Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury

2026-04-22

AI Summary

Existing deep learning models struggle to effectively model irregularly sampled clinical time-series data and lack interpretability, limiting the reliability of early warning systems for acute kidney injury (AKI). This work proposes CT-Former, a novel framework that uniquely integrates continuous-time state evolution with a causal Transformer architecture. By modeling patient trajectories in continuous time and introducing a causal attention mechanism, CT-Former explicitly constructs a structured causal matrix to trace the origin pathways of critical physiological abnormalities. The method avoids opaque black-box aggregation of hidden states through a decoupled two-stage training strategy that optimizes causal fusion. Evaluated on the MIMIC-IV cohort (N=18,419), CT-Former significantly outperforms current state-of-the-art approaches, achieving high-accuracy, interpretable early prediction of AKI.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Causality

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate early prediction of Acute Kidney Injury (AKI) is critical for timely clinical intervention. However, existing deep learning models struggle with irregularly sampled data and suffer from the opaque "black-box" nature of sequential architectures, strictly limiting clinical trust. To address these challenges, we propose CT-Former, integrating continuous-time modeling with a Causal-Transformer. To handle data irregularity without biased artificial imputation, our framework utilizes a continuous-time state evolution mechanism to naturally track patient temporal trajectories. To resolve the black-box problem, our Causal-Attention module abandons uninterpretable hidden state aggregation. Instead, it generates a directed structural causal matrix to identify and trace the exact historical onset of severe physiological shocks. By establishing clear causal pathways between historical anomalies and current risk predictions, CT-Former provides native clinical interpretability. Training follows a decoupled two-stage protocol to optimize the causal-fusion process independently. Extensive experiments on the MIMIC-IV cohort (N=18,419) demonstrate that CT-Former significantly outperforms state-of-the-art baselines. The results confirm that our explicitly transparent architecture offers an accurate and trustworthy tool for clinical decision-making.

Problem

• Acute Kidney Injury
• irregularly sampled data
• black-box models
• clinical interpretability
• early prediction

Innovation

• Causal-Transformer
• continuous-time modeling
• clinical interpretability
• irregularly sampled data
• structural causal matrix