A Method for Characterizing Disease Progression from Acute Kidney Injury to Chronic Kidney Disease

2025-11-18

AI Summary

This study addresses the challenge of risk stratification for chronic kidney disease (CKD) progression among acute kidney injury (AKI) patients. We propose a multimodal framework integrating longitudinal ICD code embedding clustering with dynamic serum creatinine trajectories to define 15 distinct post-AKI clinical states. Using multistate modeling and Cox survival analysis, we characterize CKD transition pathways and heterogeneous risk factor effects across states. In a cohort of 20,699 AKI patients, 17% progressed to CKD while 75% remained stable. Our analysis systematically reveals differential associations of both conventional (e.g., diabetes) and novel risk factors—including specific infection code combinations and medication exposure patterns—across clinical states. The framework enables dynamic modeling of AKI-to-CKD progression trajectories and delivers interpretable, subgroup-specific risk prediction, supporting timely, precision-targeted interventions.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Multimodal Learning
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Patients with acute kidney injury (AKI) are at high risk of developing chronic kidney disease (CKD), but identifying those at greatest risk remains challenging. We used electronic health record (EHR) data to dynamically track AKI patients' clinical evolution and characterize AKI-to-CKD progression. Post-AKI clinical states were identified by clustering patient vectors derived from longitudinal medical codes and creatinine measurements. Transition probabilities between states and progression to CKD were estimated using multi-state modeling. After identifying common post-AKI trajectories, CKD risk factors in AKI subpopulations were identified through survival analysis. Of 20,699 patients with AKI at admission, 3,491 (17%) developed CKD. We identified fifteen distinct post-AKI states, each with different probabilities of CKD development. Most patients (75%, n=15,607) remained in a single state or made only one transition during the study period. Both established (e.g., AKI severity, diabetes, hypertension, heart failure, liver disease) and novel CKD risk factors, with their impact varying across these clinical states. This study demonstrates a data-driven approach for identifying high-risk AKI patients, supporting the development of decision-support tools for early CKD detection and intervention.

Problem

• Characterizing disease progression from acute kidney injury to chronic kidney disease
• Identifying high-risk AKI patients likely to develop CKD using EHR data
• Developing data-driven approach for early CKD detection and intervention

Innovation

• Using EHR data to track AKI patients dynamically
• Applying clustering to identify post-AKI clinical states
• Employing multi-state modeling to estimate CKD progression