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

Abstract: TH-PO326

Random Forest Can Accurately Predict the Technique Failure of Peritoneal Dialysis-Associated Peritonitis Patients

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

  • Li, Zi, Institute of Nephrology, West China Hospital of Sichuan University, Chengdu, China
  • Zang, Zhiyun, Institute of Nephrology, West China Hospital of Sichuan University, Chengdu, China
Background

Peritoneal dialysis associated peritonitis (PDAP) is a major cause of technique failure in peritoneal dialysis (PD) patients globally. The purpose of this study is to construct a risk prediction model which could accurately predict the technique failure in PDAP patients.

Methods

This retrospective cohort study included maintenance PD patients in our center from January 1, 2010 to December 31, 2021. Technique failure was defined as catheter removal, transfer to hemodialysis (HD) or peritonitis-related death. The risk prediction models for technique failure in PDAP patients were constructed based on five machine learning algorithms: random forest (RF), the least absolute shrinkage and selection operator (LASSO), decision tree, k nearest neighbor (KNN), and logistic regression (LR). And the internal validation was conducted in the test cohort.

Results

A total of 574 episodes of peritonitis during the 12 years were included in this study. The technique failure accounted for 23.69%, and the mortality rate was 4.00%. There were significant statistical differences between the technique failure group and the technique survival group in multiple baseline characteristics. The RF prediction model is the best able to predict the technique failure in PDAP patients, with the accuracy of 93.75% and AUC of 0.881. And the model had sensitivity and specificity of 77.14% and 99.08%, respectively.

Conclusion

RF prediction model could accurately predict the technique failure of PDAP patients, which demonstrated excellent predictive performance and assist in clinical decision making.

ROC curves of prediction models based on machine learning algorithms