Digital stool color screening for biliary atresia—Comparing a deep learning approach to the analogue stool color card
Journal of Pediatric Gastroenterology and Nutrition · 29.10.2026
DOI: 10.1002/jpn3.70615 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Pediatric Gastroenterology and Nutrition, online erschienen am 29.10.2026. Verfasst von Lucas Griessmair und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatric Gastroenterology, Nephrology and Metabolic Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stiftung Charité.
Abstract (Originalsprache)
Objectives
Early diagnosis of Biliary atresia (BA) improves native liver and overall survival. Pale stools are a characteristic symptom and might be detected by deep learning image recognition. We tested convolutional neural networks (CNNs) to classify pictures of pale and healthy stools and compare the results with stool color card (SCC) assessment of health care professionals (HCP) and non‐health care professionals (NHCP).
Methods
One thousand six hundred and sixteen stool photos with diagnostic labels including BA and healthy controls were graded as pale or normal according to the SCC. A subset of photos (33 BA and 241 healthy) was presented to HCP and NHCP for SCC assessment to evaluate accuracy and interobserver reliability. For CNN model selection and training all images were split into training, validation, and test sets. Different visualization strategies and secondary data augmentation were used for explainability and estimating robustness.
Results
In SCC assessment, sensitivity by NHCP trended lower than HCP (86.4% vs. 97.3%), while there were no differences in specificity. Intra‐cohort agreement on classification of BA stools (pale vs. normal) was also lower for NHCP than for HCP (36.4% vs. 78.8%), while no significant difference was observed in healthy stools. The selected CNN (ResNet18) correctly classified 97.5% of pale and 98.5% of normal labeled stools, also showing robust results in explainability methods.
Conclusions
The high accuracy of CNN shows the potential for a digital stool color screening. In contrast, NHCP assessment of pale stools tends to be inconsistent, and there is high interobserver variability among HCP and NHCP.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pediatric Gastroenterology, Nephrology and Metabolic Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany.
- Center for Biomedical Image and Information Processing (CBMI), HTW Berlin, Berlin, Germany.
- Paediatric Surgery and Urology, University Children's Hospital Tübingen, Tübingen, Germany.
- University Children's Hospital Regensburg (KUNO), Regensburg, Germany.
- Department of Pediatric Gastroenterology, Hepatology, and Transplant Medicine, Essen University Hospital, Essen, Germany.
- Dr. von Hauner Children's Hospital, University Hospital, LMU, Munich, Germany.
ORCID-Profile: Lucas Griessmair
Förderung
- Stiftung Charité
Zitieren
APA
Griessmair, L., Krumnow, C., Slavetinsky, C., Grothues, D., Lainka, E., Kathemann, S., Lurz, E., Bührer, C., Madadi-Sanjani, O., Petersen, C., Overberg, J., Henning, S., Weber, B., Kalveram, L., Hufnagl, P., Hudert, C., & Bufler, P. (2026). Digital stool color screening for biliary atresia—Comparing a deep learning approach to the analogue stool color card. Journal of Pediatric Gastroenterology and Nutrition. https://doi.org/10.1002/jpn3.70615
Vancouver
Griessmair L, Krumnow C, Slavetinsky C, Grothues D, Lainka E, Kathemann S, et al. Digital stool color screening for biliary atresia—Comparing a deep learning approach to the analogue stool color card. Journal of Pediatric Gastroenterology and Nutrition. 2026. doi:10.1002/jpn3.70615
BibTeX
@article{Griessmair2026,
author = {Griessmair, Lucas and Krumnow, Christian and Slavetinsky, Christoph and Grothues, Dirk and Lainka, Elke and Kathemann, Simone and Lurz, Eberhard and Bührer, Christoph and Madadi-Sanjani, Omid and Petersen, Claus and Overberg, Johanna and Henning, Stephan and Weber, Benedikt and Kalveram, Laura and Hufnagl, Peter and Hudert, Christian and Bufler, Philip},
title = {Digital stool color screening for biliary atresia—Comparing a deep learning approach to the analogue stool color card},
journal = {Journal of Pediatric Gastroenterology and Nutrition},
year = {2026},
doi = {10.1002/jpn3.70615}
}
EUVIMED