No Detail Found!

AI Chatbots in Endodontic Treatment Planning: A Comparative Analysis Using the AIPI Framework

Author(s)
Faisal Alnassar Department of Restorative and Prosthetic Dental Sciences, College of Dentistry, Majmaah University, Al-Majmaah, 11952, Saudi Arabia
Abstract
More and more research is looking at how healthcare professionals may benefit from artificial intelligence (AI) chatbots powered by LLMs while making judgments. However, not much is known about how effective they are in structured endodontic treatment planning. The degree of agreement between the treatment plans generated by chatbots and the reference plans given in published endodontic cases was evaluated in this cross-sectional study using the Accuracy of Identified Prescriptive Instructions (AIPI) framework. The four chatbot systems that were analyzed were Glass Health, MedGebra GPT4o, Gemini 2.5 Pro, and ChatGPT 4.5. We used the AIPI scale, which ranges from 0 to 3, to evaluate the platforms. There were a total of 192 conversations as each chatbot received sixteen published endodontic case reports at three different times. Although MedGebra GPT-4o had an average AIPI score of 1.69 (p < 0.05), the much higher scores were attained by ChatGPT 4.5, Glass Health, and Gemini 2.5 Pro, totaling 2.69. Although all of the platforms were reliable in terms of time, ChatGPT 4.5 demonstrated the greatest level of consistency at the case level (75%). As a conclusion, although MedGebra had poorer consistency and accuracy, ChatGPT4.5, Glass Health, and Gemini 2.5 Pro all worked dependably and excellently. While these findings provide support for AI chatbots as supplemental educational and decision-support tools, they also show how important it is to validate these systems in certain domains before integrating them into clinical practice and how dangerous it is to have inconsistent or incomplete outcomes in the clinic.
Publication Details
Page(s) 1-6
Published Journal: Journal of Pioneering Medical Sciences, Volume: 15, Issue: s1, Year: 2026

Request the full text from PASTIC

Keywords
Artificial intelligence, Endodontics, Treatment Planning Accuracy, Chatbots, Clinical Decision Support, large language models
References
Kothinti R.R. .2024 .Deep learning in healthcare: transforming disease diagnosis, personalized treatment, and clinical decision-making through AI-driven innovations. World Journal of Advanced Research and Reviews, 24 : 2841-2856.
Chow J.C.,Li K. .2025 .Large language models in medical chatbots: opportunities, challenges, and the need to address AI risks. ” Information, 16 : 549.
Liu M. .2024 .Performance of ChatGPT across different versions in medical licensing examinations worldwide: systematic review and meta-analysis. ” Journal of Medical Internet Research, 26 : e60807.
Alam M.K. .2024 .Applications of artificial intelligence in the utilisation of imaging modalities in dentistry: a systematic review and meta-analysis of in-vitro studies. ” Heliyon, 10 : e24221.
Ismail M.I.B. . .Diagnostic applications of artificial intelligence in dental care for medically compromised patients: a scoping review. ” Digital Dental Journal, 2(2025) : 100036.
de Moura ,J.D.M .2024 .Comparative accuracy of artificial intelligence chatbots in pulpal and periradicular diagnosis: a cross-sectional study. ” Computers in Biology and Medicine, 183 : 109332.
Ahmed N. .2021 .Artificial intelligence techniques: analysis, application, and outcome in dentistry-a systematic review. , : 9751564.
Hung M. .2020 .Artificial intelligence in dentistry: harnessing big data to predict oral cancer survival. World Journal of Clinical Oncology, 11 : 918.
Hiraiwa T. .2019 .A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography. ” Dentomaxillofacial Radiology, 48 : 20180218.
Lin X. .2021 .Micro-computed tomography-guided artificial intelligence for pulp cavity and tooth segmentation on conebeam computed tomography. ” Journal of Endodontics, 47 : 1933-1941.
Sadr S. .2023 .Deep learning for detection of periapical radiolucent lesions: a systematic review and meta-analysis of diagnostic test accuracy. ” Journal of Endodontics, 49 : 248-261.
Qutieshat A. .2024 .Comparative analysis of diagnostic accuracy in endodontic assessments: dental students vs. artificial intelligence.” Diagnosis, 11 : 259-265.
Patil S.R.,Karobari M.I. .2024 .Exploring artificial intelligence for enhanced endodontic practice: applications, challenges, and future directions. ” Advances in Public Health, : 8075515.
Eggmann F.,Blatz F. .2023 .ChatGPT: chances and challenges for dentistry.” Compendium of Continuing Education in Dentistry. , 44 : .
Glick A. . .Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians. ” JAMIA Open, 5(2022) : ooac031.
Lechien J.R.,Laryngology J.R. .2024 .Validity and reliability of an instrument evaluating the performance of intelligent chatbot: the artificial intelligence performance instrument (AIPI).” European Archives of Oto-Rhino-. , 281 : 2063-2079.
Dronkers E.A. .2024 .Evaluating the potential of AI chatbots in treatment decision-making for acquired bilateral vocal fold paralysis in adults. ” Journal of Voice, : .
Maniaci A.,Laryngology A. .2025 .AI in clinical decision-making: ChatGPT4 vs. Llama2 for otolaryngology cases.” European Archives of Oto-Rhino-. , : .
Özbay Y. .2025 .Evaluation of the performance of large language models in clinical decision-making in endodontics. ” BMC Oral Health, 25 : 648.
İşisağ ,Karakaya K. .2025 .Assessing the accuracy, repeatability, and consistency of ChatGPT 4o in treatment planning for tooth-supported fixed prostheses: a comparative analysis of simple and complex clinical cases. ” Clinical Oral Investigations, 29 : 433.
Aljamani S. .2025 .Evaluating large language models in addressing patient questions on endodontic pain: a comparative analysis of accessible chatbots. ” Journal of Endodontics, : .
Büker M. .2025 .Comparative performance of chatbots in endodontic clinical decision support: a 4-day accuracy and consistency study. International Dental Journal, 75 : 100920.
Kaplan Tokgöz,Cankar T.,M. T. .2025 .Evidence-based potential of generative artificial intelligence large language models on dental avulsion: ChatGPT versus Gemini. ” Dental Traumatology, 41 : 178-186.
Danesh A. .2025 .Innovating dental diagnostics: ChatGPT's accuracy on diagnostic challenges. ” Oral Diseases, 31 : 911-917.
Abdulrab S. .2025 .Performance of 4 artificial intelligence chatbots in answering endodontic questions. ” Journal of Endodontics, 51 : 602-608.
Yang X. .2025 .Application of large language models in disease diagnosis and treatment. Chinese Medical Journal, 138 : 130-142.
Öztürk Arılı,E. Arılı .2025 .Evaluation of the performance of ChatGPT-4 and ChatGPT-4o as a learning tool in endodontics. International Endodontic Journal, : .
Liu Z. .2025 .The performance of large language models in dentomaxillofacial radiology: a systematic review. ” Dentomaxillofacial Radiology, : .
Aditya G. .2024 .Understanding and addressing AI hallucinations in healthcare and life sciences. International Journal of Health Sciences, : .
Gondode P. .2024 .Artificial intelligence hallucinations in anaesthesia: causes, consequences and countermeasures. Indian Journal of Anaesthesia, 68 : 658-661.
Hamid O.H. .2024 .Beyond probabilities: unveiling the delicate dance of large language models (LLMs) and AIhallucination. In: Proceedings of the IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), : 85-90.
Reader A.,Drum M. “ .2025 .A review of ChatGPT as a reliable source of scientific information regarding endodontic local anesthesia. ” Journal of Endodontics, : .
Rokhshad R. .2024 .Accuracy and consistency of chatbots versus clinicians for answering pediatric dentistry questions: a pilot study. ” Journal of Dentistry, 144 : 104938.
0

Citations

0

Downloads

13

Views