Stakeholder-Reported Requirements for Future Artificial Intelligence Decision Support in Periodontal Care: A Cross-Sectional Survey of Dentists, Physicians and Patients in Kazakhstan.
- 1Center of Epidemiology and Management, Astana Medical University, Astana010000 , Kazakhstan.
Abstract
Background/Objectives: Clinicians' expectations of artificial intelligence (AI) for periodontal care in Central Asia are largely unknown. We surveyed dentists and physicians in Kazakhstan on preliminary requirements for a future decision-support system and explored patients' self-reported periodontal signs. Methods: Cross-sectional online surveys (July-September 2026; non-probability recruitment) included 33 dentists, 91 primary health care physicians and medical specialists, and 455 adult patients whose periodontal eligibility was not clinically verified; the patient questionnaire did not address AI. Analyses used Wilson 95% confidence intervals (CI), exact tests with Holm adjustment and exploratory logistic regression. Results: Dentists prioritised history-taking (81.8%) and early gingivitis diagnosis (69.7%). Autonomy choices were spread across five clinician-controlled configurations (low autonomy most frequent, 30.3%); no autonomous option was offered. Lack of a legal framework and liability insurance was the most cited barrier (60.6%). Physicians and specialists selected early gingivitis screening (80.2%) but cited insufficient competence (53.8%). Self-reported signs occurred in 49.0% of patients. Associations with high stress (adjusted odds ratio 2.11; 95% CI 1.14-3.89) and family history (1.61; 1.02-2.55) lost significance after excluding 204 responses collected via an inter-university platform. Conclusions: Clinician responses suggest preliminary requirements; patient associations remain exploratory. Instrument and clinical outcome validation should precede system design.
Related
- Generative Artificial Intelligence in Periodontology: Application of OpenAI Models for the Classification of Periodontitis and Risk Assessment in Patients Undergoing Supportive Periodontal Care
- Physicians and artificial intelligence diverge in evaluating large language models on real clinical cases
- Quality of physicians responses using a conversational artificial intelligence system: a randomized vignette experiment in Latin America
- Artificial intelligence awareness, usage, and readiness among fellows of the West African college of physicians.
- Generative artificial intelligence in the preparation of scientific medical articles on surgery: principles of responsible use and current requirements of editorial organisations
BibTeX
@article{ayash2026stakeholderreported,
title = {{Stakeholder-Reported Requirements for Future Artificial Intelligence Decision Support in Periodontal Care: A Cross-Sectional Survey of Dentists, Physicians and Patients in Kazakhstan.}},
author = {Yerbol Ayash and Aigul Ismailova and Anar Aidarkhanova and Aiman Mussina and Zhanat Abdikadyr and Akerke Chayakova},
journal = {Healthcare (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/healthcare14203554},
url = {https://europepmc.org/article/MED/42940599},
note = {CC BY},
}
RIS
TY - JOUR
TI - Stakeholder-Reported Requirements for Future Artificial Intelligence Decision Support in Periodontal Care: A Cross-Sectional Survey of Dentists, Physicians and Patients in Kazakhstan.
AU - Yerbol Ayash
AU - Aigul Ismailova
AU - Anar Aidarkhanova
AU - Aiman Mussina
AU - Zhanat Abdikadyr
AU - Akerke Chayakova
PY - 2026
DA - 2026/10/21
JO - Healthcare (Basel, Switzerland)
DO - 10.3390/healthcare14203554
UR - https://europepmc.org/article/MED/42940599
AB - Background/Objectives: Clinicians' expectations of artificial intelligence (AI) for periodontal care in Central Asia are largely unknown. We surveyed dentists and physicians in Kazakhstan on preliminary requirements for a future decision-support system and explored patients' self-reported periodontal signs. Methods: Cross-sectional online surveys (July-September 2026; non-probability recruitment) included 33 dentists, 91 primary health care physicians and medical specialists, and 455 adult patients whose periodontal eligibility was not clinically verified; the patient questionnaire did not address AI. Analyses used Wilson 95% confidence intervals (CI), exact tests with Holm adjustment and exploratory logistic regression. Results: Dentists prioritised history-taking (81.8%) and early gingivitis diagnosis (69.7%). Autonomy choices were spread across five clinician-controlled configurations (low autonomy most frequent, 30.3%); no autonomous option was offered. Lack of a legal framework and liability insurance was the most cited barrier (60.6%). Physicians and specialists selected early gingivitis screening (80.2%) but cited insufficient competence (53.8%). Self-reported signs occurred in 49.0% of patients. Associations with high stress (adjusted odds ratio 2.11; 95% CI 1.14-3.89) and family history (1.61; 1.02-2.55) lost significance after excluding 204 responses collected via an inter-university platform. Conclusions: Clinician responses suggest preliminary requirements; patient associations remain exploratory. Instrument and clinical outcome validation should precede system design.
SN - 2227-9032
ER -