Temporal Fusion Nexus: A task-agnostic multi-modal embedding model for clinical narratives and irregular time series in post-kidney transplant care

TL;DR

Temporal Fusion Nexus (TFN) is a novel multi-modal embedding model that effectively integrates irregular time series and clinical narratives, improving prediction accuracy in post-kidney transplant care and demonstrating broad potential in healthcare applications.

Contribution

We developed TFN, a task-agnostic model that combines clinical text and time series data, outperforming existing models in transplant outcome predictions and providing interpretable insights.

Findings

TFN achieved higher AUC scores for graft loss and rejection.

Integrating clinical narratives improved model performance.

TFN provided interpretable latent factors aligned with clinical reasoning.

Abstract

We introduce Temporal Fusion Nexus (TFN), a multi-modal and task-agnostic embedding model to integrate irregular time series and unstructured clinical narratives. We analysed TFN in post-kidney transplant (KTx) care, with a retrospective cohort of 3382 patients, on three key outcomes: graft loss, graft rejection, and mortality. Compared to state-of-the-art model in post KTx care, TFN achieved higher performance for graft loss (AUC 0.96 vs. 0.94) and graft rejection (AUC 0.84 vs. 0.74). In mortality prediction, TFN yielded an AUC of 0.86. TFN outperformed unimodal baselines (approx 10% AUC improvement over time series only baseline, approx 5% AUC improvement over time series with static patient data). Integrating clinical text improved performance across all tasks. Disentanglement metrics confirmed robust and interpretable latent factors in the embedding space, and SHAP-based attributions confirmed alignment with clinical reasoning. TFN has potential application in clinical tasks beyond KTx, where heterogeneous data sources, irregular longitudinal data, and rich narrative documentation are available.