ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Please note that you are viewing an archived section from 2023 and some content may be unavailable. To unlock all content for 2023, please visit the archives.

Abstract: TH-PO325

Robust Joint Models of Albumin and All-Cause Mortality in Incident Peritoneal Dialysis Patients: A Dynamic Predictions Perspective Adjusting for Competing Risks

Session Information

  • Home Dialysis - I
    November 02, 2023 | Location: Exhibit Hall, Pennsylvania Convention Center
    Abstract Time: 10:00 AM - 12:00 PM

Category: Dialysis

  • 802 Dialysis: Home Dialysis and Peritoneal Dialysis

Authors

  • Damgov, Ivan, Center for Pediatric and Adolescent Medicine, University of Heidelberg, Heidelberg, Germany
  • Kieser, Meinhard, Institute of Medical Biometry, University of Heidelberg, Heidelberg, Germany
  • Rutherford, Peter, Baxter Healthcare Corporation, Zurich, Switzerland
  • Lambie, Mark, Faculty of Medicine and Health Sciences, Keele University, Stoke-on-Trent, United Kingdom
  • Davies, Simon J., Faculty of Medicine and Health Sciences, Keele University, Stoke-on-Trent, United Kingdom
  • Wong, Muh Geot, Department of Renal Medicine, Royal North Shore Hospital, St Leonards, New South Wales, Australia
  • Pollock, Carol A., Kolling Institute, Sydney Medical School, University of Sydney, Royal North Shore Hospital, St Leonards, New South Wales, Australia
  • Johnson, David W., Australasian Kidney Trials Network, University of Queensland, Birsbane, Queensland, Australia
  • Schmitt, Claus Peter, Center for Pediatric and Adolescent Medicine, University of Heidelberg, Heidelberg, Germany
Background

Joint models (JM) allow investigation of association between longitudinal biomarkers and mortality in patients on peritoneal dialysis (PD) and provide individual patient dynamic risk predictions. Yet, deviations from JM assumptions in dialysis trial data and consideration of competing events remain unexplored.

Methods

We evaluated the association of albumin with all-cause mortality in incident PD patients followed over 8 years in the Initiating Dialysis Early And Late trial. To account for skewness/outliers in albumin, novel JM with mixed effects sub-model with skew-normal, t and skew-t errors were compared with conventional JM under normal distribution. Furthermore, we adjusted for the competing events of transfer to hemodialysis and transplantation using Weibull cause-specific hazards. The dataset (N=314 patients) was randomly split into training dataset (3/4, N=236) for model fitting and validation dataset (1/4, N=78) to infer predictive performance. We obtained 6-month individual patient survival predictions from all JM at cut-offs 1, 1.5 and 2 years utilizing albumin trajectory and baseline risk factors.

Results

A median of 9 albumin records per patient and a 35% death rate with median time-to-event of 4.5 years ensured convergence of all 16 joint models. Albumin hazard ratio of death remained robust (0.78 to 0.81), suggesting significant inverse relationship between albumin and death across all models.
Longer follow-up improved the prediction accuracy of all JM in the validation dataset. JM with competing events outperformed JM with survival only (area under the curve (AUC) ranges at 1, 1.5 and 2-years: 0.53-0.57 vs 0.52-0.55, 0.75-0.80 vs 0.75-0.77, 0.84-0.90 vs 0.82-0.88), regardless of the distribution assumption for albumin. Prediction performance of all JM surpassed classical Cox model with baseline albumin (AUC = 0.46, 0.70, 0.75). Results were confirmed by two simulation studies.

Conclusion

This first comprehensive JM in dialysis patients demonstrates utility for dynamic personalized survival prediction, with robustness of estimates to deviations from normality and higher predictive accuracy when adjusting for competing risks, and marked superiority to the classical Cox approach.

Funding

  • Commercial Support – Baxter Healthcare Corporation