Related Experiment Video
Updated: Jul 26, 2025

A Large Animal Model for Acute Kidney Injury by Temporary Bilateral Renal Artery Occlusion
Published on: February 2, 2021
Interpretable Stratification for Chronic Kidney Disease Progression Based on Time to Event Analysis
Mohamed Ghalwash1, Akira Koseki2, Toshiya Iwamori2
1IBM Research, Healthcare and Life Sciences, Yorktown, NY, USA.
Insights
This study identifies key factors for Chronic Kidney Disease (CKD) progression to dialysis. Early identification of these features aids in developing new treatments and preventative strategies for CKD patients.
Area of Science:
- Nephrology
- Biostatistics
- Data Science
Background:
- Chronic Kidney Disease (CKD) affects kidney function, often undetected early.
- Progression to dialysis is a significant health consequence for CKD patients.
- Understanding early CKD progression is crucial for timely intervention.
Purpose of the Study:
- To stratify CKD patients based on time to dialysis from early stages.
- To identify key clinical features predicting rapid progression to dialysis.
- To develop interpretable models for CKD patient stratification.
Main Methods:
- Feature reduction and predictive modeling on ~40,000 CKD patients.
- Time-to-event analysis to model time to dialysis.
- Stratification of a subpopulation (3,522 patients) with anemia and cardiovascular drug prescriptions.
Main Results:
- Identified top important features for predicting time to dialysis.
- Stratified a high-risk CKD subpopulation exhibiting anemia and cardiovascular drug use.
- Conventional clustering methods lacked interpretability for identifying fast progression factors.
Conclusions:
- Developed the first interpretable feature-based stratification for early CKD patients using time-to-event analysis.
- The findings can aid in CKD prevention and the development of novel therapeutic strategies.
- This approach offers a clearer understanding of factors driving rapid CKD progression.
Abstract:
In Chronic Kidney Disease (CKD), kidneys are damaged and lose their ability to filter blood, leading to a plethora of health consequences that end up in dialysis. Despite its prevalence, CKD goes often undetected at early stages. In order to better understand disease progression, we stratified patients with CKD by considering the time to dialysis from diagnosis of early CKD (stages 1 or 2). To achieve this, we first reduced the number of clinical features in a predictive time-to-dialysis model and identified the top important features on a cohort of ∼ 40, 000 CKD patients. The extracted features were used to stratify a subpopulation of 3, 522 patients that showed anemia and were prescribed for cardiovascular-related drugs and progressed faster to dialysis. On the other side, clustering patients using conventional clustering methods based on their clinical features did not allow such clear interpretation to identify the main factors for leading fast progression to dialysis. To our knowledge this is the first study extracting interpretable features for stratifying a cohort of early CKD patients using time-to-event analysis which could help prevention and the development of new treatments.
Related Concept Videos
Chronic Kidney Disease I: Introduction
Chronic Kidney Disease III: Interprofessional Care
Acute Kidney Injury I: Introduction
Acute Kidney Injury III: Clinical Manifestations
Acute Kidney Injury IV: Diagnostic Studies and Prevention
Chronic Kidney Disease II: Clinical Manifestations

