PREDICTIVE MODEL FOR UNPLANNED DIALYSIS INITIATION IN STAGE 5 CKD PATIENTS: RESULTS FROM THE TRADITCO STUDY

Certificate Output Instructions

For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".

To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".

Presented the abstract " "
(Abstract co-author(s): )

Back

E-Poster Presentation

During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.

Preparing your E-Poster

Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.

E-Poster Submission Deadline

Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.

E-Poster Format Requirements

PDF file
Layout: Portrait (vertical orientation)
One page only (Dim A4: 210 x 297mm or PPT)
E-Poster can be prepared in PowerPoint (one (1) PowerPoint slide) but must be saved and submitted as PDF file.
File Size: Maximum file size is 2 Megabytes (2 MB)
No hyperlinks, animated images, animations, and slide transitions
Language: English
Include your abstract number
E-posters can include QR codes, tables and photos

E-Poster

https://storage.unitedwebnetwork.com/files/1099/bfb8419eeb28cc075eb8abd0e90bfb83.pdf

Abstract Title *

PREDICTIVE MODEL FOR UNPLANNED DIALYSIS INITIATION IN STAGE 5 CKD PATIENTS: RESULTS FROM THE TRADITCO STUDY

Please follow the instructions below to input your abstract title.

Abstract titles should be brief and reflect the content of the abstract.

The title will not be accepted if it exceeds 25 words.
Type in CAPITAL LETTERS.
Lowercase may be used for abbreviations only, for example, mRNA.

Co-author 1

Peter Rutherford peter.rutherford@vantive.com Vantive corporation Medical Affairs Zurich Switzerland *

Co-author 2

Mauricio Sanabria mauricio.sanabria@vantive.com Renal Care Services Latin-America Medical Affairs Bogota Colombia -

Co-author 3

Jasmin Vesga jasmin.vesga@vantive.com Renal Care Services Colombia Medical Affairs Bucaramanga Colombia -

Co-author 4

Sergio Paez spaezm@unal.edu.co National University of Colombia Science Bogota Colombia -

Co-author 5

Angela Rivera angela.rivera@vantive.com Vantive corporation Medical Affairs Deerfield United States -

Co-author 6

Co-author 7

Co-author 8

Co-author 9

Co-author 10

Co-author 11

Co-author 12

Co-author 13

Co-author 14

Co-author 15

Introduction

Unplanned initiation of dialysis is associated with increased short-term negative outcomes and healthcare costs. Early identification of at-risk patients allows proactive care and a smoother transition to kidney replacement therapy (KRT). This study aimed to develop and validate a predictive model for unplanned dialysis initiation among stage 5 CKD patients in a nephroprotection program.

Methods

A retrospective cohort analysis included 1,471 patients with CKD stage G5 enrolled in the Renal Care Services (RCS) nephroprotection program in Colombia. Data were randomly split into a 70% training set and a 30% internal validation set. A logistic regression model was developed using LASSO for variable selection and Ridge penalization to stabilize coefficients. Model performance was evaluated by the area under the ROC curve (AUC) and the confusion matrix.

Results

We observed unplanned dialysis initiation in 35.5% of cases (n = 522). The predictive model included the following factors: having permanent access, serum albumin levels, the use of angiotensin II receptor blockers, the Karnofsky scale score, absenteeism, and the number of emergency visits or hospitalizations. The permanent access variable has the greatest weighting in the model (Table 1). Model performance was excellent; the sensitivity was 0.81, with a specificity of 0.99, and the area under the ROC curve was 0.94 (Table 2). Figure 1 provides an overview of the proposed tool for clinicians in the CKD program.

Table 1. Predictive model for unplanned dialysis initiation

Table 2. Metrics for the confusion matrix

Conclusion

The TRADITCO predictive model has a high level of accuracy in identifying cases of unplanned dialysis initiation. Integrating this tool into clinical practice could support real-time risk stratification, enabling earlier multidisciplinary interventions and improved outcomes.

Kewords