evidencegaps
Primary study · included by 1 review

Development and Validation of a Non-Invasive, Chairside Oral Cavity Cancer Risk Assessment Prototype Using Machine Learning Approach.

Shimpi 2022 · Shimpi Neel, Glurich Ingrid, Rostami Reihaneh, et al. · Journal of personalized medicine · 2022

Included by

Artificial intelligence for oral cancer diagnosis: a systematic review and meta-analysis of image-based and non-imaging models.
Non-Cochrane · DTA;prognostic · 2026 · cited as Shimpi 2022 · Table 1; Figures 3-5
Outcome this study informsPooled effectEvidenceCertainty
Diagnostic accuracy
AI models for oral cancer diagnosis or risk assessment (image-based and text-based) vs Reference standard (histopathology where available, otherwise expert clinical diagnosis)
Pooled accuracy (proportion) 0.89 [0.83, 0.95]11 studiesGRADE not reported
Diagnostic specificity
AI models for oral cancer diagnosis or risk assessment (image-based and text-based) vs Reference standard (histopathology where available, otherwise expert clinical diagnosis)
Pooled specificity (proportion) 0.89 [0.84, 0.95]14 studiesGRADE not reported

1 including review in total.