Predicting Local Anesthetic Success in Symptomatic Irreversible Pulpitis: A Machine Learning Study

This study will develop and internally validate three machine learning models - logistic regression, random forest, and XGBoost - to predict local anesthetic (LA) success in patients undergoing endodontic treatment for symptomatic irreversible pulpitis (SIP). A large retrospective cohort of 4,390 consecutive adult patients treated at a single center (May 2014-October 2025) is being analyzed. The dataset was frozen in October 2025 for this analysis.

Inclusion Criteria: * Adults (≥18 years) presenting with a clinical diagnosis of symptomatic irreversible pulpitis in a permanent tooth * Diagnosis confirmed on the basis of patient-reported symptoms (spontaneous pain, lingering pain to thermal stimuli), clinical examination, and positive pulp sensibility testing (cold test and/or electric pulp test) * Absence of radiographic evidence of periapical pathology * ASA physical status I or II * No prior local anesthetic injection for the same tooth within the preceding 24 hours * No documented allergy or contraindication to amide local anesthetics Exclusion Criteria: * ASA physical status classification III or higher * Pregnancy * Confirmed radiographic periapical lesion or diagnosis of pulp necrosis * Prior local anesthetic injection for the same tooth within the preceding 24 hours * Documented allergy or contraindication to amide local anesthetics * Age under 18 years * Records with missing key predictor or outcome variables (9.2% of initially screened records excluded)