Cytokine Signatures Outperform Immune Subsets in Machine Learning Models for Predicting Acute Graft‐Versus‐Host Disease at Neutrophil Engraftment
Journal of Immunology Research · 2026-01 · 2026 (1)
DOI: 10.1155/jimr/1066614 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Immunology Research, online erschienen am 23.02.2026. Verfasst von Mohini Mendiratta und 21 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Oncology, Dr. B. R. Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences, New Delhi, Delhi, India…. Hauptthemen laut MEDLINE: Graft vs Host Disease, Cytokines, Hematopoietic Stem Cell Transplantation, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Indian Council of Medical Research.
Abstract (Originalsprache)
Background
Acute graft‐versus‐host disease (aGvHD) is a major immune complication of allogeneic hematopoietic stem cell transplantation (Allo‐HSCT), driven by complex immune‐cytokine interactions. This study employed machine learning (ML) algorithms to develop early predictive models for aGvHD using immune and cytokine profiles of Allo‐HSCT recipients at the time of engraftment. Materials and Methods Seventy patients with hematological disorders undergoing their first Allo‐HSCT were recruited prospectively. Peripheral blood immune subsets and cytokines were analyzed using flow cytometry and ELISA, respectively. ML models, including support vector classifier (SVC), decision tree, and random forest, were trained on 48 features: 34 immune subsets and 14 cytokines.
Results
Patients who developed aGvHD exhibited a reduced CD4 + /CD8 + ratio, lower Tregs, elevated Th1, Th17, cytotoxic natural killer (NK) cells, dendritic cells (DCs), B cell, and increased proinflammatory cytokines (IFN‐γ, IL‐1β, IP‐10, TNF‐α, IL‐17α, IL‐12p70, MIP‐1α, MIP‐1β, and RANTES). ML models demonstrated excellent predictive performance, with cytokine profiles alone or combined with immune data achieving perfect accuracy (1.00), followed by T‐cell (0.96), NK cell (0.93), DC (0.90), and B cell (0.86) models.
Conclusion
Cytokine profiles emerged as superior predictors over immune subsets, supporting their integration into ML‐based aGvHD risk prediction. These findings provide a foundation for developing biomarker‐guided strategies for early aGvHD detection and management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Medical Oncology, Dr. B. R. Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences, New Delhi, Delhi, India, aiims.edu.
- Indraprastha Institute of Information Technology, New Delhi, Delhi, India, iiitd.ac.in.
- Laboratory Oncology Unit, Dr. B. R. Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences, New Delhi, Delhi, India, aiims.edu.
- Stem Cell Facility (DBT-Centre of Excellence for Stem Cell Research), All India Institute of Medical Sciences, New Delhi, Delhi, India, aiims.edu.
- Amity Centre for Translational Research, Amity University, Sector 125, Noida, Uttar Pradesh, India, amity.edu.
- Department of Gastroenterology and Human Nutrition, All India Institute of Medical Sciences, New Delhi, Delhi, India, aiims.edu.
ORCID-Profile: Mohini Mendiratta, Sandeep Rai, Meenakshi Mendiratta, Sachin Kumar, Aditya Kumar Gupta, Tulika Seth, Ranjit Kumar Sahoo
Förderung
- Indian Council of Medical Research
Zitieren
APA
Mendiratta, M., Pandey, P., Pandey, S., Rai, S., Mendiratta, M., Prakash, H., Ganguly, S., Sasi, A., Gupta, R., Malik, P. S., Pramanik, R., Kumar, S., Nayak, B., Mir, R. A., Bakhshi, S., Pushpam, D., Aggarwal, M., Gupta, A. K., Dhawan, R., …, & Sahoo, R. K. (2026). Cytokine Signatures Outperform Immune Subsets in Machine Learning Models for Predicting Acute Graft‐Versus‐Host Disease at Neutrophil Engraftment. Journal of Immunology Research, 2026(1). https://doi.org/10.1155/jimr/1066614
Vancouver
Mendiratta M, Pandey P, Pandey S, Rai S, Mendiratta M, Prakash H, et al. Cytokine Signatures Outperform Immune Subsets in Machine Learning Models for Predicting Acute Graft‐Versus‐Host Disease at Neutrophil Engraftment. Journal of Immunology Research. 2026;2026(1). doi:10.1155/jimr/1066614
BibTeX
@article{Mendiratta2026,
author = {Mendiratta, Mohini and Pandey, Praful and Pandey, Shobhit and Rai, Sandeep and Mendiratta, Meenakshi and Prakash, Hridayesh and Ganguly, Shuvadeep and Sasi, Archana and Gupta, Ritu and Malik, Prabhat Singh and Pramanik, Raja and Kumar, Sachin and Nayak, Baibaswata and Mir, Riyaz Ahmed and Bakhshi, Sameer and Pushpam, Deepam and Aggarwal, Mukul and Gupta, Aditya Kumar and Dhawan, Rishi and Seth, Tulika and Mahapatra, Manoranjan and Sahoo, Ranjit Kumar},
title = {Cytokine Signatures Outperform Immune Subsets in Machine Learning Models for Predicting Acute Graft‐Versus‐Host Disease at Neutrophil Engraftment},
journal = {Journal of Immunology Research},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/jimr/1066614}
}
EUVIMED