Estudio clínico de superioridad

Supuestos

El control activo tiene una tasa de éxito de 75 ± 5%. Se espera que BD tenga una tasa de éxito del 95 ± 5% en el seguimiento a dos años.

Paquetes

library("TrialSize")

Formula

Chow S, Shao J, Wang H. 2008. Sample Size Calculations in Clinical Research. 2nd Ed. Chapman & Hall/CRC Biostatistics Series. page 90.

Argumentos

• alpha significance level
• beta power = 1-beta
• p1 the mean response rate for test drug
• p2 the rate for reference drug
• k k=n1/n2
• delta delta=p1-p2
• margin the superiority or non-inferiority margin

TwoSampleProportion.NIS(alpha = 0.05, 
                        beta = 0.2, 
                        p1 = 0.95, 
                        p2 = 0.75, 
                        k = 1, 
                        delta = 0.2, 
                        margin = 0.05)

[1] 64.57338

Resultados

Al finalizar los 24 meses, deberían haber 32 pacientes en cada grupo para evaluar una diferencia de 0.2 (0.95 - 0.75) con una hipótesis de superioridad.

Asumiendo una atrición de 15% cada 12 meses (30% en total) y un compliance del 95%, deberían comenzar el estudio con dos grupos de 41 pacientes cada uno.

Consideraciones

Ho: p1 − p2 ≤ margin Ha: p1-p2 > margin

if margin >0, the rejection of Null Hypothesis indicates the true rate p1 is superior over the reference value p2;

if margin <0, the rejection of the null hypothesis implies the true rate p1 is non-inferior against the reference value p2.

Lecturas recomendadas

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2014556/

https://www.rdocumentation.org/packages/TrialSize/versions/1.3

Información adicional

Realizado en R + Rstudio

sessionInfo()

R version 3.4.1 (2017-06-30)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 14.04.5 LTS

Matrix products: default
BLAS: /usr/lib/libblas/libblas.so.3.0
LAPACK: /usr/lib/lapack/liblapack.so.3.0

locale:
 [1] LC_CTYPE=es_CL.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=es_CL.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=es_CL.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] TrialSize_1.3

loaded via a namespace (and not attached):
 [1] Rcpp_0.12.12    packrat_0.4.8-1 digest_0.6.12   rprojroot_1.2  
 [5] jsonlite_1.5    backports_1.1.0 magrittr_1.5    evaluate_0.10.1
 [9] stringi_1.1.5   rmarkdown_1.6   tools_3.4.1     stringr_1.2.0  
[13] rsconnect_0.8.5 yaml_2.1.14     compiler_3.4.1  base64enc_0.1-3
[17] htmltools_0.3.6 knitr_1.17