Pharmaceutical Research

, Volume 12, Issue 3, pp 406–412 | Cite as

Neural Network Predicted Peak and Trough Gentamicin Concentrations

  • Michael E. Brier
  • Jacek M. Zurada
  • George R. Aronoff


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 µg/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 µg/ml range. Neural networks made peak serum concentration predictions within the 2.5-6.0 µg/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 µg/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.

neural networks NONMEM pharmacokinetics prediction gentamicin 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. M. Zurada. Introduction to artificial neural systems. St Paul MN: West Publishing Company, 1992.Google Scholar
  2. 2.
    P. Veng-Pedersen and N. B. Modi. Application of neural networks to pharmacodynamics. J. Pharm. Sci. 82:918–926 (1993).Google Scholar
  3. 1.
    Brater D. C. Pocket Manual of drug use in clinical medicine 3rd Edition. Philadelphia, PA: B.C. Decker Inc., 1987.Google Scholar
  4. 2.
    R. A. Jacobs. Increased rates of convergence through learning rate adaptation. Neural Networks. 1:295–307 (1988).Google Scholar
  5. 3.
    A. A. Minai and R. D. Williams. Acceleration of back-propagation through learning rate and momentum adaptation. International Joint Conference on Neural Networks. 1:676–679 (1990).Google Scholar
  6. 4.
    NONMEM Users Guides. S. L. Beal and L. B. Sheiner (Eds) NONMEM Project Group, University of California at San Francisco, San Francisco, 1992.Google Scholar
  7. 5.
    L. B. Sheiner and S. L. Beal. Some suggestions for measuring predictive performance. J. Pharmacokin. Biopharm. 9:503–512 (1981).Google Scholar
  8. 6.
    J. R. Varvel, D. L. Donoho and S. L. Shafer. Measuring the predictive performance of computer-controlled infusion pumps. J. Pharmacokin. Biopharm. 20:63–94 (1992).Google Scholar
  9. 7.
    M. M. Reidenberg. Trends in clinical pharmacokinetics. Clin. Pharmacokinet. 24:1–9 (1993).Google Scholar
  10. 8.
    A. W. Kelman, A. H. Thomson, B. Whiting, S. M. Bryson, D. A. Steedman, G. E. Mawer and L. A. Samba-Donga. Estimation of gentamicin clearance and volume of distribution in neonates and young children. Bj. J. Clin. Pharmac. 18:685–692 (1984).Google Scholar
  11. 9.
    A. H. Thomson, S. Way, S. M. Bryson, E. M. McGovern, A. W. Kelman and B. Whitting. Population pharmacokinetics of gentamicin in neonates. Dev. Pharmacol. Ther. 11:173–179 (1988).Google Scholar
  12. 10.
    P. Cohen, L. Collart, C. G. Prober, A. F. Fischer and T. F. Blaschke. Gentamicin pharmacokinetics in neonates undergoing extracoporal membrane oxygenation. Pediatr. Infect. Dis. J. 9:562–566 (1990).Google Scholar
  13. 11.
    P. D. Jensen, B. E. Edgren and R. C. Brundage. Population pharmacokinetics of gentamicin in neonates using nonlinear, mixed-effects models. Pharmacotherapy 12:178–182 (1992).Google Scholar
  14. 12.
    A. U. Lewin. Predicting with feedforward networks. Proc. of the World Congress on Neural Networks. III:385–388 (1993).Google Scholar
  15. 13.
    A. S. Weigend and N. A. Gershenfeld. Results of the time series prediction competition at the Santa Fe Institute. Proc. of the World Congress on Neural Networks IV:663–670 (1993).Google Scholar
  16. 14.
    J. A. Sims and C. P. Snyder. Implementing Neural Networks. Ch. 6, book to be published in 1993 by DEC, Waynard, Mass.Google Scholar
  17. 15.
    D. C. Park, M. A. Elsharkawi, R. J. Marks, L. E. Atlas and M. J. Dambarg. Electric Load Forecasting Using Artificial Neural Network, IEEE Trans. on Power Systems, 6:442–449 (1991).Google Scholar
  18. 16.
    P. Caire, C. Hatabian and C. Muller. Progress in Forecasting by Neural Networks, Proc. of the Intern. Joint Conf. on Neural Networks, Baltimore, MD. 540–545 (1992).Google Scholar
  19. 17.
    A. S. Hussain X. Yu and R. D. Johnson. Application of neural computing in pharmaceutical product development. Pharm. Res. 8:1248–1252 (1991).Google Scholar
  20. 18.
    P. Veng-Pedersen and N. B. Modi. Neural networks in pharmacodynamic modeling. Is current modeling practice of complex kinetic systems at a dead end? J. Pharmacokin. Biopharm. 20: 397–412 (1992).Google Scholar
  21. 19.
    A. S. Hussain, R. D. Johnson, N. N. Vachharajani and W. A. Ritschel. Feasibility of developing a neural network for prediction of human pharmacokinetics parameters from animal data. Pharm. Res. 10:466–469 (1993).Google Scholar

Copyright information

© Plenum Publishing Corporation 1995

Authors and Affiliations

  • Michael E. Brier
    • 1
    • 2
    • 3
  • Jacek M. Zurada
    • 4
  • George R. Aronoff
    • 2
    • 3
  1. 1.Department of Veterans AffairsUniversity of LouisvilleLouisville
  2. 2.Department of MedicineUniversity of LouisvilleLouisville
  3. 3.Department of PharmacologyUniversity of LouisvilleLouisville
  4. 4.Department of Electrical EngineeringUniversity of LouisvilleLouisville

Personalised recommendations