•  
  •  
 

Journal of Innovation in Science, Engineering and Technology

Document Type

Original Study

Abstract

Dental caries (tooth decay) is one of the most common global oral health problems and remains a significant public health concern due to late diagnosis and inadequate access to dental care in many populations. This study proposes the design and development of an Artificial Intelligence (AI)-based mobile application for early detection of tooth decay using smartphone-captured oral images combined with questionnaire-based analysis. The proposed system employs a Convolutional Neural Network (CNN) to analyze tooth images and determine the presence and severity of dental caries. Users also complete a structured questionnaire comprising 14 questions related to oral hygiene habits, dietary practices, medications, and medical conditions. A hybrid scoring system, consisting of 60% image-based prediction and 40% questionnaire-derived risk evaluation, is used to generate the final tooth decay classification as healthy, early-stage decay, moderate decay, or severe decay. Experimental results demonstrated that integrating behavioral and medical risk factors with visual image analysis improved diagnostic reliability compared with image-only AI systems. The proposed hybrid system achieved an accuracy of 92.4%, precision of 91.2%, recall of 90.7%, and an F1-score of 90.9% and operates using standard smartphone cameras without requiring specialized dental equipment, making it a potentially affordable and accessible tool for preliminary dental screening and preventive care. The findings of this study contribute to the development of intelligent mobile health systems and may improve early diagnosis and remote oral healthcare, particularly in underserved communities

First Pages

36

Last Page

44

Download

Share

COinS