Introduction

Dental caries is a significant global health concern. Early and accurate diagnosis is critical to prevent its progression and to alleviate the risk of associated complications such as pulpitis and abscess formation. The recent development in the field of artificial Intelligence (AI) to diagnose dental caries from the radiographs has contributed towards enhanced accuracy and efficiency for diagnosing dental caries.

Aim

To comparing the diagnostic accuracy of AI‑based software with human interpretation for detecting dental caries using intraoral radiographs. 

Patient Profile 

Methods

Study Design

Intraoral Radiographs 

AI-Based Software & Human Interpretation

• A deep learning algorithm-based AI software designed to detect dental caries from the radiographs was developed and used for this study.
• The radiographs were also independently evaluated by experienced dentists (considered as gold standard for comparison).
• Sensitivity, specificity, and overall accuracy were calculated to compare the performance of both AI and human interpretations. Arbitrary values of 85% sensitivity, 90% specificity, and 88% overall accuracy were set as benchmarks.

Results

• The AI‑based software demonstrated a sensitivity of 88%, a specificity of 91%, and an overall accuracy of 89% for diagnosing dental caries using the intraoral radiographs. 
• With regards to human interpretation, the sensitivity, specificity and overall accuracy were 84%, 88%, and 86%, respectively. 
• The performance of AI closely met or exceeded the arbitrary benchmark values of 85% sensitivity, 90% specificity, and 88% overall accuracy, indicating it to be an effective diagnostic tool. 
• Human interpretation showed good diagnostic accuracy, nevertheless, it slightly trailed behind the AI‑based software in terms of sensitivity, specificity, and overall accuracy.

Conclusions

• The AI‑based software is a valuable tool for diagnosing dental caries from intraoral radiographs. The performance of AI was comparable to or exceeded that of experienced human dentists. 
• The consistent accuracy of AI in this context underscores its potential as an adjunctive diagnostic tool, to aid dental professionals in more precise caries detection.

J Pharm Bioall Sci 2024;16:S812-4.