Pain after post-operative root canal therapy is an ever-present clinical concern influenced by multiple patient-related, procedural, and biological factors. Traditionally, clinicians have attempted to predict the occurrence and degree of occurrence of pain based on clinical experience, radiographic findings, and presenting symptoms, but all these methods have had a minimum level of inaccuracy. With the development of artificial intelligence, new AI-based predictive models are being created to augment the accuracy of in silico outcome-endodontic assessment. Systems of AI, which could be machine learning or deep learning, have the capabilities to go through very large, comprehensive datasets that consist of preoperative clinical features, imaging data, operator variables, and biological markers, finding certain patterns and linking them to post-operative pain. From the existing scenario, it is evident that AI can offer suspicious stratification tools for the clinician, thus improving treatment planning and the evolution of individualized patient care. This manuscript looks at the roles of AI in assessing post-operative pain after an RCT, discussing the potential concerns, benefits, and limitations, and also indicating the need for further validation and incorporation into clinical practice.
Artificial intelligence, Machine learning, Deep learning, Post-operative pain, Root canal therapy, Endodontics, Predictive modeling, Personalized dentistry, Risk assessment.
IRE Journals:
Francesco Rossi "AI Prediction of Post-Operative Pain in Root Canal Therapy" Iconic Research And Engineering Journals Volume 5 Issue 9 2022 Page 782-788 https://doi.org/10.64388/IREV5I9-1710593-4169
IEEE:
Francesco Rossi
"AI Prediction of Post-Operative Pain in Root Canal Therapy" Iconic Research And Engineering Journals, 5(9) https://doi.org/10.64388/IREV5I9-1710593-4169