EXPERTS ENDOSCOPISTS VS. ARTIFICIAL INTELLIGENCE IN THE EVALUATION OF UNDETERMINED BILIARY STRICTURES IN CHOLANGIOSCOPY: A MULTICENTER, BLINDED, NESTED CONTROLLED TRIAL

Aims Digital single-operator cholangioscopy (DSOC) findings achieve high diagnostic accuracy for neoplastic bile duct lesions; however, endoscopists’ intra and interobserver agreements vary widely. We have recently proposed an AI model to classify bile duct lesions during real-time DSOC and currently pursue clinical validation of our AI model, compared with high DSOC experienced endoscopists.

Methods Multi-center diagnostic trial. Four DSOC experts endoscopists (blinded to clinical records), observed and classified a set of videos among neoplastic or non-neoplastic bile duct lesions. All videos were blinded for DSOC experts and for the AI software (Mdconsgroup, Guayaquil, Ecuador). The neoplastic bile duct criteria are in accordance with the Robles-Medranda et al and the Mendoza classifications. The experts assessed neoplastic bile duct by presence or absence of disaggregated criteria. Likewise, the statistical software computed disaggregated answers. The final diagnosis of malignancy was based on histological results, and 1-year clinical follow-up outcomes. NCT05147389.

Results A total of 170 videos from 170 patients from 4 different centers were analyzed with the AI model. There was an equal distribution among neoplastic and non-neoplastic DOCS diagnosis (Table 1). DSOC AI software achieved statistically significant accuracy values (p<0.001) for neoplastic diagnosis with a≥90% sensitivity,≥68% specificity,≥65% positive and≥83% negative predictive values ([Figure 1]) when compared with endoscopist expert.

Table 1 Baseline data stratifi ed by neoplasia confi rmation during one-year follow-up.

	Total (N=170)	Neoplasia (N=85)	Non-neoplasia (N=85)
Age (years), median (IQR)	62.5 (57.0 – 68.8)	64.0 (59.0 – 71.0)	59.0 (52.0 – 65.0)
Gender (female), n (%)	79 (46.5)	45 (52.9)	34 (40.0)
Visual Impression – DOCS diagnosis, (%)
Non-Neoplasia	85 (50)	-	85 (100)
Neoplasia	85 (50)	85 (100)	-
Neoplasia Biospy diagnosis, (%)	154 (90.6)	85 (100)	-
Non-neoplasia Biospy diagnosis, (%)	16 (9.4)	-	85 (100)

Conclusions The proposed AI model accurately recognized between neoplastic and non-neoplastic bile duct lesions with good accuracy, being statistically significant over experts in DSOC. This model may shorten learning curves time in less experienced endoscopists, while attaining accurate biliary lesion recognition skills.

Fig. 1

Publication History

Article published online:
14 April 2022