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

ASN / Education & Meetings / Kidney Week /

Please note that you are viewing an archived section from 2021 and some content may be unavailable. To unlock all content for 2021, please visit the archives.

Abstract: PO1195

Phenotypes of Patients with Abnormal Phosphate on Admission by Consensus Clustering and Associated Mortality Risks

Session Information

Category: Fluid, Electrolyte, and Acid-Base Disorders

  • 902 Fluid, Electrolyte, and Acid-Base Disorders: Clinical

Authors

  • Dumancas, Carissa Y., Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Thongprayoon, Charat, Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Kattah, Andrea G., Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Mao, Michael A., Mayo Clinic's Campus in Florida, Jacksonville, Florida, United States
  • Erickson, Stephen B., Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Dillon, John J., Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Garovic, Vesna D., Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Cheungpasitporn, Wisit, Mayo Clinic Minnesota, Rochester, Minnesota, United States
Background

Hospitalized patients with abnormal phosphate are heterogeneous and cluster approaches may identify specific homogenous groups. This study aimed to cluster patients with abnormal phosphate on admission using unsupervised machine learning approach and to evaluate the mortality risk among these distinct clusters.

Methods

Consensus cluster analysis was performed on hospitalized adult patients with abnormal phosphate on admission, based on clinical and laboratory data. We determined each cluster’s key features using the standardized mean difference. We assessed the association of the clusters with hospital and one-year mortality.

Results

Cluster 2 patients with hypophosphatemia had older age, higher comorbidity burden, hypertension, diabetes, coronary artery disease, lower eGFR, and more acute kidney injury (AKI) (Fig 1a). Cluster 2 patients with hyperphosphatemia had older age, more admission for kidney disease, hypertension, end-stage kidney disease, AKI, and higher admission K+, Mg2+, or PO4 levels (Fig 1b). Both cohorts in cluster 2 had higher one-year mortality while hyperphosphatemic cluster 2 patients had higher hospital mortality (Fig 2).

Conclusion

The cluster analysis identified clinically distinct phenotypes with differing mortality risk in hospitalized patients with abnormal phosphate on admission. The age, comorbidities, and kidney function were key features.

Fig 1. The Manhattan plot of standardized differences in the hypophosphatemia (a) and hyperphosphatemia cohort (b).

Fig 2. The hospital mortality (a) and one-year mortality (b) in the hypophosphatemia cohort, and the hospital mortality (c) and one-year mortality (d) in the hyperphosphatemia cohort.