Basic Principles for Calculating the Required Number of Participants in Clinical Trials. Part 1. Common Approaches (Review)

INTRODUCTION. A well-planned design of a clinical trial (CT) ensures valid results in assessing the efficacy and safety of medicines for human use. However, at present, there are no clear criteria for selecting the basic elements underlying the development of a CT design. This lack of selection criteria primarily concerns planning research hypotheses, calculating the expected therapeutic effect, statistical significance level, and study power, and selecting statistical models for sample size calculation.

AIM. The authors aimed to systematise and harmonise the technical requirements for sample size determination in designing CTs.

DISCUSSION. First, this article describes the basic requirements for and methodological approaches to designing CTs to assess the efficacy of medicines and to confirm their safety. Next, the article presents the basic principles for calculating the sample size to ensure the required CT power. Finally, the article covers the mathematical models describing the null and alternative hypotheses used in the development of basic statistical designs for efficacy and safety studies. A general requirement for the quality of a study sample is to ensure its representativeness, that is, its compliance with the target CT population. The selection of a mathematical (probabilistic) model to formulate research hypotheses and calculate study samples representative of the target population is based on general data from systematic reviews of previous studies on the therapeutic effects of the study product and the specific characteristics of the target population. In addition, model selection relies on the classification of the study product. Sample size calculation requires defining and justifying certain criteria at the stage of CT design and statistical model development, in line with the general requirements for representativeness. Software for calculating the statistical power and required sample size facilitates routine CT planning.

CONCLUSIONS. The sample size determination requires more than the application of basic statistical models. Given the multitude of CT designs and methodological approaches to CT planning, treatment regimens, and data collection and analysis, it is necessary to consider the statistical design of each CT on a case-by-case basis. This consideration should include assessments of individual cases, survival analysis methods, relative risks, diagnostic tests, and adaptive and other infrequent CT designs. The above highlights the need to develop additional guidelines and information resources that would explain and demonstrate the use of probabilistic statistics. The resulting national standards should be harmonised with international standards.

1. Moher D, Dulberg CS, Wells GA. Statistical power, sample size, and their reporting in randomized controlled trials. JAMA. 1994;272(2):122–4. https://doi.org/10.1001/jama.1994.03520020048013

2. Thabane L. Sample size determination in clinical trials. HRM-733 Class Notes. Hamilton: St Joseph’s Healthcare, 2004.

3. Altman DG. Statistics and ethics in medical research. III. How large a sample? BMJ. 1980;281(6251):1336–8. https://doi.org/10.1136/bmj.281.6251.1336

4. Petrie A, Sabin K. Medical statistics at a glance. Moscow: GEOTAR-MED; 2003 (In Russ.).

5. Zodpey SP. Sample size and power analysis in medical research. Indian J Dermatol Venereol Leprol. 2004;70(2):123–8. PMID: 17642587

6. Araujo P, Frøyland L. Statistical power and analytical quantification. J Chromatogr B Analyt Technol Biomed Life Sci. 2007;847(2):305–8. https://doi.org/10.1016/j.jchromb.2006.10.002

7. Eng J. Sample size estimation: how many individuals should be studied? Radiology. 2003;227(2):309–13. https://doi.org/10.1148/radiol.2272012051

8. Cohen J. Statistical power analysis for the behavioral sciences. New York: Routledge; 1988. https://doi.org/10.4324/9780203771587

9. Lenth RV. Some practical guidelines for effective sample size determination. Am Stat. 2001;55(3):187–93. https://doi.org/10.1198/000313001317098149

10. Dubey SD. Some thoughts on the one-sided and two-sided tests. J Biopharm Stat. 1991;1(1):139–50. https://doi.org/10.1080/10543409108835011

11. Bland JM, Altman DG. One and two sided tests of significance. BMJ. 1994;309(6949):248. https://doi.org/10.1136/bmj.309.6949.248

12. Matthews JN. Introduction to randomized controlled clinical trials. New York: Chapman & Hall; 2006. https://doi.org/10.1201/9781420011302

13. Lehr R. Sixteen S-squared over D-squared: a relation for crude sample size estimates. Stat Med. 1992;11(8):1099–102. https://doi.org/10.1002/sim.4780110811

14. Machin D, Campbell MJ. Statistical tables for the design of clinical trials. Blackwell Scientific Publications; 1995. https://doi.org/10.1002/sim.4780071211

15. Pocock SJ. Clinical trials: a practical approach. Wiley & Sons; 2013. https://doi.org/10.1002/9781118793916

16. Armitage P, Berry G. Statistical methods in medical research. Oxford: Blackwell Scientific Publications; 2002. https://doi.org/10.1002/9780470773666

17. Fleiss JL. General design issues in efficacy, equivalency and superiority trials. J Periodontal Res. 1992;27(4 Pt 2):306–13. https://doi.org/10.1111/j.1600-0765.1992.tb01684.x

18. Christensen Е. Methodology of superiority vs. equivalence trials and non-inferiority trials. J Hepatol. 2007;46(5):947–54. https://doi.org/10.1016/j.jhep.2007.02.015

19. Garrett AD. Therapeutic equivalence: fallacies and falsification. Stat Med. 2003;22(5):741–62. https://doi.org/10.1002/sim.1360

20. Blackwelder WC. “Proving the null hypothesis” in clinical trials. Control Clin Trials. 1982;3(4):345–53. https://doi.org/10.1016/0197-2456(82)90024-1

21. Greene WL, Concato J, Feinstein AR. Claims of equivalence in medical research: are they supported by the evidence? Ann Intern Med. 2000;132(9):715–22. https://doi.org/10.7326/0003-4819-132-9-200005020-00006

22. Costa LJ, Xavier AC, Giglio A. Negative results in cancer clinical trials — equivalence or poor accrual? Control Clin Trials. 2004;25(5):525–33. https://doi.org/10.1016/j.cct.2004.08.001

23. Dimick JB, Diener-West M, Lipsett PA. Negative results of randomized clinical trials published in the surgical literature: equivalency or error? Arch Surg. 2001;136(7):796–800. https://doi.org/10.1001/archsurg.136.7.796

24. Detsky AS, Sackett DL. When was a “negative” clinical trial big enough? How many patients you needed depends on what you found. Arch Intern Med. 1985;145(4):709–12. https://doi.org/10.1001/archinte.1985.00360040141030

25. Djulbegovic B, Clarke M. Scientific and ethical issues in equivalence trials. JAMA. 2001;285(9):1206–8. https://doi.org/10.1001/jama.285.9.1206

26. Jones B, Jarvis P, Lewis JA, Ebbutt AF. Trials to assess equivalence: the importance of rigorous methods. BMJ. 1996;313(7048):36–9. https://doi.org/10.1136/bmj.313.7048.36

27. Lange S, Freitag G. Choice of delta: requirements and reality — results of a systematic review. Biomed J. 2005;47(1):12–27. https://doi.org/10.1002/bimj.200410085

28. Durrleman S, Simon R. Planning and monitoring of equivalence studies. Biometrics. 1990;46(2):329–36. https://doi.org/10.2307/2531438

29. Ebbutt AF, Frith L. Practical issues in equivalence trials. Stat Med. 1998;17(15–16):1691–701. https://doi.org/10.1002/(sici)1097-0258(19980815/30)17:15/16%3C1691::aid-sim971%3E3.0.co;2-j

30. Wiens BL. Choosing an equivalence limit for noninferiority or equivalence studies. Control Clin Trials. 2002;23(1):2–14. https://doi.org/10.1016/s0197-2456(01)00196-9

31. Chan A-W, Hróbjartsson A, Haahr MT, Gøtzsche PC, Altman DG. Empirical evidence for selective reporting of outcomes in randomized trials: comparison of protocols to published articles. JAMA. 2004;291(20):2457–65. https://doi.org/10.1001/jama.291.20.2457

32. Thomas L, Krebs CJ. A Review of statistical power analysis software. Bull Ecol Soc Am. 1997;78(2):128–39.

33. Lindley DV. The choice of sample size. Statistician. 1997;46(2):129–38. https://doi.org/10.1111/1467-9884.00068

34. Lindley DV. A statistical paradox. Biometrika. 1957;44(1/2):187–92. https://doi.org/10.2307/2333251

35. Gittins J, Pezeshk H. A behavioral Bayes method for determining the size of a clinical trial. Drug Inf J. 2000;34(2):355–63. https://doi.org/10.1177/009286150003400204

36. Gittins J, Pezeshk H. How large should a clinical trial be? J R Stat Soc Series D Stat. 2000;49(2):177–87. https://doi.org/10.1111/1467-9884.00228

37. O’Hagan A, Stevens JW, Campbell MJ. Assurance in clinical trial design. Pharm Stat. 2005;4(3):187–201. https://doi.org/10.1002/pst.175

38. Shreder OV, Bunyatyan ND, Goryachev DV, Subaev RD, Engalycheva GN, Kuznetsova AD, Kosenko VV. Mathematical prediction of the efficacy of medicinal products in preclinical studies. Bulletin of the Scientific Centre for Expert Evaluation of Medicinal Products. Regulatory Research and Medicine Evaluation. 2022;12(3):315–30 (In Russ.). https://doi.org/10.30895/1991-2919-2022-12-3-315-330

39. Karkishchenko NN. Biomedicine alternatives. Part 1. Basic principles of biomedicine and pharmacomodeling. Moscow: Interacademic Publishing House of the Military Industrial Complex; 2007 (In Russ.). EDN: SOPUYN

40. Senn S. Determining the sample size. In: Statistical issues in drug development. John Wiley & Sons; 2007. https://doi.org/10.1002/9781119238614.ch13

41. Julious SA. Designing clinical trials with uncertain estimates of variability. Pharm Stat. 2004;3(4):261–8. https://doi.org/10.1002/pst.139