Related Experiment Video
Updated: Jul 16, 2025
Digital Home-Monitoring of Patients after Kidney Transplantation: The MACCS Platform
Published on: April 12, 2021
Predicting hospitalizations for patients with chronic kidney disease
Steph Karpinski, Scott Sibbel, Kathryn Gray
1Davita, Inc, 825 S 8th St, Ste 300, Minneapolis, MN 55404.
Insights
Patients with chronic kidney disease (CKD) face higher hospitalization risks. A new algorithm using medical claims identifies high-risk CKD patients for better resource allocation and improved clinical outcomes.
Area of Science:
- Nephrology
- Health Informatics
- Predictive Analytics
Background:
- Patients with chronic kidney disease (CKD) have elevated hospitalization rates compared to the general population.
- Hospitalizations in CKD patients are linked to increased medical costs, morbidity, and mortality.
- Identifying high-risk CKD individuals is crucial for enhancing clinical outcomes and optimizing healthcare resource allocation.
Purpose of the Study:
- To develop and validate a predictive algorithm for identifying patients with stages 3-5 CKD at high risk of near-term hospitalization.
- To leverage Medicare claims data for risk stratification within the CKD population.
- To create a decision support tool for clinical programs managing CKD patient populations.
Main Methods:
- A retrospective, observational cohort study utilizing Medicare Part A and B claims from 2017-2018.
- A dataset of 50,000 unique patients with stage 3-5 CKD was divided into training (40,000) and testing (10,000) sets.
- A gradient-boosting machine model with 399 input features was developed to predict all-cause hospitalization within 90 days.
Main Results:
- The final gradient-boosting model achieved an area under the curve (AUC) of 0.73 for predicting hospitalization, consistent in both training and testing sets.
- The model demonstrated positive predictive values of 0.306, 0.240, and 0.216 at 10%, 20%, and 30% thresholds, respectively.
- Sensitivity at these thresholds was 0.288, 0.453, and 0.609, respectively, indicating the model's ability to identify a significant proportion of at-risk patients.
Conclusions:
- An algorithm was successfully developed using medical claims data to identify Medicare patients with CKD stages 3-5 at high risk for hospitalization.
- The developed algorithm shows potential as a decision support tool for clinical programs focused on CKD patient management.
- This tool can aid in the proactive management of CKD patients, potentially reducing hospitalizations and improving care coordination.
Objectives:
Patients with chronic kidney disease (CKD) are at higher risk of being admitted to the hospital than the general population. Hospitalizations in patients with CKD are associated with higher medical costs and increased morbidity and mortality. Identification of patients with CKD who are at greatest risk of hospitalization may hold promise to improve clinical outcomes and enable judicious allocation of health care resources.
Study Design:
Retrospective, observational cohort study.
Methods:
Medicare Part A and Part B claims from calendar years 2017 and 2018 from 50,000 unique patients with a diagnosis of stage 3 to 5 CKD were used for this study. Data were split into training (n = 40,000) and test (n = 10,000) sets. A variety of model types were built to predict all-cause hospitalization within 90 days.
Results:
The final model was a gradient-boosting machine with 399 input terms. The model demonstrated good ability to discriminate (area under the curve [AUC] for the receiver operating characteristic curve = 0.73), which was stable when tested in the test set (AUC = 0.73). The positive predictive value in the test set was 0.306, 0.240, and 0.216 at the 10%, 20%, and 30% thresholds, respectively. The sensitivity in the test set was 0.288, 0.453, and 0.609 at the 10%, 20%, and 30% thresholds, respectively.
Conclusions:
We developed an algorithm that uses medical claims to identify Medicare patients with CKD stages 3 to 5 who are at highest risk of being hospitalized in the near term. This algorithm could be used as a decision support tool for clinical programs focusing on management of patient populations with CKD.
Related Concept Videos
01:28Chronic Kidney Disease III: Interprofessional Care
01:18Chronic Kidney Disease IV: Nursing Management
01:25Chronic Kidney Disease I: Introduction
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
01:22Acute Kidney Injury VI: Nursing Management
01:20Acute Kidney Injury V: Interprofessional Care