Optimizing Tacrolimus Dosing During Hospitalization After Kidney Transplantation: A Comparative Model Analysis

01 April 2025 : Original article

Sangkyun Mok

^{ABCDEF 1}, Sun Cheol Park

^{ABDEF 2*}, Sang Seob Yun^{AF 2}, Young Jun Park

^{AF 3}, Dongin Sin^{CD 4}, Jung K. Hyun

^{CD 5}

DOI: 10.12659/AOT.947768

Ann Transplant 2025; 30:e947768

Authors information Article notes Copyright and License information

Introduction Material and Methods Results Discussion Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Table 9 Tacrolimus trough level prediction performance metrics.

Model	Split	R2	MAE	MAPE	MSE	RMSE
XGBoost	0	0.136	1.659	0.199	6.593	2.568
	1	0.371	1.622	0.222	4.326	2.08
	2	0.237	1.382	0.176	3.575	1.891
	3	0.267	1.789	0.251	4.93	2.22
	4	0.309	1.786	0.215	6.142	2.478
Average (Split=5) (mean±SD)		0.264±0.087	1.648±0.166	0.213±0.028	5.113±1.252	2.247±0.279
Linear regression	0	0.058	1.706	0.198	7.187	2.681
	1	0.379	1.621	0.224	4.269	2.066
	2	0.27	1.377	0.174	3.417	1.849
	3	0.367	1.601	0.227	4.257	2.063
	4	0.276	1.808	0.215	6.431	2.536
Average (Split=5) (mean±SD)		0.270±0.129	1.623±0.160	0.208±0.022	5.112±1.610	2.239±0.352
Elastic net regression	0	0.082	1.676	0.194	6.998	2.645
	1	0.387	1.61	0.223	4.213	2.053
	2	0.281	1.368	0.174	3.367	1.835
	3	0.372	1.604	0.228	4.222	2.055
	4	0.267	1.822	0.217	6.508	2.551
Average (Split=5) (mean±SD)		0.278±0.122	1.616±0.164	0.207±0.023	5.062±1.592	2.228±0.351
R – coefficient of determination; MAE – mean absolute error; MAPE – mean absolute percentage error; MSE – mean squared error; RMSE – root mean square error.

Back to the Article