Knowledge Representation for Computer-Aided Planning of Controlled Clinical Trials: the PATriCIa Project

The main thesis of the PATriCIa project is that a knowledge-based system can provide efficient and reliable support for biometricians as well as physicians involved in planning of controlled clinical trials, resulting in a higher quality of medical research. Structure and contents of study protocols are analyzed, and an object-oriented method for formally representing biometric knowledge is proposed. A study protocol can be generated from this formal representation. The programming language Prolog is used to realize the system based on a blackboard architecture. It is concluded that the knowledge representation method developed in the PATriCIa project is well suited for the purpose of generating study protocols for controlled clinical trials.

Keywords

Controlled Clinical Trials - Study Protocols - Knowledge-based System

• REFERENCES

• 1 Altman DG. Practical Statistics for Medical Research. London: Chapman and Hall; 1991
• 2 Friedman LM, Furberg CD, DeMets DL. Fundamentals of Clinical Trials. 2nd ed. Littleton: PSG Publishing Company; 1985
• 3 Pocock SJ. Clinical Trials. A Practical Approach. Chichester: Wiley; 1983
• 4 CPMP Working Party on Efficacy of Medicinal Products. Good Clinical Practice for Trials on Medicinal Products in the European Community, note for guidance. Brussels: Commission of the European Communities, Directorate-General for Internal Market and Industrial Affairs, Committee for Proprietary Medicinal Products; 1990
• 5 Andersen B. Methodological Errors in Medical Research (reprint). Oxford: Blackwell; 1991
• 6 Moher D, Dulberg CS, Wells GA. Statistical power, sample size, and their reporting in randomized controlled trials. JAMA 1994; 272: 122-4.
• 7 Altman DG, De Stavola BL, Love SB, Stepniewska KA. Review of survival analyses published in cancer journals. Br J Cancer 1995; 72: 511-8.
• 8 Goldin i, Zhu W, Sayre JW. A review of the statistical analysis used in papers published in Clinical Radiology and British Journal of Radiology. Clin Radiol 1996; 51: 47-50.
• 9 Rasch D, Darius P. Computer aided design of experiments. In: Dirschedl P, Ostermann R. Computational Statistics. Heidelberg: Physica; 1994: 187-210.
• 10 Gale WA, Hand DJ, Kelly AE. Statistical applications of Artificial Intelligence. In: Rao CR. Handbook of Statistics. Vol. 9: Computational Statistics. Amsterdam: North- Holland; 1993: 535-76.
• 11 Haag U. Knowledge-based systems in statistics. A tutorial overview with examples. In: Dirschedl P, Ostermann R. eds. Computational Statistics. Heidelberg: Physica; 1994: 211-36.
• 12 Haag U. Knowledge-based systems in statistics: critical review of a decade of research. CSDA 1994; 18: 373-5.
• 13 Jockei KH. Statistical expert systems and the statistical consultant - considerations about the planning stage of clinical studies. In: Haux R. ed. Expert Systems in Statistics. Stuttgart: Fischer; 1986: 27-43.
• 14 Haag U, Antes G, Bismarck M, Haux R, Holle R, Neiß A, Nürnberg G. Knowledge- based planning of clinical trials. In: Faulbaum F. ed. SoflStat’91. Advances in Statistical Software 3. Stuttgart: Fischer; 1992: 13-8.
• 15 Wyatt JC, Altman DG, Heathfield HA, Pantin CFA. Development of Design-aTrial, a knowledge-based critiquing system for authors of clinical trial protocols. Com- put Meth Progr Biomed 1994; 43: 283-91.
• 16 Meinert CL. Clinical Trials. Design, Conduct, and Analysis. New York: Oxford University Press; 1986
• 17 World Medical Association. Declaration of Helsinki. Femey-Voltaire: World Medical Association; 1989
• 18 CPMP Working Party on Efficacy of Medicinal Products. Biostatistical Methodology in Clinical Trials in Applications for Marketing Authorizations for Medicinal Products, note for guidance. Brussels: Commission of the European Communities, Directorate-General for Internal Market and Industrial Affairs, Committee for Proprietary Medicinal Products; 1994
• 19 Booch G. Object Oriented Design, with Applications. Redwood City: Benjamin/ Cummings; 1991
• 20 Minski M. A Framework for Representing Knowledge. Artificial Intelligence Memo 306, MIT AI-Laboratory. 1974
• 21 Hayes-Roth B. A blackboard architecture for control. Artif Intell 1985; 26: 251-321.
• 22 Nii HP. Blackboard systems: The blackboard model of problem solving and the evolution of blackboard architectures (part one). The AI Magazine 1986; 07: 38-53.
• 23 Nii HP. Blackboard systems: Blackboard application systems, blackboard systems from a knowledge engineering perspective (part two). The AI Magazine 1986; 07: 82-106.