1 February 2018 in Energy and Buildings
27 April 2022 in Therapeutic Apheresis and Dialysis
1 March 2022 in Annals of Vascular Surgery
1 January 2021 in Annals of Surgical Treatment and Research
Park YJ, et al. Ann Surg Treat Res. 2021 Dec;101(6):368-373. https://doi.org/10.4174/astr.2021.101.6.368
25 March 2025 in Annals of Transplantation
The optimization of tacrolimus dosing during the early postoperative hospitalization period is essential to prevent rejection, minimize nephrotoxicity, and minimize the risk of opportunistic infections. Patient pharmacokinetic variability poses challenges in dose adjustment. This study aimed to evaluate tacrolimus dosing optimization using machine learning and statistical methods. We conducted a retrospective study of 749 kidney transplant recipients at Seoul St. Mary’s Hospital between January 2015 and December 2019. Data on tacrolimus doses, trough levels, and other clinical variables were collected and analyzed during the first 12 postoperative days of hospitalization. Three approaches were evaluated: Extreme Gradient Boosting (XGBoost), Elastic Net regression (EN), and Linear regression (LR). The models were trained and validated using 5-fold cross-validation, with performance assessed using R2 errors and alignment with clinically acceptable error margins. Elastic Net showed the best performance with R2 (Coefficient of Determination) of 0.861±0.044 and RMSE (Root Mean Square Error) of 0.930±0.220. Linear Regression and XGBoost provided clinically relevant predictions but with slightly lower accuracy. External validation was not performed, limiting the generalizability of the results. The Elastic Net is a practical and reliable model for predicting the optimal tacrolimus dose. Machine learning and statistical methods are useful tools for optimizing tacrolimus dosing during hospitalization after kidney transplantation. Future studies should incorporate multi-center validation to improve clinical applicability.
23 March 2022 in Vascular
Objectives: Current guidelines recommend initial postoperative follow-up with computed tomography angiography (CTA) after endovascular aneurysm repair (EVAR). However, CTA has risks associated with ionizing radiations and nephrotoxic contrast agents. We investigated possibilities to replace the initial postoperative CTA with contrast enhanced duplex ultrasound (CE-DUS) in selected patients. Methods: Out of the 273 consecutive patients who underwent EVAR, 173 were excluded and the 100 patients who underwent CTA and CE-DUS imaging concurrently (≤1 month interval between CTA and CE-DUS imaging) within 60 days after EVAR were analyzed. Patients who underwent EVAR outside the manufacturer’s instructions for use or who had endoleaks discovered on intraoperative angiography were classified as the high-risk group, otherwise, they were classified as the low-risk group. Measurements of diagnostic values of CE-DUS related to the detection of complications were calculated using CTA as the gold standard. McNemar’s test was performed to compare these values and Pearson correlation coefficient was derived to compare CE-DUS measurements of sac diameters with CTA. Results: In the low-risk group, no difference was observed between CE-DUS and CTA in the detection of EVAR-related complications (sensitivity = 0.95, specificity = 0.93). In the high-risk group, CE-DUS was not as accurate as CTA for the detection of overall EVAR-related complications (sensitivity = 0.57, specificity = 0.86, p = 0.04) and for the detection of complications other than endoleaks ( p = 0.02). Regarding sac diameter measurement, there was good agreement between CE-DUS and CTA ( r = 0.92, p < 0.001). Conclusions: First postoperative CE-DUS was reliable for the evaluation of EVAR-related complications compared to CTA in selected patients. Individualized EVAR follow-up strategy using CE-DUS based on the initial risk of EVAR-related complications should be considered.