Evaluation of Smart Dose's predictive effectiveness on vancomycin blood concentration
10.12206/j.issn.1006-0111.202009010
- VernacularTitle:Smart Dose对万古霉素血药浓度的预测效能评价
- Author:
Yan LI
1
;
Lizhi CHEN
1
;
Xuebin WANG
1
;
Yunyun YANG
1
;
Xiaolin YANG
1
;
Zhuo WANG
1
Author Information
1. Department of Pharmacy, Changhai Hospital Affiliated to Naval Medical University, Shanghai 200433, China.
- Keywords:
vancomycin;
therapeutic drug monitoring;
software
- From:
Journal of Pharmaceutical Practice
2021;39(2):164-168
- CountryChina
- Language:Chinese
-
Abstract:
Objective To evaluate clinical utility of the personalized drug delivery decision support system, Smart Dose, applied to the monitoring of therapeutic drugs in Chinese population. Methods Use Smart Dose system to predict the trough concentration of vancomycin in patients, analyze the difference between the predicted value and the measured value of the trough concentration, and to evaluate the prediction performance of the system for vancomycin blood concentration. Results Smart Dose adjusts the difference between the predicted value of concentration and the measured value, the average percentage error, and the average absolute percentage error is less than the difference between the predicted value of initial concentration and the measured value. The difference between the initial concentration prediction value and the measured value of the neurosurgery group was smaller than that of the non-neurosurgery group, and the prediction efficiency was better than that of the non-neurosurgery group. The predicted initial concentration of the high trough concentration group and the low-age group (<59 years old) are closer to the measured value. The predictive performance of different BMI for the initial concentration is similar. Conclusion Smart Dose system is more suitable for predicting the adjusted concentration of vancomycin; When used for initial concentration prediction, the prediction values of neurosurgery group, high trough concentration, and low age group are more accurate. Different BMI has similar performance in predicting initial concentration.
