Kidney Week

Abstract: TH-PO203

Using Machine Learning to Help Predict Elevated Serum Phosphate Levels in Patients with ESRD

Session Information

• Bone and Mineral Metabolism: Clinical - I
  October 25, 2018 | Location: Exhibit Hall, San Diego Convention Center
  Abstract Time: 10:00 AM - 12:00 PM

Category: Bone and Mineral Metabolism

• 402 Bone and Mineral Metabolism: Clinical

Authors

• Long, Andrew, Fresenius Medical Care North America, Waltham, Massachusetts, United States

Andrew Long,

• Blanchard, Tommy C., Fresenius Medical Care North America, Waltham, Massachusetts, United States

Tommy C. Blanchard,

• Willetts, Joanna, Fresenius Medical Care North America, Waltham, Massachusetts, United States

Joanna Willetts,

• Chaudhuri, Sheetal, Fresenius Medical Care North America, Waltham, Massachusetts, United States

Sheetal Chaudhuri,

• O'Connell, Michael Ryan, Fresenius Medical Care North America, Waltham, Massachusetts, United States

Michael Ryan O'Connell,

• Belmonte, Kathleen, Fresenius Kidney Care, Waltham, Massachusetts, United States

Kathleen Belmonte,

• Lee, Marissa A., Fresenius Medical Care North America, Waltham, Massachusetts, United States

Marissa A. Lee,

• Usvyat, Len A., Fresenius Medical Care North America, Waltham, Massachusetts, United States

Len A. Usvyat,

• Ketchersid, Terry L., Fresenius Medical Care North America, Waltham, Massachusetts, United States

Terry L. Ketchersid,

• Maddux, Franklin W., Fresenius Medical Care North America, Waltham, Massachusetts, United States

Franklin W. Maddux,

Background

According to USRDS, over two-thirds of patients treated with hemodialysis had serum phosphate (PO₄) greater than the KDIGO guidelines of 4.5 mg/dl (USRDS 2017, KDIGO 2009). In practice, most clinicians try to achieve PO₄ levels between 3.0 and 5.5 mg/dl (Handbook on dialysis 2015). Proactively identifying patients who may transition from the normal clinical range to greater than 5.5 mg/dl may help clinicians target their interventions and avoid elevated PO₄ levels.

Methods

We built a machine learning model with over 1000 variables to predict which HD patients will realize a PO₄ lab value greater than 5.5mg/dl during the following month. We restrict our model to patients using a pharmacy specializing in renal medications with all PO₄ draws less than 5.5 mg/dl in the last 180 days. Some of the variables included in this model are history of lab values, treatment vital signs, treatment no shows, comprehensive assessments from dieticians and social workers, and PO₄ binder medication possession ratios. To train the XGBoost machine learning model, we utilized data from patients who were treated in Fresenius Medical Care North America clinics between January 2016 and October 2017. The results shown below are from un-seen test data with 16639 patients in 2017.

Results

For the patients enrolled in the specialty pharmacy who have all PO₄ values less than 5.5 mg/dl in the previous 180 days, the prevalence of having next month’s lab draw greater than 5.5 mg/dl is approximately 10%. Results from the test data include area under the receiver operating curve (AUROC) of 0.75, sensitivity of 72% and specificity of 66%. The confusion matrix for test data is shown in Table 1.

Conclusion

We created a predictive model to help identify patients who may unexpectedly have elevated PO₄ lab values in the next month. Identifying these patients may help to target interventions that mitigate negative consequences associated with high PO₄ levels.

Confusion matrix for test data (n = 16639)

Funding

• Commercial Support –