Endodontic Technology · Microscope, CBCT 3D, MTA · Sunnyvale

AI: promise is not proof of patient benefit

Silicon Valley Endodontics editorial addition. Only the Swanson and Turgeon summaries in this addition were clinically reviewed by Dr. Jason Kung, DDS, MS, on September 30, 2026, in English and all seven translations. Other summaries are not covered by that review; review of these two summaries does not update the surrounding page's earlier clinical review.

Swanson and colleagues’ JADA perspective (2026;157(9):957–967) discusses bringing emerging technology, including potential AI applications, into care. The question is not simply whether a tool performs well in a study, but whether it improves outcomes that matter to patients. This is not an AI diagnostic-accuracy trial or proof of superior endodontic outcomes. Independent validation and clinical judgment remain important; this summary does not claim our practice uses diagnostic AI.

Swanson et al. JADA 2026;157(9):957–967.

New JOE evidence shows why an AI alert needs clinical interpretation. In Allihaibi’s commercial-platform study, tooth-level sensitivity was higher than clinicians’ (67.3% versus 49.3%), but specificity was lower (82.3% versus 92.5%): more possible findings, more false alarms. CBCT was the imaging reference, not proof that treatment failed. In Akyüz’s separate 60-case benchmark, chatbots missed important complications, including perforations and broken instruments. These studies do not demonstrate better healing.