Development and validation of multivariable prognostic machine learning models to identify patients at risk for inadequate bowel preparation when undergoing colonoscopy: a prospective, multicentre study

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: AUC 0.71-0.74 across ML models

• Primary Outcome: Inadequate bowel preparation rate 16% (424/2652 patients)

• Nnt Or Sensitivity: Sensitivity 0.51-0.86, Specificity 0.52-0.83, NPV >0.9, NNE 8-10

• Confidence Interval: Not reported in abstract

Clinical Application

Models require demographic and clinical data collection, feasible in routine practice with electronic health records Relevant to Australian colonoscopy programs including National Bowel Cancer Screening Program, could inform quality improvement initiatives aligned with GESA guidelines Adult patients undergoing colonoscopy in hospital and outpatient settings

Abstract

OBJECTIVE: Inadequate bowel preparation impairs the accuracy of colonoscopy and increases the burden on patients and healthcare systems. Consequently, the quality of bowel preparation is an important quality indicator. We aim to develop and validate multivariable prognostic models for the identification of patients at risk of inadequate bowel preparation using machine learning (ML). METHODS: Demographic and clinical data from consecutive patients ≥18 years of age who underwent colonoscopy at six centres in Germany were prospectively collected. Adequate bowel preparation was defined as Boston Bowel Preparation Scale ≥6 with a value ≥2 in each colonic segment. We used statistical and ML methods to build prognostic models and to compare them to published models. RESULTS: Overall, we analysed 2652 patients, including 699 (26.4%) inpatient procedures. The mean patient age was 57.6 years (SD 16 years), and 48.9% were women. In 1401 (52.8%) patients, the indication was screening or surveillance, and 1035 (39%) patients had a first-time colonoscopy. The rate of inadequate bowel preparation was 16%. Sensitivities, specificities and areas under the curve of predictive models obtained by generalised boosting models, Ranger, support vector machine (radial), CatBoost and Net Regularised Generalised Linear Models were 0.51-0.86, 0.52-0.83 and 0.71-0.74, respectively. They were only marginally superior to a logistic regression model. All models had high negative predictive values >0.9 for inadequate bowel preparation. To detect one patient with inadequate bowel preparation, 8-10 patients need to be evaluated. CONCLUSIONS: Predictive models to identify patients at risk for inadequate bowel preparation obtained by ML showed comparable results compared with a logistic regression model. TRIAL REGISTRATION NUMBER: DRKS00018878.

References

1. 1.Schramm, C., Hehn, C., Curth, H., Scheller, I., Weingaertner, J. H., Reichert, M. C., Kasper, P., Bozal, D., Allo, G., Casper, M., Adams, T., Jochheim, L., Zeller, A., Rahe, G., Zeeh, J., Neumann-Haefelin, C., Lammert, F., Schmidt, H., Friedrich, C. M., & Buerger, M. (2026). Development and validation of multivariable prognostic machine learning models to identify patients at risk for inadequate bowel preparation when undergoing colonoscopy: a prospective, multicentre study. BMJ Open Gastroenterology, 13(1), e002238. https://doi.org/10.1136/bmjgast-2025-002238