Diagnostic Accuracy and Efficiency of AI-Assisted Radiographic Interpretation Compared to Conventional Methods in Early Detection of Dental Caries

Q: What was the objective of the study?

To assess and compare diagnostic accuracy and efficiency of AI-assisted radiographic interpretation versus conventional clinician-based evaluation for early detection of dental caries.

Q: How was the comparison between AI and clinicians performed?

A cross-sectional analytical study used 400 bitewing radiographs from 200 patients. Group A used conventional interpretation by three experienced clinicians, while Group B used a CNN-based AI software, with consensus diagnosis after clinical validation as the reference standard.

Q: Which method showed better diagnostic performance and time efficiency?

AI-assisted interpretation demonstrated significantly higher sensitivity (91.2% vs 84.6%) and higher overall diagnostic accuracy (89.4% vs 87.0%). Mean interpretation time was substantially lower with AI (21.5 seconds vs 48.2 seconds).

Sep 30, 2026

Uploaded by LangkahRina

Early detection of dental caries is essential for preventive management and for reducing the need for invasive interventions. Conventional radiographic interpretation by clinicians remains effective but suffers from inter-observer variability and diagnostic subjectivity. This cross-sectional analytical study evaluated whether AI-assisted interpretation improves diagnostic accuracy and efficiency. Using 400 bitewing radiographs from 200 patients, AI based on a convolutional neural network was compared with three experienced clinicians against a consensus reference standard.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages3

Reading Time8 min

AccessFree to download

Abstract

Background

Objective

Methods

Results

Conclusion

Introduction

Materials and Methods

Original Research Diagnostic Accuracy and Efficiency of AI‑Assisted Radiographic Interpretation Compared to Conventional Methods in Early Detection of Dental Caries Hardikkumar B. Patel1, Jasmine Marwaha2, Nidhi Hirani3, Pratik Suthar4, Ashtha Arya5, Neetu Pandey6 1Department of Conservative Dentistry and Endodontics, Siddhpur Dental College and Hospital, Siddhpur, Gujarat, India, 2Department of Conservative Dentistry and Endodontics, National Dental College and Hospital, Derabassi, Punjab, India, 3Department of Oral Medicine and Radiology, Government Dental College and Hospital, Jamnagar, Gujarat, India, 4Department of Conservative Dentistry and Endodontics, Ahmedabad Dental College, Ahmedabad, Gujarat, India, 5Department of Conservative Dentistry and Endodontics, SGT Dental College, Hospital and Research Institute, SGT University, Gurugram, Haryana, India, 6Department of Oral Medicine and Radiology, Mansarovar Dental College, Bhopal, Madhya Pradesh, India Submitted: 22‑Jul‑2025 Revised: 28‑Jul‑2025 Accepted: 12‑Aug‑2025 Published: 17‑Dec‑2025 Abstract Background: Early detection of dental caries is critical for implementing preventive measures and avoiding invasive treatments. Traditional radiographic interpretation by clinicians, though effective, is prone to variability. Artificial intelligence (AI)‑assisted interpretation has emerged as a promising adjunct. Objective: To assess and compare the diagnostic accuracy and efficiency of AI‑assisted radiographic interpretation with conventional clinician‑based evaluation in the early detection of dental caries. Methods: A cross‑sectional analytical study was conducted on 400 bitewing radiographs from 200 patients aged 18–40 years. Two groups were compared: Group A (conventional method) with three experienced clinicians, and Group B (AI‑assisted method) using a convolutional neural network (CNN)‑based software. The reference standard was consensus diagnosis after clinical validation. Diagnostic performance was evaluated using sensitivity, specificity, accuracy, and time‑efficiency metrics. Results: AI‑assisted interpretation showed significantly higher sensitivity (91.2% ± 3.5) than conventional interpretation (84.6% ±4.2; P = 0.01) . Specificity was marginally better in the conventional group (89.5% ±3.1) compared to AI‑assisted (87.1% ± 2.9; P = 0.14) . Overall diagnostic accuracy was higher in the AI group (89.4% ± 3.2 vs. 87.0% ±3.6; P = 0.04) . Mean interpretation time was significantly lower in the AI group (21.5 ± 5.3 seconds) than in the clinician group (48.2 ± 6.7 seconds; P < 0.001) . Conclusion: AI‑assisted radiographic interpretation demonstrated superior diagnostic accuracy and markedly improved efficiency compared to conventional methods in early caries detection. AI tools can serve as reliable diagnostic adjuncts, enhancing clinical workflow and reducing diagnostic variability. Keywords: AI assisted, caries, dental AI Introduction Dental caries remains one chronic diseases globally, of the most prevalent with significant public health implications. Early diagnosis plays a crucial role in reversing or arresting lesion progression through non‑invasive strategies. Traditional detection techniques primarily rely on clinical examination and radiographic interpretation by trained professionals.[1] Despite their widespread use, conventional radiographic evaluations can be limited by inter‑observer variability | Access this article online | | | --- | --- | | Quick Response Code:
| Website: [https://journals.lww.com/jpbs](https://journals.lww.com/jpbs) | | | DOI: 10.4103/jpbs.jpbs_1278_25 | and diagnostic subjectivity.[2] To overcome these limitations, recent advances in artificial intelligence (AI) and machine learning have led to the development of automated diagnostic tools. AI systems, particularly those utilizing convolutional neural networks (CNNs), | Address for correspondence: Dr. Hardikkumar B. Patel, Department of Conse

FAQs

What was the objective of the study?

To assess and compare diagnostic accuracy and efficiency of AI-assisted radiographic interpretation versus conventional clinician-based evaluation for early detection of dental caries.

How was the comparison between AI and clinicians performed?

A cross-sectional analytical study used 400 bitewing radiographs from 200 patients. Group A used conventional interpretation by three experienced clinicians, while Group B used a CNN-based AI software, with consensus diagnosis after clinical validation as the reference standard.

Which method showed better diagnostic performance and time efficiency?

AI-assisted interpretation demonstrated significantly higher sensitivity (91.2% vs 84.6%) and higher overall diagnostic accuracy (89.4% vs 87.0%). Mean interpretation time was substantially lower with AI (21.5 seconds vs 48.2 seconds).

Sep 30, 2026

Uploaded by LangkahRina