*Purpose: iBox is a validated cloud-based software as a service (SaaS) algorithm that provides a predictive analysis of the post-transplant patient, quantifying the risk of kidney loss based upon multiple pre-determined clinical factors in kidney transplant scenarios at any time point following surgery as long as the inputs necessary are available. iBox mandatory inputs include: 1. time from transplant to risk evaluation; 2. estimated GFR (mL/min/1,73m²); and 3. proteinuria (g/g of creatinine/total protein). Additional inputs that improve the accuracy include DSA MFI, scores for Banff indices (g,i,t, ptc,cg,ci,ct) or diagnoses based on pathology (ABMR, TCMR, CNI, Recurrence, BK, AKI). The output result includes allograft loss probabilities for 1, 3 and 5 years from evaluation time, and potential stratification based on renal function trajectory prediction. The objective of this study was to characterize the iBox algorithm using a smaller cohort of patients from 14 centers who were prospectively surveyed in the DART study over 12 months (ClinicalTrials.gov Identifier: NCT02424227). Due to the small sample size and short time window, the analysis assessed the ability of iBox iBox to predict a surrogate for graft loss, eGFR<20. Donor derived cell free DNA (dd-cfDNA), not currently included in the iBox algorithm, was independently considered as a predictor of outcome at 12 months.

*Methods: 185 patients from DART had sufficient data to complete the mandatory inputs required for iBox. Within 12 months of follow up, these patients had a total of 9 events, defined as eGFR<20 without return to higher eGFR. iBox scores were calculated at the 7 time points used in the surveillance protocol: months 1,2,3,4,6,9 and 12. This population was representative of patients followed through standard of care practice in US kidney transplant programs.

*Results: DART data did not have complete parameters for iBox at each time-point; for example biopsies were not done at each point; the best model possible for each sample was used. Within this set of samples 19.5% included both DSA and biopsy. Using the best fit model for each sample a C-statistic of 0.83 was obtained for iBox prediction of these events in the 185 DART patients (standard error 0.1). iBox 1-year prognostication scores measured for the samples were not correlated with dd-cfDNA measurement at the same sample (correlation=-0.1213, p = 0.083).

*Conclusions: As transplant moves toward increasingly relying on predictions made by computer models to inform clinical decisions, knowing the iBox algorithm performs as expected in smaller cohorts when considering diagnosis and 1-year prognosis, suggests clear translational value. As the data may be complementary, the inclusion of dd-cfDNA considering allograft injury may be a valuable addition to evolve this algorithm as we improve understanding as well as consider the impact of medical interventions and treatment response on graft failure risk.

« Back to 2020 American Transplant Congress