ASN's Mission

ASN leads the fight to prevent, treat, and cure kidney diseases throughout the world by educating health professionals and scientists, advancing research and innovation, communicating new knowledge, and advocating for the highest quality care for patients.

learn more

Contact ASN

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

email@asn-online.org

202-640-4660

The Latest on Twitter

Kidney Week

Abstract: TH-PO033

Identification of AKI Subtypes in Patients with Sepsis Using Unsupervised Clustering

Session Information

Category: Acute Kidney Injury

  • 101 AKI: Epidemiology, Risk Factors, and Prevention

Authors

  • Chan, Lili, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Chaudhary, Kumardeep, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Duffy, Aine, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Poojary, Priti, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Saha, Aparna, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Chauhan, Kinsuk, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Do, Ron, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Van Vleck, Tielman T., Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Coca, Steven G., Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Nadkarni, Girish N., Icahn School of Medicine at Mount Sinai, New York, New York, United States
Background

Acute kidney injury is highly prevalent in critically ill patients. Physicians recognize that subphenotypes of sepsis associated AKI exist. Our goal was to identify subphenotypes of AKI in patients admitted to the intensive care unit with sepsis.

Methods

This was a retrospective analysis using the Medical Information Mart for Intensive Care (MIMIC)-III database. We identified AKI using the Kidney Disease Improving Global Outcomes criteria and sepsis utilizing the Clinical Classification Software. We used unsupervised machine learning to identify clusters using laboratory results and vital signs prior to AKI diagnosis.

Results

1,865 patients were identified with sepsis associated AKI. After data processing and feature selection, 59 features, of which 28 were measures of variability, remained for inclusion into our unsupervised machine learning model. We utilized k-means clustering with k ranging from 2 – 10; k=2 had the highest silhouette score (0.62). Cluster 1 had 1,358 patients while Cluster 2 had 507 patients. There were no significant differences between clusters on age or gender. Small but significant differences were found on comorbidities, several laboratory results, and vital sign parameters. In-hospital mortality was significantly higher in cluster 2 patients (25%) vs. cluster 1 (20%, p=0.008). Features with the largest differences between clusters included basophil variability, eosinophil variability, ALT variability, and Creatine Kinase values.

Conclusion

To our knowledge this is the first study to identify two distinct subphenotypes of sepsis associated AKI utilizing electronic medical record data. Variability among laboratory values was important for clustering. Future studies in other cohorts and additional features are needed to validate and expand on the results of our study.

Funding

  • NIDDK Support