Evolving Classification Models for Prediction of Patient Recruitment in Multicentre Clinical Trials Using Grammatical Evolution

  • Gilyana BorlikovaEmail author
  • Michael Phillips
  • Louis Smith
  • Michael O’Neill
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9597)


Successful and timely completion of prospective clinical trials depends on patient recruitment as patients are critical to delivery of the prospective trial data. There exists a pressing need to develop better tools/techniques to optimise patient recruitment in multicentre clinical trials. In this study Grammatical Evolution (GE) is used to evolve classification models to predict future patient enrolment performance of investigators/site to be selected for the conduct of the trial. Prediction accuracy of the evolved models is compared with results of a range of machine learning algorithms widely used for classification. The results suggest that GE is able to successfully induce classification models and analysis of these models can help in our understanding of the factors providing advanced indication of a trial sites’ future performance.


Clinical trials Enrolment Grammatical evolution Grammar-based genetic programming 



The authors would like to thank Thomas O’Leary, Pamela Howard and Wilhelm Muehlhausen from ICON Plc. for critical reading of the manuscript and expert advice on patient recruitment and Dr. David Fagan, Dr. Alexandros Agapitos and Stefan Forstenlechner from the UCD Natural Computing Research and Applications Group for their insightful advice on GE methodology. This research is based upon work supported by ICON plc.


  1. 1.
    Schueler, P., Buckley, B. (eds.): Re-Engineering Clinical Trials. Best Practices for Streamlining the Development Process, 1st edn. Academic Press Elsevier, Amsterdam (2014)Google Scholar
  2. 2.
    Marks, L., Power, E.: Using technology to address recruitment issues in the clinical trial process. Trends Biotechnol. 20(3), 105–109 (2002)CrossRefGoogle Scholar
  3. 3.
    Trizna, C.: Chapter 9 - no patients, no data: patient recruitment in the 21st century. In: Re-Engineering Clinical Trials. Best Practices for Streamlining the Development Process, 1st edn, pp. 91–105. Academic Press Elsevier (2014)Google Scholar
  4. 4.
    Tufts: CSDD impact report - 89% of trials meet enrolment, but timelines slip, half of sites under-enrol. 15(1) (2013)Google Scholar
  5. 5.
    Kasenda, B., von Elm, E., You, J., Blumle, A., Tomonaga, Y., Saccilotto, R., Amstutz, A., Bengough, T., Meerpohl, J.J., Stegert, M., Tikkinen, K.A.O., Neumann, I., Carrasco-Labra, A., Faulhaber, M., Mulla, S.M., Mertz, D., Akl, E.A., Bassler, D., Busse, J.W., Ferreira-Gonzalez, I., Lamontagne, F., Nordmann, A., Gloy, V., Raatz, H., Moja, L., Rosenthal, R., Ebrahim, S., Schandelmaier, S., Xin, S., Vandvik, P.O., Johnston, B.C., Walter, M.A., Burnand, B., Schwenkglenks, M., Hemkens, L.G., Bucher, H.C., Guyatt, G.H., Briel, M.: Prevalence, characteristics, and publication of discontinued randomized trials. JAMA 311, 1045–1052 (2014)CrossRefGoogle Scholar
  6. 6.
    O’Neill, M., Ryan, C.: Grammatical Evolution: Evolutionary Automatic Programming in a Arbitrary Language, Genetic programming, vol. 4. Kluwer Academic Publishers, Dordrecht (2003)CrossRefzbMATHGoogle Scholar
  7. 7.
    Dempsey, I., O’Neill, M., Brabazon, A.: Foundations in Grammatical Evolution for Dynamic Environments. SCI, vol. 194. Springer, Heidelberg (2009)Google Scholar
  8. 8.
    McKay, R.I., Hoai, N.X., Whigham, P.A., Shan, Y., O’Neill, M.: Grammar-based genetic programming: a survey. Genet. Program. Evolvable Mach. 11(3/4), 365–396 (2010). Tenth Anniversary Issue: Progress in Genetic Programming and Evolvable MachinesCrossRefGoogle Scholar
  9. 9.
    Anisimov, V.V., Fedorov, V.V.: Modelling, prediction and adaptive adjustment of recruitment in multicentre trials. Stat. Med. 26(27), 4958–4975 (2007)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Aegerter, P., Bendersky, N., Tran, T.C., Ropers, J., Taright, N., Chatellier, G.: The use of drg for identifying clinical trials centers with high recruitment potential: a feasibility study. Stud. Health Technol. Inf. 205, 783–787 (2014)Google Scholar
  11. 11.
    Kopcke, F., Lubgan, D., Fietkau, R., Scholler, A., Nau, C., Sturzl, M., Croner, R., Prokosch, H.U., Toddenroth, D.: Evaluating predictive modeling algorithms to assess patient eligibility for clinical trials from routine data. BMC Medical Informatics and Decision Making (2013)Google Scholar
  12. 12.
    Kopcke, F., Prokosch, H.U.: Employing computers for the recruitment into clinical trials: a comprehensive systematic review. J. Med. Internet Res. 16(7), 161 (2014)CrossRefGoogle Scholar
  13. 13.
    Barnard, K.D., Dent, L., Cook, A.: A systematic review of models to predict recruitment to multicentre clinical trials. BMC Medical Research Methodology 10(63) (2010)Google Scholar
  14. 14.
    Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. MORGAN KAUFMANN, San Francisco (2011)zbMATHGoogle Scholar
  15. 15.
    Koza, J.R.: Hierarchical genetic algorithms operating on populations of computer programs. In: Sridharan, N.S. (ed.) Proceedings of the Eleventh International Joint Conference on Artificial Intelligence IJCAI 1989, vol. 1, pp. 768–774. Detroit, MI, USA, Morgan Kaufmann, 20–25 August 1989Google Scholar
  16. 16.
    Koza, J.R., Keane, M.A., Streeter, M.J., Mydlowec, W., Yu, J., Lanza, G.: Genetic Programming IV: Routine Human-Competitive Machine Intelligence. Kluwer Academic Publishers, Dordrecht (2003)zbMATHGoogle Scholar
  17. 17.
    Espejo, P.G., Ventura, S., Herrera, F.: A survey on the application of genetic programming to classification. IEEE Trans. Syst. Man Cybernetics, Part C: Appl. Rev. 40(2), 121–144 (2010)CrossRefGoogle Scholar
  18. 18.
    Nicolau, M., Saunders, M., O’Neill, M., Osborne, B., Brabazon, A.: Evolving interpolating models of net ecosystem CO\(_{2}\) exchange using grammatical evolution. In: Moraglio, A., Silva, S., Krawiec, K., Machado, P., Cotta, C. (eds.) EuroGP 2012. LNCS, vol. 7244, pp. 134–145. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  19. 19.
    Brabazon, A., O’Neill, M.: Diagnosing corporate stability using grammatical evolution. Int. J. Appl. Math. Comput. Sci. 14(3), 363–374 (2004)zbMATHGoogle Scholar
  20. 20.
    Brabazon, A., O’Neill, M.: Credit classification using grammatical evolution. Informatica 30(3), 325–335 (2006)zbMATHGoogle Scholar
  21. 21.
    Tuite, C., Agapitos, A., O’Neill, M., Brabazon, A.: A preliminary investigation of overfitting in evolutionary driven model induction: implications for financial modelling. In: Di Chio, C., et al. (eds.) EvoApplications 2011, Part II. LNCS, vol. 6625, pp. 120–130. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  22. 22.
    Kuhn, M.: Building predictive models in r using the caret package. J. Stat. Softw. 28(5), 1–26 (2008)CrossRefGoogle Scholar
  23. 23.
    Ryan, C., Azad, R.M.A.: Sensible initialisation in grammatical evolution. In: Barry, A.M. (ed.) GECCO 2003: Proceedings of the Bird of a Feather Workshops, Genetic and Evolutionary Computation Conference, AAAI 142–145 (2003)Google Scholar
  24. 24.
    Agapitos, A., O’Neill, M., Brabazon, A.: Evolving seasonal forecasting models with genetic programming in the context of pricing weather-derivatives. In: Di Chio, C., et al. (eds.) EvoApplications 2012. LNCS, vol. 7248, pp. 135–144. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  25. 25.
    Kuhn, M., Johnson, K.: Applied Predictive Modeling. Springer, New York (2013)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Gilyana Borlikova
    • 1
    Email author
  • Michael Phillips
    • 2
  • Louis Smith
    • 2
  • Michael O’Neill
    • 1
  1. 1.Natural Computing Research and Applications Group, School of BusinessUniversity College DublinDublinIreland
  2. 2.ICON PlcDublinIreland

Personalised recommendations