Enhancing diagnostic accuracy in dentistry through artificial intelligence and machine learning models

Read full text Summarise with VIRAT
Authors: Zela Margot Murray, Valery Geovana Prens Baena, Larry Angel Delgado Martín, Harlee C. Cruzatt
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Background and aim: This study evaluates the diagnostic capabilities of AI and ML models in dentistry, comparing their performance with human diagnoses of conditions such as caries, bone loss, periodontal disease, and oral cancer. Traditional diagnostic methods, such as radiographs, are often influenced by human interpretation, which can delay early detection of disease. The main aim of this study is to assess the ability of AI models to accurately identify dental pathologies and predict orthodontic treatment outcomes. Material and Methods: A survey using a 5-point Likert scale was conducted with 400 participants, including dentists, researchers, and dental students from Bangladesh, India, and the USA. Data were analyzed using descriptive statistics and Cronbach’s alpha, yielding a reliability score of 0.86. Results: The results indicated that AI models performed well, particularly in detecting bone loss, achieving an average score of 3.13, comparable to human diagnoses. However, variability was observed regarding radiograph quality, transparency of AI models, and their integration into clinical practice. Conclusion: AI shows promise in improving diagnostic accuracy, challenges related to data quality and clinical integration must be addressed for wider adoption in practice.

Fields of Study & Subjects

Dental Radiography and Imaging Artificial Intelligence in Healthcare and Education AI in cancer detection

Publication details

Journal / source
International Journal of Applied Dental Sciences
Volume
12
Issue
3
Pages
44–51
Publication date
1 March 2026
Language
EN