Graft-versus-host disease (GVHD) is a rare but often fatal complication in liver transplantation, with a very high mortality rate. By harnessing multi-modal deep learning methods to integrate heterogeneous and imbalanced electronic health records (EHR), we aim to advance early prediction of GVHD, paving the way for timely intervention and improved patient outcomes. In this study, we analyzed pre-transplant electronic health records (EHR) spanning the period before surgery for 2,100 liver transplantation patients, including 42 cases of graft-versus-host disease (GVHD), from a cohort treated at Mayo Clinic between 1992 and 2025. The dataset comprised four major modalities: patient demographics, laboratory tests, diagnoses, and medications. We developed a multi-modal deep learning framework that dynamically fuses these modalities, handles irregular records with missing values, and addresses extreme class imbalance through AUC-based optimization. The developed framework outperforms all single-modal and multi-modal machine learning baselines, achieving an AUC of 0.836, an AUPRC of 0.157, a recall of 0.768, and a specificity of 0.803. It also demonstrates the effectiveness of our approach in capturing complementary information from different modalities, leading to improved performance. Our multi-modal deep learning framework substantially improves existing approaches for early GVHD prediction. By effectively addressing the challenges of heterogeneity and extreme class imbalance in real-world EHR, it achieves accurate early prediction. Our proposed multi-modal deep learning method demonstrates promising results for early prediction of a GVHD in liver transplantation, despite the challenge of extremely imbalanced EHR data.

Liver transplantation often faces fairness challenges across subgroups defined by sensitive attributes like age group, gender, and race/ethnicity. Machine learning models for outcome prediction can introduce additional biases. To address these, we introduce Fairness through the Equitable Rate of Improvement in Multitask Learning (FERI) algorithm for fair predictions of graft failure risk in liver transplant patients. FERI constrains subgroup loss by balancing learning rates and preventing subgroup dominance in the training process. Our experiments show that FERI maintains high predictive accuracy with AUROC and AUPRC comparable to baseline models. More importantly, FERI demonstrates an ability to improve fairness without sacrificing accuracy. Specifically, for gender, FERI reduces the demographic parity disparity by 71.74%, and for the age group, it decreases the equalized odds disparity by 40.46%. Therefore, the FERI algorithm advances fairness-aware predictive modeling in healthcare and provides an invaluable tool for equitable healthcare systems.

Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure. Analyzing the post-transplant cause of death (CoD) after organ transplant provides a powerful tool for clinical decision making, including personalized treatment and organ allocation. However, traditional methods like Model for End-stage Liver Disease (MELD) score and conventional machine learning (ML) methods are limited in CoD analysis due to two major data and model-related challenges. To address this, we propose a novel framework called CoD-MTL leveraging multi-task learning to model the semantic relationships between various CoD prediction tasks jointly. Specifically, we develop a novel tree distillation strategy for multi-task learning, which combines the strength of both the tree model and multi-task learning. Experimental results are presented to show the precise and reliable CoD predictions of our framework. A case study is conducted to demonstrate the clinical importance of our method in the liver transplant. 1 Introduction Organ transplant is a crucial therapeutic option for individuals with end-stage diseases, e.g., kidney failure [1], liver failure [2], liver cancer [3], etc.

In this work, we present a flexible method for explaining, in human readable terms, the predictions made by decision trees used as decision support in liver transplantation. The decision trees have been obtained through machine learning applied on a dataset collected at the liver transplantation unit at the Coru\~na University Hospital Center and are used to predict long term (five years) survival after transplantation. The method we propose is based on the representation of the decision tree as a set of rules in a logic program (LP) that is further annotated with text messages. This logic program is then processed using the tool xclingo (based on Answer Set Programming) that allows building compound explanations depending on the annotation text and the rules effectively fired when a given input is provided. We explore two alternative LP encodings: one in which rules respect the tree structure (more convenient to reflect the learning process) and one where each rule corresponds to a (previously simplified) tree path (more readable for decision making).

Understanding an agent's priorities by observing their behavior is critical for transparency and accountability in decision processes, such as in healthcare. While conventional approaches to policy learning almost invariably assume stationarity in behavior, this is hardly true in practice: Medical practice is constantly evolving, and clinical professionals are constantly fine-tuning their priorities. We desire an approach to policy learning that provides (1) interpretable representations of decision-making, accounts for (2) non-stationarity in behavior, as well as operating in an (3) offline manner. First, we model the behavior of learning agents in terms of contextual bandits, and formalize the problem of inverse contextual bandits (ICB). Second, we propose two algorithms to tackle ICB, each making varying degrees of assumptions regarding the agent's learning strategy. Finally, through both real and simulated data for liver transplantations, we illustrate the applicability and explainability of our method, as well as validating its accuracy.

One of the current problems in decision support from Artifici al Intelligence systems is the lack of explanations. When a system is making decisions in critical co ntexts and those decisions may have an impact on people's life like in the medical or legal domains, then explanations turn to be crucial, especially if we expect that a domain expert relies on the obtaine d answers. One of these situations from the medical domain where explanations have a crucial role is the process of donor-patient matching in an organ transplantation unit. This process starts when a new o rgan is received and consists in selecting a patient among those included in a waiting list for transplan tation. The transplantation unit is expected to follow an objective policy that takes into account medica l parameters and is experimentally supported by the existing records, but more importantly, this decisio n must be easily reproducible and explicable in a comprehensible way for other agents potentially involved, since it may have life-critical consequences at personal, medical and legal levels. Typically, this deci sion is taken in terms of a set of numerical weights (the impact of weights variation is studied in [7]). Although different classification systems based on Artificial Neural Networks (ANNs) are being propose d (see for instance [2] for the case of liver transplantation) their decisions rely on a black box whose b ehaviour is not explicable in human terms. In this paper, we present a rule interpreter, web-liver, designed for assisting the medical experts in the donor-patient matching of a liver transplantation un it, using the case scenario from the Digestive F. Aguado et al.

In this paper, we present the application of deep learning techniques to develop a modern model for the prediction of graft failure and survival analysis in liver transplant patients. We trained our model using the United Network for Organ Sharing (UNOS) dataset consisting of 59,115 patients from year 2002 to 2016 with around 150 features each. We also compare our model against an- other dataset – Scientific Registry of Transplant Recipients (SRTR) including 87,334 patients from year 2002 to 2018 – after selecting features by mapping them from UNOS data. Some of the most important features common to both datasets are Model for End-stage Liver Disease (MELD) score, patient body mass index (BMI), donor and patient age, cold ischemia time, and levels of various chemicals within the patient. To provide an additional tool to clinical practitioners in the allocation of a scarce resource, we developed a multi-task model to learn the survival function of a donor-recipient pair and hence predict the exact time of failure which outper- forms the traditional cox hazard models. The multi-task model produces very promising C-index results of 0.82 and 0.57 on the SRTR and UNOS datasets respectively.