CSP algorithm performance
The CSP algorithm was developed and tested on a total of 23,029 patients from 47 countries.
When using the 11.5% cutoff to determine whether patients were high risk, the CSP algorithm: correctly detected 80.5% of the patients with an eGFR below 60 as high risk, identified 53.2% as being high risk, and increased the positive predictive value (relatively) by 51.5%, on average, globally.
These results translate to the CSP algorithm offering improved efficiency of identifying patients with an eGFR below 60, or a reduced cost to identify the same number of patients (Figure right).
Development of minimal resource pre-screening tools for chronic kidney disease in people with type 2 diabetes
Global Validation of a Minimal-Resource Pre-Screening Model for Reduced Kidney Function in Patients With Type 2 Diabetes
Journal of the American Society of Nephrology33 (Abstract Supplement), 681 (2022).