Machine Learning Model for Predicting Postoperative Pain in Cases of Irreversible Pulpitis
Machine-Learning-Modell zur Vorhersage postoperativer Schmerzen bei irreversibler Pulpitis
International Endodontic Journal · 2026-02
DOI: 10.1111/iej.70106 ↗Auf einen Blick
Bei 354 Patient:innen wurden überwachte Machine-Learning-Modelle zur Vorhersage postoperativer Schmerzen nach endodontischer Behandlung entwickelt und validiert. Die besten Ergebnisse zeigten Logistische Regression nach 24 h und Support Vector Machine nach 72 h.
Fragestellung
Lassen sich postoperative Schmerzen nach endodontischer Behandlung bei irreversibler Pulpitis mit überwachten Machine-Learning-Modellen vorhersagen?
Methode
Prospektive Analyse von 354 Patient:innen aus randomisierten klinischen Studien; 70 % Trainings- und 30 % Testsatz; 8 Algorithmen; SMOTE, Grid Search und stratified five-fold Cross Validation.
Ergebnisse
Logistische Regression: 24 h AUC 0,74 (95 %-KI 0,61–0,85), Precision 0,81 (95 %-KI 0,73–0,88). Support Vector Machine: 72 h AUC 0,81 (95 %-KI 0,69–0,92), Precision 0,88 (95 %-KI 0,79–0,94).
Schlussfolgerung der Autor:innen
Überwachte Machine-Learning-Modelle zeigten eine vielversprechende Leistung zur Vorhersage postoperativer Schmerzen nach endodontischer Behandlung. Logistische Regression und Support Vector Machine waren am konsistentesten.
Kernaussagen
- AUC 0,74 nach 24 h für Logistische Regression
- AUC 0,81 nach 72 h für Support Vector Machine
- Alter und Geschlecht waren die wichtigsten Prädiktoren
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift International Endodontic Journal, 2026-02. Verfasst von Pedro Felipe de Jesus Freitas und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Dentistry, Tuiuti University of Paraná, Curitiba, Brazil. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Schmerzmanagement, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Aim
Postoperative pain is a frequent clinical concern following endodontic treatment. This study aimed to develop and validate supervised machine learning models to predict the occurrence of postoperative pain in cases of irreversible pulpitis. Methodology A prospective sample of 354 patients aged 18 to 60 years undergoing standardised endodontic treatment was analysed. In the original randomised clinical trials from which the data were derived, each patient had only one eligible tooth included. Clinical variables included postoperative pain at 24 and 72 h, treated tooth group, occlusal reduction, photobiomodulation therapy, use of non‐steroidal anti‐inflammatory drugs (NSAIDs), sex and age. Eight supervised machine learning algorithms were trained to predict pain occurrence, including Logistic Regression, Support Vector Machine, Gradient Boosting, Random Forest, Decision Tree, K‐Nearest Neighbours, AdaBoost and Multilayer Perceptron. The dataset was divided into training (70%) and testing (30%) sets using stratified sampling. Class imbalance in the training set, characterised by a lower proportion of cases with moderate or severe pain, was addressed using the Synthetic Minority Oversampling Technique. Hyperparameters were optimised through grid search combined with stratified five‐fold cross validation. Model performance was evaluated using the area under the curve (AUC), accuracy, precision, recall and F1‐score, with 95% confidence intervals estimated by bootstrapping.
Results
The predictive models achieved good discrimination of pain outcomes. Logistic Regression showed the best test performance at 24 h (AUC 0.74 [95% CI: 0.61 to 0.85], precision 0.81 [95% CI: 0.73 to 0.88]). At 72 h, the Support Vector Machine achieved the highest performance (AUC 0.81 [95% CI: 0.69 to 0.92], precision 0.88 [95% CI: 0.79 to 0.94]). Age and sex emerged as the most influential predictors across models.
Conclusions
Supervised machine learning models demonstrated promising performance for predicting postoperative pain following endodontic treatment. Logistic Regression and Support Vector Machine algorithms presented the most consistent results, supporting their potential clinical application for personalised pain management.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Dentistry, Tuiuti University of Paraná, Curitiba, Brazil.
- School of Dentistry, Federal University of Amazonas, Manaus, Amazonas, Brazil.
- Post-Graduation Program in Health and Environment, University of Joinville (Univille), Joinville, Santa Catarina, Brazil.
- Department of Restorative Dentistry, Dental School of Ribeirão Preto, University of São Paulo, São Paulo, Brazil.
ORCID-Profile: Pedro Felipe de Jesus Freitas, Thalita de Paris Matos, Flares Baratto-Filho, Bianca Marques de Mattos de Araujo, Manoel Damião Sousa-Neto, Leandro de Moura Martins, Fernando José Herkrath, Emílio Carlos Sponchiado-Júnior, Cristiano Miranda de Araujo
Zitieren
APA
Freitas, P. F. J., Cunha, I. L. M., Matos, T. P., Baratto-Filho, F., de Araujo, B. M. M., Sousa-Neto, M. D., Martins, L. M., Herkrath, F. J., Sponchiado-Júnior, E. C., & de Araujo, C. M. (2026). Machine Learning Model for Predicting Postoperative Pain in Cases of Irreversible Pulpitis. International Endodontic Journal. https://doi.org/10.1111/iej.70106
Vancouver
Freitas PFJ, Cunha ILM, Matos TP, Baratto-Filho F, de Araujo BMM, Sousa-Neto MD, et al. Machine Learning Model for Predicting Postoperative Pain in Cases of Irreversible Pulpitis. International Endodontic Journal. 2026. doi:10.1111/iej.70106
BibTeX
@article{Freitas2026,
author = {Freitas, Pedro Felipe de Jesus and Cunha, Ingrid Luiza Mendonça and Matos, Thalita de Paris and Baratto-Filho, Flares and de Araujo, Bianca Marques de Mattos and Sousa-Neto, Manoel Damião and Martins, Leandro de Moura and Herkrath, Fernando José and Sponchiado-Júnior, Emílio Carlos and de Araujo, Cristiano Miranda},
title = {Machine Learning Model for Predicting Postoperative Pain in Cases of Irreversible Pulpitis},
journal = {International Endodontic Journal},
year = {2026},
doi = {10.1111/iej.70106}
}
EUVIMED