Abstract: PO1365
Data-Backed Multidisciplinary Care Substantially Improves Renal Replacement Therapy Outcomes
Session Information
- Vascular Access
October 22, 2020 | Location: On-Demand
Abstract Time: 10:00 AM - 12:00 PM
Category: Dialysis
- 704 Dialysis: Vascular Access
Authors
- Wang, Xiaoyan, pulseData, New York, New York, United States
- Fielding, Ollie, pulseData, New York, New York, United States
- Son, Jung Hoon, pulseData, New York, New York, United States
- Lee, Edward M., pulseData, New York, New York, United States
- Bohmart, Andrew, The Rogosin Institute, New York, New York, United States
- Liu, Frank, The Rogosin Institute, New York, New York, United States
- Silberzweig, Jeffrey I., The Rogosin Institute, New York, New York, United States
Group or Team Name
- The PEAK team
Background
The Rogosin Institute created the Program for Education in Advanced Kidney Disease (PEAK), a multidisciplinary care team that assists patients in making a smooth transition to renal replacement therapy (RRT) in 2015. In October 2018 the PEAK team transitioned to using a machine learning (ML) algorithm and care platform devised by pulseData to identify their highest risk patients and increase the rate of optimal RRT starts and increase support for patients in choosing a home dialysis modality.
Methods
The ML model continually surveys the Electronic Health Record (EHR) to identify patients at risk of progression to an eGFR <10 or RRT start in the next six months for referral into the PEAK program. The patient review platform presents a longitudinal view of the patient’s data, allows for the documentation of the RRT care plan and is used to review the high risk patients at a weekly care planning session. The care team updates patient progress and the platform highlights patients who have had no recent care actions.
Results
Home dialysis rates increased 50% after the ML/platform deployment (30% vs 20%). Home dialysis rates among graduates of the PEAK program are now 10x the NYC average (27% since January 1, 2019 vs 2.5%). Patients who spend more time in the PEAK program are more likely to receive an optimal dialysis start (as an outpatient and with venous access) (p<0.00002, unequal variances t-test); the mean PEAK duration for an optimal start is 316 days vs. 196 for non-optimal starts. Optimal starts are also associated with a greater number of PEAK appointments, (4.9 appointments vs 3.7; p<0.0004, unequal variances t-test). Further, of patients starting dialysis using a central venous catheter (CVC), PEAK program graduates remove them significantly sooner (mean 88.57 days for non-PEAK vs. 54.71 mean days for PEAK (p<0.02, unequal variances t-test).
Conclusion
The PEAK MDC-pulseData partnership has dramatically improved care coordination resulting in a substantial increase in home dialysis modality and optimal dialysis starts and reduced the amount of time dialysis patients spend using a CVC.
Funding
- Commercial Support – pulseData