Methods Inf Med 1993; 32(01): 55-58
DOI: 10.1055/s-0038-1634888
Original Article
Schattauer GmbH

A Genetic Algorithm to Improve a Neural Network to Predict a Patient’s Response to Warfarin

M. N. Narayanan
1   Dept of Haematology, Manchester Royal Infirmary, and Faculty of Medicine Computational Group, The Medical School, Manchester University, Manchester, UK
,
S. B. Lucas
1   Dept of Haematology, Manchester Royal Infirmary, and Faculty of Medicine Computational Group, The Medical School, Manchester University, Manchester, UK
› Author Affiliations
Further Information

Publication History

Publication Date:
06 February 2018 (online)

Abstract:

The ability of neural networks to predict the international normalised ratio (INR) for patients treated with Warfarin was investigated. Neural networks were obtained by using all the predictor variables in the neural network, or by using a genetic algorithm to select an optimal subset of predictor variables in a neural network. The use of a genetic algorithm gave a marked and significant improvement in the prediction of the INR in two of the three cases investigated. The mean error in these cases, typically, reduced from 1.02 ± 0.29 to 0.28 ± 0.25 (paired t-test, t = −4.71, p <0.001, n = 30). The use of a genetic algorithm with Warfarin data offers a significant enhancement of the predictive ability of a neural network with Warfarin data, identifies significant predictor variables, reduces the size of the neural network and thus the speed at which the reduced network can be trained, and reduces the sensitivity of a network to over-training.

 
  • REFERENCES

  • 1 Shinton NK. ed. Guidelines on Oral Coagulation. British Society for Haematology. 1984
  • 2 Gilman AG, Rail TW, Nies AS, Taylor P. eds. The Pharmacological Basis of Therapeutics. 8th ed.. New York: Pergamon Press; 1990
  • 3 Poller L. Guidelines on Oral Coagulation. 2nd edition J Clin Pathol 1990; 43: 177-83.
  • 4 Lee C, Coleman RW, Mungall DR. Effect of using Warfarin plasma concentrations in Bayesian forecasting of prothrombin-time response. Clin Pharm 1987; 06: 406-12.
  • 5 Farrow L, Mungall D, Raskob G, Hull R. Predicting the daily prothrombin time response to Warfarin. Ther Drug Monit 1990; 12: 246-9.
  • 6 Carter BL, Barr W, Rock W, Taylor JW. Warfarin dosage predictions assisted by analog computer. Ther Drug Monit 1988; 10: 69-73.
  • 7 Ryan PJ, Gilbert M, Rose PE. Computer control of anticoagulant dose for therapeutic management. Br Med J 1989; 299: 1207-9.
  • 8 Kubie A, James AH, Timms J, Britt RP. Experience with a computer-assisted anticoagulant clinic. Clin Lab Haemat 1989; 11: 385-91.
  • 9 Van den Besselaar AMHP. Recommended method for reporting therapeutic control of oral anticoagulant therapy. Thromb and Haemostas 1990; 63: 316-7.
  • 10 Goldberg DE. Genetic Algorithms in Search, Optimization and Machine Learning. 1st ed.. Reading, Mass: Addison-Wesley Publ Comp; 1989: 1-2.
  • 11 Beale R, Jackson T. Neural Computing: An Introduction. 1st ed.. Bristol: Adam Hilger; 1990: 63-105.