NEURAL-NETWORK PREDICTED PEAK AND TROUGH GENTAMICIN CONCENTRATIONS

被引:99
作者
BRIER, ME
ZURADA, JM
ARONOFF, GR
机构
[1] DEPT VET AFFAIRS, LOUISVILLE, KY USA
[2] UNIV LOUISVILLE, DEPT MED, LOUISVILLE, KY 40292 USA
[3] UNIV LOUISVILLE, DEPT PHARMACOL, LOUISVILLE, KY USA
[4] UNIV LOUISVILLE, DEPT ELECT ENGN, LOUISVILLE, KY USA
关键词
NEURAL NETWORKS; NONMEM; PHARMACOKINETICS; PREDICTION; GENTAMICIN;
D O I
10.1023/A:1016260720218
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Predictions of steady state peak and trough serum gentamicin concentrations were compared between a traditional population kinetic method using the computer program NONMEM to an empirical approach using neural networks. Predictions were made in 111 patients with peak concentrations between 2.5 and 6.0 mu g/ml using the patient factors age, height, weight, dose, dose interval, body surface area, serum creatinine, and creatinine clearance. Predictions were also made on 33 observations that were outside the 2.5 and 6.0 mu g/ml range. Neural networks made peak serum concentration predictions within the 2.5-6.0 mu g/ml range with statistically less bias and comparable precision with paired NONMEM predictions. Trough serum concentration predictions were similar using both neural networks and NONMEM. The prediction error for peak serum concentrations averaged 16.5% for the neural networks and 18.6% for NONMEM. Average prediction errors for serum trough concentrations were 48.3% for neural networks and 59.0% for NONMEM. NONMEM provided numerically more precise and less biased predictions when extrapolating outside the 2.5 and 6.0 mu g/ml range. The observed peak serum concentration distribution was multimodal and the neural network reproduced this distribution with less difference between the actual distribution and the predicted distribution than NONMEM. It is concluded that neural networks can predict serum drug concentrations of gentamicin. Neural networks may be useful in predicting the clinical pharmacokinetics of drugs.
引用
收藏
页码:406 / 412
页数:7
相关论文
共 21 条
[1]  
Beal SL., 2022, NONMEM 7 4 USERS GUI
[2]  
BRATER DC, 1987, POCKET MANUAL DRUG U
[3]  
CAIRE P, 1992, P INT JOINT C NEUR N, P540
[4]   GENTAMICIN PHARMACOKINETICS IN NEONATES UNDERGOING EXTRACORPOREAL MEMBRANE-OXYGENATION [J].
COHEN, P ;
COLLART, L ;
PROBER, CG ;
FISCHER, AF ;
BLASCHKE, TF .
PEDIATRIC INFECTIOUS DISEASE JOURNAL, 1990, 9 (08) :562-566
[5]   APPLICATION OF NEURAL COMPUTING IN PHARMACEUTICAL PRODUCT DEVELOPMENT [J].
HUSSAIN, AS ;
YU, XQ ;
JOHNSON, RD .
PHARMACEUTICAL RESEARCH, 1991, 8 (10) :1248-1252
[6]   FEASIBILITY OF DEVELOPING A NEURAL NETWORK FOR PREDICTION OF HUMAN PHARMACOKINETIC PARAMETERS FROM ANIMAL DATA [J].
HUSSAIN, AS ;
JOHNSON, RD ;
VACHHARAJANI, NN ;
RITSCHEL, WA .
PHARMACEUTICAL RESEARCH, 1993, 10 (03) :466-469
[7]   INCREASED RATES OF CONVERGENCE THROUGH LEARNING RATE ADAPTATION [J].
JACOBS, RA .
NEURAL NETWORKS, 1988, 1 (04) :295-307
[8]  
JENSEN PD, 1992, PHARMACOTHERAPY, V12, P178
[9]   ESTIMATION OF GENTAMICIN CLEARANCE AND VOLUME OF DISTRIBUTION IN NEONATES AND YOUNG-CHILDREN [J].
KELMAN, AW ;
THOMSON, AH ;
WHITING, B ;
BRYSON, SM ;
STEEDMAN, DA ;
MAWER, GE ;
SAMBADONGA, LA .
BRITISH JOURNAL OF CLINICAL PHARMACOLOGY, 1984, 18 (05) :685-692
[10]  
LEWIN AU, 1993, P WORLD C NEURAL NET, V3, P385