Background and objectives Tertiary hyperparathyroidism in kidney allograft recipients is associated with bone loss, allograft dysfunction, and cardiovascular mortality. Accurate pretransplant risk prediction of tertiary hyperparathyroidism may support individualized treatment decisions.We aimed to develop an integer score system that predicts the risk of tertiary hyperparathyroidism using machine learning algorithms. Design, setting, participants, & measurementsWe used two separate cohorts: a derivation cohort with the data of kidney allograft recipients (n5669) who underwent kidney transplantation at Severance Hospital, Seoul, Korea between January 2009 and December 2015 and a multicenter registry dataset (the Korean Cohort Study for Outcome in Patients with Kidney Transplantation) as an external validation cohort (n5542). Tertiary hyperparathyroidism was defined as post-transplant parathyroidectomy. The derivation cohort was split into 75% training set (n5501) and 25% holdout test set (n5168) to develop prediction models and integer-based score. Results Tertiary hyperparathyroidism requiring parathyroidectomy occurred in 5% and 2% of the derivation and validation cohorts, respectively. Three top predictors (dialysis duration, pretransplant intact parathyroid hormone, and serum calcium level measured at the time of admission for kidney transplantation) were identified to create an integer score system (dialysis duration, pretransplant serum parathyroid hormone level, and pretransplant calcium level score [DPC]; 0–15 points) to predict tertiary hyperparathyroidism. The median DPC score was higher in participants with post-transplant parathyroidectomy than in those without (13 versus three in derivation; 13 versus four in external validation; P, 0.001 for all). Pretransplant dialysis duration, pretransplant serum parathyroid hormone level, and pretransplant calcium level score predicted post-transplant parathyroidectomy with comparable performance with the best-performing machine learning model in the test set (area under the receiver operating characteristic curve: 0.94 versus 0.92; area under the precision-recall curve: 0.52 versus 0.47). Serial measurement of DPC scores ($13 at least two or more times, 3-month interval) during 12 months prior to kidney transplantation improved risk classification for post-transplant parathyroidectomy compared with single-time measurement (net reclassification improvement, 0.28; 95% confidence interval, 0.02 to 0.54; P50.03). Conclusions A simple integer-based score predicted the risk of tertiary hyperparathyroidism in kidney allograft recipients, with improved classification by serial measurement compared with single-time measurement.
|Number of pages||10|
|Journal||Clinical Journal of the American Society of Nephrology|
|Publication status||Published - 2022 Jul|
Bibliographical noteFunding Information:
This research was supported by Korea Centers for Disease Control and Prevention grants 2012E3301100, 2013E3301600, 2013E3301601, 2013E3301602, 2016E3300200, 2016E3300201, 2016E3300202, 2019E320100, and 2019E320101 and Severance Hospital Research Fund for Clinical Excellency grant C-2019-0032.
© 2022 by the American Society of Nephrology.
All Science Journal Classification (ASJC) codes
- Critical Care and Intensive Care Medicine