GraftIQ: Hybrid multi-class neural network integrating clinical insight for multi-outcome prediction in liver transplant recipients

Divya Sharma, Neta Gotlieb, Daljeet Chahal, Joseph C. Ahn, Bastian Engel, Richard Taubert, Eunice Tan, Lau Kai Yun, Sara Naimimohasses, Ankit Ray, Yoojin Han, Sara Gehlaut, Maryam Shojaee, Surabie Sivanendran, Maryam Naghibzadeh, Amirhossein Azhie, Sareh Keshavarzi, Kai Duan, Leslie Lilly, Nazia Selzner, Cynthia Tsien, Elmar Jaeckel, Wei Xu and Mamatha Bhat ()
Additional contact information
Divya Sharma: University Health Network
Neta Gotlieb: University of Ottawa
Daljeet Chahal: University of British Columbia
Joseph C. Ahn: Division of Gastroenterology and Hepatology at Mayo Clinic
Bastian Engel: Hannover Medical School
Richard Taubert: Hannover Medical School
Eunice Tan: National University Hospital
Lau Kai Yun: National University Hospital
Sara Naimimohasses: University Health Network
Ankit Ray: University Health Network
Yoojin Han: University Health Network
Sara Gehlaut: University Health Network
Maryam Shojaee: University Health Network
Surabie Sivanendran: University Health Network
Maryam Naghibzadeh: University Health Network
Amirhossein Azhie: University Health Network
Sareh Keshavarzi: University Health Network
Kai Duan: University Health Network
Leslie Lilly: University Health Network
Nazia Selzner: University Health Network
Cynthia Tsien: University Health Network
Elmar Jaeckel: University Health Network
Wei Xu: University Health Network
Mamatha Bhat: University Health Network

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Liver transplant recipients (LTRs) are at risk of graft injury, leading to cirrhosis and reduced survival. Liver biopsy, the diagnostic gold standard, is invasive and risky. We developed a hybrid multi-class neural network (NN) model, ‘GraftIQ,’ integrating clinician expertise for non-invasive graft pathology diagnosis. Biopsies from LTRs (1992–2020) were classified into six categories using demographic, clinical, and lab data from 30 days pre-biopsy. The dataset (5217 biopsies) was split 70/30 for training/testing, with external validation at Mayo Clinic, Hannover Medical School, and NUHS Singapore. Bayesian fusion was used to combine clinician-derived probabilities with NN predictions, improving performance. Here we show that GraftIQ (MulticlassNN+clinical insight) achieved an AUC of 0.902 (95% CI:0.884–0.919), up from 0.885 with NN alone. Internal and external validation demonstrated 10–16% higher AUC than conventional ML models. GraftIQ demonstrates high accuracy in identifying graft etiologies and offers a valuable clinical decision support tool for LTRs.

Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-59610-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-59610-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-59610-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().