Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0258
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-18T06:20:06.648872Z
status: published
lens: g_space
sector: health
headline: Effect of AI-assisted caries annotation on dental students' performance in caries detection on panoramic radiographs
dek: Dental caries remains one of the most prevalent oral diseases globally. The integration of artificial intelligence (AI) into dental radiographic interpretation, particularly for caries detection, has expanded rapidly. AI-assisted caries annotation may help dental students identify carious lesions on panoramic radiographs-a commonly used diagnostic tool for evaluating teeth and surrounding structures-thereby improving diagnostic accuracy, efficiency, and confidence. This study aimed to assess the effect of AI-ass…
gain_title: AI-assisted caries annotation increased dental students' diagnostic accuracy, sensitivity, and confidence while reducing interpretation time on panoramic radiographs.
problem_title: (none)
trace_subject: (none)
gain_reading: AI-assisted caries annotation increased dental students' diagnostic accuracy, sensitivity, and confidence while reducing interpretation time on panoramic radiographs.
gain_evidence: Accuracy increased from 0.91 to 0.96, sensitivity from 0.35 to 0.67, specificity from 0.96 to 0.99 | mean diagnostic time per radiograph significantly decreased from 67.89 to 53.92 s | Students' confidence improved notably for enamel caries (4.0 to 6.0), dentin caries (5.0 to 7.0), and pulp-involved caries (8.0 to 8.5), as well as overall detection (5.0 to 7.0)
problem_reading: (none)
problem_evidence: (none)
quick_read: In a study published July 16, 2026, 40 fourth-year dental students interpreted 40 panoramic radiographs first without assistance and then one month later with AI-assisted caries annotation. The radiographs contained multistage lesions verified by bite-wing radiographs, and students recorded lesion location, depth, time, and confidence.

The results matter because panoramic interpretation is a core competency where students traditionally miss early lesions, and the observed gains in sensitivity and confidence suggest AI annotation could serve as an educational adjunct. What remains uncertain from the text is whether improvements persist without AI, transfer to real patient care, or generalize beyond the single institution and 40-student sample.
limitation: 
tag: Evidence-backed gain
key_points: Study used 50 panoramic radiographs with multistage carious lesions verified by bite-wing radiographs as the gold standard, with 40 used for testing. | 40 fourth-year dental students completed Session 1 on unannotated radiographs and Session 2 one month later with AI-assisted annotation. | Sensitivity rose from 0.35 to 0.67 and miss rate decreased from 0.65 to 0.33 with AI assistance. | Calibration included ten sets of unannotated and AI-annotated radiographs before testing.
rundown: The experiment was structured as two sessions one month apart using the same 40 radiographs, with location and depth of detected caries, diagnostic time, and self-reported confidence on a 0-10 scale recorded per radiograph.

Statistical comparison used paired t-tests or Wilcoxon tests and reported improvements across accuracy, balanced accuracy from 0.65 to 0.83, precision from 0.33 to 0.77, and negative predictive value from 0.95 to 0.98.
sources:
- peer_reviewed | BMC Medical Education | https://doi.org/10.1186/s12909-026-09950-w | 2026-07-16
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

dbdabbc1b9c3af5e2d5e4c360aea04666bfef37635c42f230e7f56e4ff51d9a4

previous

0000000000000000000000000000000000000000000000000000000000000000