What Is Normal? Multimodal Characterization Of Non-Diseased Pediatric Duodenal Biopsies Using Machine Learning Image Analysis And Transcriptomics
Chotani, A.; Liu, J.; Moradinasab, N.; Khan, S.; Sessions, J.; Rhoads, F.; Srivastava, S.; Zulqarnain, F.; Jain, V.; Raghavan, S.; Moskaluk, C.; Greene, A.; Marie, C.; Brown, D.; Syed, S.
Show abstract
Pediatric endoscopy is performed only when clinically indicated, limiting access to healthy duodenal tissue. Biopsies with duodenal no pathologic abnormality (NPA) are often used as controls despite the presence of symptoms or inflammatory disease found elsewhere in the gastrointestinal (GI) tract. We characterized pediatric duodenal NPA tissue across clinical, histologic, cellular, and transcriptomic domains. Methods Archival duodenal NPA biopsies were obtained with clinical metadata and hematoxylin-and-eosin whole-slide images (WSIs). Duodenal mRNA-seq data were analyzed from a subset of patients with duodenal NPA. Clinical metadata and WSIs underwent machine-learning analysis, cell populations were quantified from WSIs, and RNA-seq data underwent differential expression and pathway-enrichment analyses. Results The primary cohort included 195 patients with duodenal NPA. Comparisons between patients with non-duodenal GI disease and those with no GI disease showed differences in inflammatory biomarkers and follow-up utilization. Unsupervised clinical clustering identified three clusters with partial enrichment for IBD with colonic inflammation and Eosinophilic Esophagitis (EoE) with esophageal inflammation. Supervised clinical classification showed modest discrimination. WSI clustering showed limited disease-status discrimination, and cell quantification showed no significant group differences. In the separate RNA-seq cohort of 43 patients, differential-expression and pathway-enrichment analyses identified transcriptional and pathway-level differences between disease-status groups. Conclusions This multi-level characterization indicates that pediatric duodenal NPA tissue should not be treated as a uniform control category. Clinical metadata and transcriptomics revealed clinical and molecular heterogeneity, while histologic and cell analyses showed limited disease-status separation, supporting a refined definition of control tissue.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Intestinal barrier function in the naked mole-rat: an emergent model for gastrointestinal insights 91%
- Single-cell transcriptomics predict novel potential regulators of acute epithelial restitution in the ischemia-injured intestine 90%
- The RNA-binding protein Imp1 promotes a Spdef transcriptional program and mucus fucosylation during necrotizing enterocolitis 90%
Similar papers in this journal
Similar papers in this journal
- Deep learning-based approach for the characterization and quantification of histopathology in mouse models of colitis 92%
- High circulating elafin levels are associated with Crohn’s disease-associated intestinal strictures 91%
- Colonic mucosal associated invariant T cells in Crohn’s disease have a diverse and non-public T cell receptor beta chain repertoire 90%
Similar papers in this journal
- Aberrant miR-29 is a predictive feature of severe phenotypes in pediatric Crohn's disease 92%
- Microfluidic Device Facilitates Novel In Vitro Modeling of Human Neonatal Necrotizing Enterocolitis-on-a-Chip 92%
- Prebiotic proanthocyanidins inhibit bile reflux-induced esophageal adenocarcinoma through reshaping the gut microbiome and esophageal metabolome 90%
Similar papers in this journal
- Histopathologic Evaluation and Single-Cell Spatial Transcriptomics of the Colon Reveal Cellular and Molecular Abnormalities Linked to J-Pouch Failure in Patients with Inflammatory Bowel Disease. 91%
- Single-Cell Analysis Reveals Regional Reprogramming during Adaptation to Massive Small Bowel Resection in Mice 91%
- Loss of intestinal endosome associated protein sorting nexin 27 disrupts epithelial barrier and promotes inflammation 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.