GraftIQ: Hybrid multi-class neural network integrating clinical insight for multi-outcome prediction in liver transplant recipients
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.
Authors
- Bastian Engel (ORCID: https://orcid.org/0000-0002-0972-3454)
- Daljeet Chahal (ORCID: https://orcid.org/0000-0003-2486-1449)
- Eunice X. Tan (ORCID: https://orcid.org/0000-0002-3757-4986)
- Richard Taubert (ORCID: https://orcid.org/0000-0001-9270-2496)
- Elmar Jaeckel (ORCID: https://orcid.org/0000-0003-4108-7192)
- Kai Duan (ORCID: https://orcid.org/0000-0002-3401-7228)
- Neta Gotlieb (ORCID: https://orcid.org/0000-0003-3827-8262)
- Maryam Naghibzadeh (ORCID: https://orcid.org/0000-0002-1780-7113)
- Amirhossein Azhie (ORCID: https://orcid.org/0000-0001-6393-9064)
- Mamatha Bhat (ORCID: https://orcid.org/0000-0003-1960-8449)
- Nazia Selzner (ORCID: https://orcid.org/0000-0002-9435-2597)
- Cynthia Tsien (ORCID: https://orcid.org/0000-0002-9807-3843)
- Sara Naimimohasses
- Joseph Ahn (ORCID: https://orcid.org/0000-0001-6994-2870)
- Sareh Keshavarzi (ORCID: https://orcid.org/0000-0002-4884-2448)
- Wei Xu (ORCID: https://orcid.org/0000-0002-1960-0992)
- Yun Li (ORCID: https://orcid.org/0000-0002-8426-565X)
- Yoo-Jin Han
- Divya Sharma (ORCID: https://orcid.org/0009-0004-5022-697X)
- Leslie Lilly
- Ankit Ray
- Sara Gehlaut
- Maryam Shojaee
- Surabie Sivanendran
Institutions
- University Health Network (CA)
- University of Ottawa (CA)
- University of Toronto (CA)
- York University (CA)
- Princess Margaret Cancer Centre (CA)
- Vancouver General Hospital (CA)
- Medizinische Hochschule Hannover (DE)
- Mayo Clinic in Arizona (US)
- National University Hospital (SG)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-05-28
- DOI
- https://doi.org/10.1038/s41467-025-59610-8
- Citations
- 5
- Primary Topic
- Liver Disease and Transplantation
- Type
- article
- Field-Weighted Citation Impact
- 6.61
Funders
- American Society of Transplantation
- Deutsche Forschungsgemeinschaft
- Medizinischen Hochschule Hannover
- Canadian Society of Transplantation
- Canadian Institutes of Health Research
- CIHR Skin Research Training Centre