Clinical Applications of AI in Contemporary Dentistry

— FDA regulatory pathways for AI/ML medical devices: 510(k) clearance, De Novo classification, and PMA approval

— The regulatory pathway most commonly used by dental AI/ML products

— Current landscape of FDA-cleared dental AI/ML products and the growth of the field

— What FDA clearance means for a dental AI product and what it does not guarantee about performance in individual clinical practice

— Clinical validation, intended use, and the importance of independent evaluation before integrating AI tools into practice.

— AI-assisted implant position planning based on CBCT data

— Automated segmentation of anatomical structures relevant to surgical planning, including the mandibular canal

— AI-assisted intraoral scanning and AI-supported CAD/CAM workflows for crowns, dentures, and digital smile design

— Clinical applications where AI can reduce chair time and areas where manual correction and clinician oversight remain necessary.

— Computer vision approaches for screening oral potentially malignant disorders (OPMD) using clinical photographs

— Current evidence on AI-based screening: promising sensitivity in controlled studies but limited real-world validation

— Clinical limitations of AI screening and the importance of specialist referral and biopsy when indicated

— Why a positive or negative AI screening result cannot replace definitive diagnosis by biopsy.

— Current evidence for AI in pediatric dental diagnostics, including caries detection and growth assessment

— Limitations of adult-trained AI models in pediatric and mixed-dentition cases

— Emerging AI applications for monitoring myofunctional therapy compliance, orthodontic treatment, and airway health in children

— Pediatric-specific considerations for informed consent and communication with minor patients and caregivers

— A pediatric-specific checklist for the critical appraisal of AI tools before clinical use.

— Automated cephalometric landmark identification and reported accuracy compared with manual tracing

— AI-assisted decision support for extraction versus non-extraction treatment

— Prognostic modeling and predictive analytics for treatment duration and outcomes

— Digital smile design and AI-assisted aligner treatment planning.

— AI-assisted detection and classification of periapical lesions and apical periodontitis on dental radiographs and CBCT

— AI-supported analysis of root canal anatomy, including curved, calcified, and complex canal systems

— Automated working length estimation and AI-assisted assessment of root canal morphology

— Detection and segmentation of endodontic findings, including missed canals, periapical pathology, and vertical root fractures

— AI-assisted treatment planning and decision support in primary and retreatment cases

— Current evidence, limitations, and clinical validation of AI tools in endodontics

— Where AI can support clinical decision-making and where independent clinician assessment remains essential.

— AI-assisted measurement of alveolar bone loss on dental radiographs

— AI-based classification and staging of periodontal disease

— Personalized homecare and oral hygiene recommendations based on the patient’s periodontal risk profile

— Detection and segmentation of periapical lesions and apical periodontitis

— AI-assisted detection of vertical root fractures

— Current clinical role of AI tools as decision-support systems rather than replacements for professional diagnosis.

— Deep learning for caries detection on bitewing and periapical radiographs

— Typical reported sensitivity ranges for AI-based caries detection

— FDA-cleared AI solutions for caries detection, including Pearl, Overjet, and VideaHealth

— Indications and findings each AI solution is cleared to flag

— Current evidence and limitations: risk of bias in published caries-detection studies

— Clinical interpretation of AI-generated findings and the importance of independent clinician review of the radiograph.