REAL-TIME COMPUTER AIDED DETECTION-ASSISTED COLONOSCOPY ELIMINATES DIFFERENCES IN ADENOMA DETECTION RATE BETWEEN TRAINEE AND EXPERIENCED ENDOSCOPISTS

Aims Adenoma detection rate (ADR) is a well-accepted quality indicator of screening colonoscopy. In recent years, artificial intelligence (AI) showed its added value in terms of ADR and adenoma miss rate (AMR). To date, there are no studies evaluating the impact of AI on the performance of trainee endoscopists (TE). Aim of this study was to evaluate whether AI may eliminate any difference in ADR or AMR between TE and experienced endoscopists (EE).

Methods We performed a prospective observational study in 45 subjects referred for screening colonoscopy. A same-day tandem examination was carried out for each patient by a TE with the AI assistance and subsequently by an EE unaware of the lesions detected by the TE. Besides ADR and AMR, we also calculated for each subgroup of endoscopists the adenoma per colonoscopy (APC), the polyp detection rate (PDR), the polyp per colonoscopy (PPC) and the polyp miss rate (PMR). Sub-analyses according to size, morphology and site were performed.

Fig. 1

Results ADR, APC, PDR, and PPC of AI-supported TE were 38%, 0.93, 62%, 1.93, respectively. The corresponding parameters for EE were 40%, 1.07, 58%, 2.22. No significant difference was found for each analysis between the two groups (ρ>0.05). AMR and PMR for AI-assisted TE were 12.5% and 13%. Sub-analyses did not show any significantly difference (ρ>0.05).

Conclusions In this monocenter prospective study, AI showed its possible impact on the endoscopists’ quality training. In the future, this could result in better efficacy of screening colonoscopy by reducing the incidence of interval or missed cancers.

Publication History

Article published online:
14 April 2022