Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps

Incomplete reporting has been identified as a major source of avoidable waste in biomedical research. Essential information is often not provided in study reports, impeding the identification, critical appraisal, and replication of studies. To improve the quality of reporting of diagnostic accuracy studies, the Standards for Reporting Diagnostic Accuracy (STARD) statement was developed. Here we present STARD 2015, an updated list of 30 essential items that should be included in every report of a diagnostic accuracy study. This update incorporates recent evidence about sources of bias and variability in diagnostic accuracy and is intended to facilitate the use of STARD. As such, STARD 2015 may help to improve completeness and transparency in reporting of diagnostic accuracy studies.

Few bowel-preparation rating scales have been validated. Most scales were intended for comparing oral purgatives and fail to account for washing and/or suctioning by the endoscopist. This limits their utility in studies of colonoscopy outcomes, such as polyp-detection rates. To develop a valid and reliable scale for use in colonoscopy outcomes research. Academic medical center. We developed the Boston bowel preparation scale (BBPS), a 10-point scale that assesses bowel preparation after all cleansing maneuvers are completed by the endoscopist. We assessed interobserver and intraobserver reliability by using video footage of colonoscopies viewed on 2 separate occasions by 22 clinicians. We then applied the BBPS prospectively during screening colonoscopies and compared BBPS scores with clinically meaningful outcomes, including polyp-detection rates and procedure times. The intraclass correlation coefficient (a measure of interobserver reliability) for BBPS scores was 0.74. The weighted kappa (a measure of intraobserver reliability) for scores was 0.77 (95% CI, 0.66-0.87). During 633 screening colonoscopies, the mean (SD) BBPS score was 6.0 +/- 1.6. Higher BBPS scores (> or =5 vs <5) were associated with a higher polyp-detection rate (40% vs 24%, P < .02). BBPS scores were inversely correlated with colonoscope insertion (r = -0.16, P < .003) and withdrawal (r = -0.23, P < .001) times. Single-center study. The BBPS is a valid and reliable measure of bowel preparation. It may be well suited to colonoscopy outcomes research because it reflects the colon's cleanliness during the inspection phase of the procedure.