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 2022 and some content may be unavailable. To unlock all content for 2022, please visit the archives.

Abstract: TH-PO664

Discontinuation of Artificial Intelligence (AI) Tool for Anemia Management Results in Higher Drug Exposure, Lower Hemoglobin (Hb)

Session Information

  • Anemia and Iron Metabolism
    November 03, 2022 | Location: Exhibit Hall, Orange County Convention Center‚ West Building
    Abstract Time: 10:00 AM - 12:00 PM

Category: Anemia and Iron Metabolism

  • 200 Anemia and Iron Metabolism

Authors

  • Brier, Michael E., University of Louisville, Louisville, Kentucky, United States
  • Gaweda, Adam E., University of Louisville, Louisville, Kentucky, United States
  • Aronoff, George R., Dosis Inc, San Francisco, California, United States
Background

We innovated a clinical decision support tool for anemia management. This tool uses AI methods to classify patients into multiple dose-response categories combined with predictive control to achieve target Hb over time. The tool was modified for use with long acting epoetin isoforms (epotein beta, Mircera®). We tested the hypothesis that dropping anemia management guidance will decrease quality.

Methods

Data were abstracted from a commercially available software Strategic Anemia Advisor (SAA, Dosis Inc, San Francisco, CA) between Dec 2018 and Mar 2022 on 855 patients in 5 dialysis facilities receiving epoetin beta located in the same geographic area. SAA use was left at the discretion of the facility medical director. Two facilities used SAA over the duration of the data capture (Facility 1 and 2), one facility never used SAA (Facility 3) and two facilities discontinued SAA at month 53 and 54 (Facility 4 and 5). Data were aggregated by month and an indicator of SAA recommendations.

Results

Facilities that used SAA guidance had higher Hb and lower monthly dose of epoetin beta/patient than the facility that did not use SAA (p<0.001). Discontinuation of SAA caused Hb to fall by about 0.6 g/dL and dose increased 30-39 mcg/patient/month. Mean Hb and dose are shown in Table 1. SAA use is shown as a solid line and no SAA use is shown as a dashed line in Figure1.

Conclusion

Discontinuing AI management results in an immediate, detrimental effect on Hb and ESA dose. Those facilities that never used SAA or discontinued use observed an increased dose of epoetin beta and a decrease in Hb obtained. This is likely due to increased manipulation of the dose in resulting in over control the Hb concentration.

Facility12345
SAAYesYesNoYesNoYesNo
Hb (g/dL)11.110.610.310.59.810.710.1
Dose (mcg/patient/month)4770139651025989

Statistical Analysis Oneway SNK