Development and validation of the Open-Source Automatic Bowel Preparation Scale.

BACKGROUND AND AIMS

Insufficient bowel preparation accounts for up to 42% of missed adenomas in colonoscopy. However, major analysis programs found no correlation between adenoma detection rate and the human-rated Boston Bowel Preparation Scale (BBPS), indicating limitations of the scale. We therefore aimed to develop an Open-Source Automatic Bowel Preparation Scale (OSABPS) based on artificial intelligence that is correlated to the polyp detection rate.

METHODS

The OSABPS was trained on 50,000 frames from 20 colonoscopies from 3 hospitals. It involved quantifying the presence of fecal matter within the colonoscopy frames, using an approach termed the fecal ratio-the proportion of pixels identified as feces (F) relative to those identified as mucosal tissue (M) (OSABPS = F/M)-thereby making 0 the optimal score, indicating a perfect cleansing. The Youden J was used to set the threshold because it determines the optimal balance between sensitivity and specificity. The algorithm was then tested on 1405 colonoscopies from 3 hospitals (internal validation) and 5525 frames from a public colonoscopy database (Nerthus, external validation).

RESULTS

Internal validation: the OSABPS correlated significantly with the BBPS (Pearson r = -0.42, P < .001). A threshold of 0.09 OSABPS was determined using the Youden J. The polyp detection rate was higher for colonoscopies below the threshold of the Youden J (2-proportion z-test, P < .001). External validation: the OSABPS correlated significantly with the BBPS (Pearson r = -0.70, P < .001).

CONCLUSIONS

The OSABPS can automatically, instantly, and without human bias assess bowel preparation quality. Colonoscopies with an OSABPS of >0.09 should be considered for reexamination. The OSABPS's open-source nature allows free implementation.