AI-assisted assessment of bowel preparation from patient-generated images for pre-procedure triage.
AI model distinguished inadequate from adequate bowel preparation using patient-submitted toilet photos
AI-assisted assessment of bowel preparation from patient-generated images for pre-procedure triage.
Inadequate bowel preparation before colonoscopy or colorectal surgery can delay procedures, require repeat preparation, and increase clinical workload.
To develop and explore the feasibility of an AI-assisted pre-procedure triage model that classifies bowel-preparation adequacy from patient-generated toilet images to support pre-colonoscopy assessment.
A total of 1,508 patient-generated toilet images were retrospectively collected from colorectal surgery patients at a tertiary hospital (Aug 2019–Feb 2023).
correctly told adequate from inadequate prep most of the time
To avoid within-patient correlation, we retained one image per patient, excluding 490 images from patients with multiple submissions, resulting in 1,018 images from 1,018 unique patients.
A DenseNet-201 model incorporating a Feature Pyramid Network (Feature Pyramid Network) for multi-scale feature representation was trained to classify bowel preparation as clean or not clean.
Grad-CAM visualization showed attention focused on residual stool and water turbidity, consistent with clinician interpretation.
Ablation analysis indicated incremental improvements from random oversampling, smoothing weight decay, and Feature Pyramid Network integration.
Further studies should validate the model prospectively and evaluate its integration into clinical workflow.