Özdemir ÖT, Kavan MY, Güven Y. Evaluation of the readability, quality, and accuracy of AI chatbot responses to questions about deleterious oral habits. BMC Oral Health. 2025;25(1):1812.
  4. Aljamani S, Hassona Y, Fansa HA, H MS, Dafi Jamani K. Evaluating Large Language Models in Addressing Patient Questions on Endodontic Pain: A Comparative Analysis of Accessible Chatbots. J Endod. 2025;51(11):1617-24.
  5. Cole-Healy Z, Adam D, Noh K, Graham RM. Introducing the FATLIPS acronym for assessing the red flag clinical features of dental infection. Br Dent J. 2021;230(3):170-2.
  6. Devine C. Aptly coined acronym. British Dental Journal. 2021;230(7):386.
  7. Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Lancet Digit Health. 2020;2(10):e537-e48.
  8. Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med. 2020;26(9):1351-63.