Microbiome-based prediction of allogeneic hematopoietic stem cell transplantation outcome Journal Article


Authors: Shtossel, O.; Eshel, A.; Fried, S.; Geva, M.; Danylesko, I.; Yerushalmi, R.; Shem-Tov, N.; Fein, J. A.; Fabbrini, M.; Shimoni, A.; Turjeman, S.; Louzoun, Y.; Nagler, A.; Koren, O.; Shouval, R.
Article Title: Microbiome-based prediction of allogeneic hematopoietic stem cell transplantation outcome
Abstract: Background: Allogeneic hematopoietic stem cell transplantation (HSCT) is potentially curative for hematologic malignancies but is frequently complicated by relapse and immune-mediated complications, such as graft-versus-host disease (GVHD). Emerging evidence suggests a role for the intestinal and oral microbiome in modulating HSCT outcomes, yet predictive models incorporating microbiome data remain limited. Methods: We applied the RATIO (suRvival Analysis lefT barrIer lOss) model to longitudinal stool and saliva microbiome data from 204 adult HSCT recipients to predict the timing of seven outcomes: overall survival (OS), non-relapse mortality (NRM), relapse, acute GVHD (grades II–IV and III–IV), chronic GVHD, and oral chronic GVHD. A total of 514 stool and 1291 saliva samples were collected over 70 weeks post-HSCT. Model performance was evaluated using the concordance index (CI) and Spearman correlation coefficient (SCC), with SHAP (SHapley Additive exPlanations) analysis used for model interpretability. Results: Oral and stool microbial dysbiosis peaked within the first 2 weeks post-HSCT, followed by partial recovery. Using the RATIO model, we found that microbiome features from early time points (weeks 1–2) were most predictive of short-term complications such as acute GVHD, while later samples (weeks 36–70) were more informative for long-term outcomes, including overall survival. RATIO outperformed traditional survival models (Cox and Random Survival Forest) across most outcomes (median CI > 0.65), with stool microbiota showing greater predictive power than saliva. SHAP analysis identified specific stool genera, including Collinsella and Eggerthella, associated with shorter time to various complications. External validation using a pediatric GVHD cohort confirmed the model’s generalizability and reproducibility. External validation using a pediatric HSCT cohort (n = 90) confirmed the reproducibility and generalizability of these microbiome-based predictions. Conclusions: Microbiome profiling of stool and saliva samples offers robust, time-sensitive prediction of post-HSCT complications. The RATIO model enables interpretable, time-to-event prediction across multiple outcomes and may inform microbiome-guided interventions to improve transplant success. © The Author(s) 2025.
Keywords: adult; controlled study; human tissue; treatment outcome; middle aged; survival analysis; major clinical study; overall survival; nonhuman; treatment duration; outcome assessment; sensitivity analysis; reproducibility; cohort analysis; hematopoietic stem cell transplantation; information processing; prediction; cancer mortality; intervention study; acute graft versus host disease; chronic graft versus host disease; data analysis; graft versus host reaction; allogeneic hematopoietic stem cell transplantation; disease duration; graft recipient; predictive value; feces analysis; longitudinal study; saliva analysis; external validity; graft-versus-host disease; time factor; machine learning; microbiome; human; male; female; article; dysbiosis; stool microbiome; ratio model; saliva microbiome; time-to-event analysis; collinsella; eggerthella
Journal Title: Genome Medicine
Volume: 17
ISSN: 1756994X
Publisher: The Author(s) 2025  
Date Published: 2025-07-17
Start Page: 80
Language: English
DOI: 10.1186/s13073-025-01507-8
PROVIDER: scopus
PMCID: PMC12273375
PUBMED: 40676635
DOI/URL:
Notes: Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Roni Shouval -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Roni Shouval
    170 Shouval