AJKD Publishes Abstract, “Baseline Characteristics and Early Results From the GEMINI-RAPA Project: Improving the Quality of CKD Care with Risk Prediction and Personalized Recommendations” [1]
- The study included over 16,000 patients, with 28% identified as high risk for CKD progression based on Klinrisk assessment.
- Following implementation of Khure Health’s risk prediction and clinical decision support, UACR testing rates increased by 66% at 6 months post-initiation, suggesting a positive shift towards guideline-recommended testing.
- Initial trends suggest increased prescription of goal-directed medical therapy medications at 6 months.
Chronic kidney disease (CKD) is a significant public health concern, affecting an estimated 1 in 7 Americans [2]. CKD is a progressive disease and can lead to End-Stage Kidney Disease (ESKD) requiring dialysis or transplantation. Furthermore, CKD is associated with cardiovascular disease and is associated with increased mortality [3].
While effective interventions exist to slow CKD progression and prevent heart failure, implementing these interventions consistently remains a challenge in clinical practice. Utilization rates for guideline-recommended testing and therapies often fall short of optimal levels [4]. This gap between evidence-based recommendations and real-world practice necessitates novel approaches to improve the quality of CKD care.
The Study
The project, a collaboration between Khure Health and a leading life science company, investigated a novel approach to improve CKD care. This approach leveraged a risk prediction algorithm, Klinrisk and Khure Health’s clinical decision support (CDS) platform. Patient data, including estimated glomerular filtration rate (eGFR), albuminuria, demographics, laboratory results, and co-morbidities, was obtained from electronic health records (EHR). This allowed for individual patient risk stratification of CKD progression, encouraging physicians to order guideline-recommended tests like uACR for high-risk patients who may have otherwise remained undetected. Clinicians can then prioritize these patients for goal-directed medical therapy (GDMT) implementation and ongoing monitoring. This comprehensive approach has the potential to significantly improve patient outcomes and quality of life for those battling chronic kidney disease.
Baseline characteristics of patient population included in the study:
Future Direction
This study demonstrates the potential of integrating a machine learning risk prediction model with CDS to enhance CKD care. The early results suggest an improvement in guideline-recommended testing practices. Longer follow-up is needed to assess the impact on GDMT adherence and patient outcomes.
Discover More
The study’s findings will be presented at the upcoming National Kidney Foundation Spring Clinical Meetings (May 14-18, 2024), providing an opportunity for further discussion and exploration of this promising approach to managing CKD. Connect with us to learn more: khurehealth.ca/contact-us/
References
[1] Tangri, N., Leon, S., Watts, D., Woo, C., Fatoba, S., Saigal, N., & Pergola, P. (2024). Baseline characteristics and early results from the GEMINI-RAPA project: Improving the quality of CKD care with risk prediction and personalized recommendations. AJKD: NKF Spring Clinical Meetings Abstracts, 83(4), S87.
[2] Centers for Disease Control and Prevention. Chronic Kidney Disease in the United States, 2021. Centers for Disease Control and Prevention, US Department of Health and Human Services; 2021.
[3] Rashidi A., Sehgal A.R., Rahman M., O’Connor A.S. The case for chronic kidney disease, diabetes mellitus, and myocardial infarction being equivalent risk factors for cardiovascular mortality in patients older than 65 years. Am J Cardiol. 2008;102(12):1668–1673.
[4] Stevens, L. A., et al. Low Rates of Testing and Diagnostic Codes Usage in a Commercial Clinical Laboratory: Evidence for Lack of Physician Awareness of Chronic Kidney Disease. Journal of the American Society of Nephrology. 2005; 16(8): 2439-2448, DOI: 10.1681/ASN.2005020192
