Can AI predict full pulpotomy outcomes?

A machine-learning approach could help uncover endodontic and postoperative outcomes in patients with symptomatic irreversible pulpitis.

In a retrospective study published in the Journal of Endodontics, researchers developed machine-learning models to predict treatment success, postoperative pain and analgesic use in patients with symptomatic irreversible pulpitis who underwent full pulpotomy across more than 200 permanent molars.

After a minimum follow-up of two years, the researchers found that the machine-learning models — particularly the logistic regression model and a variable of bleeding time — demonstrated a modest discriminative ability in predicting treatment success. However, the artificial intelligence models were not as effective in predicting postoperative pain and analgesic use.

The researchers concluded that the machine-learning models may aid in the risk stratification of permanent molars with symptomatic irreversible pulpitis, but clinicians should avoid using the models for decision-making.

Read more: Journal of Endodontics

The article presented here is intended to inform you about the broader media perspective on dentistry, regardless of its alignment with the ADA's stance. It is important to note that publication of an article does not imply the ADA's endorsement, agreement, or promotion of its content.