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-PO041

A Novel Clinical Prioritization Tool Stratifies Nephrology Patients by Acuity and Change over Time

Session Information

Category: Augmented Intelligence, Digital Health, and Data Science

  • 300 Augmented Intelligence, Digital Health, and Data Science

Authors

  • Nguyen, Elizabeth D., University of Washington, Seattle, Washington, United States
  • Mokiao, Michael, Seattle Children's Research Institute, Seattle, Washington, United States
  • Pollack, Ari, University of Washington, Seattle, Washington, United States
Background

Finding information to prioritize patient care is a difficult task with the growing amount of data in the electronic health record (EHR). Systems that highlight clinically meaningful patterns in laboratory data can support decision making, particularly for nephrology patients whose disease severity often correlates with abnormalities in metabolic balance. In this work, we present and evaluate a novel tool which captures a patient’s acuity and degree of change based on laboratory data, then places patients in four clinically applicable categories to aid in prioritization.

Methods

An algorithm was developed to use laboratory data to calculate a unique score for patient (1) clinical acuity and (2) degree of change. Data was collected for diverse patient encounters from a tertiary care pediatric hospital. Scores were used to categorize patients as well, chronically sick, acutely sick or improving. To evaluate categorizations, results were compared to physician assessment of eight patient cases using C2 goodness of fit.

Results

There was agreement in categorization between physicians and the tool (p<0.001). Patient categorization by the tool matched what was expected for their encounter and subspeciality type. Patients labeled as “acutely sick” were in the PICU (70% of acutely sick patients). Patients categorized as “chronically sick” were split between inpatient and outpatient encounters. Most chronically sick inpatients were outside of the PICU (89% of chronically sick inpatients) and most chronically sick outpatients were nephrology patients (70% of chronically sick outpatients).

Conclusion

This clinical priority scoring tool supports a physician’s recognition of meaningful patterns in the EHR that matches their clinical assessment of patients. The tool also detected subtle trends in the trajectory of patients not otherwise captured by physicians on their first assessment. Specifically, the tool categorized nephrology patients as being chronically sick as compared to other patients which correlates with the electrolyte and acid/base imbalance, anemia and metabolic bone disease often seen in this population. Using the tool to categorize patients, physicians can rapidly identify which patients in the outpatient setting may need further evaluation for admission and which patients in the hospital may need intensive care.

Funding

  • NIDDK Support