What makes a biostatistician?

Biostatisticians play an important role in medical research. They are co-responsible for an appropriate and efficient study design, they are involved in monitoring the study conduct, they plan and perform the data analysis, and they are involved in interpreting and publishing the results. However, how are the biostatisticians prepared for their tasks and responsibilities? Graduate programs in biostatistics are being offered, but some practicing biostatisticians completed their studies in a mathematical or epidemiological program, or obtained their degree in subject-specific fields (such as medicine or biology). Therefore, the expertise and the competencies can vary widely between the individual biostatisticians, also depending on the application field. In this article, focusing on European and US practices, we discuss the required professional expertise for the main areas of applications in the medical field as well as the necessary soft skill competencies of a biostatistician.     

筛检对肝癌死亡率影响的研究

5581名HBsAg阳性的男性随机分入周期性筛检组(A组,3712人)及对照组(B组,1869人)。A组(19155.4人年)共发生肝癌257例,B组(9785.5人年)为117例,两组的肝癌发生率分别为1342/10万与1196/10万;两组肝癌死亡分别为218与109例,肝癌死亡率分别为1138/10万与1114/10万。两组中Ⅰ期肝癌病例分别为29.6％与6.0％,差异有非常显著性意义。1、3、5年相对生存率A组为23.7％、7.0％、4.0％,B组为9.7％、4.0％、4.1％。用Poisson回归模型拟合显示,在调正年龄、初筛AFP及入列年份后,筛检对于肝癌的相对危险度为0.83,95％CI为0.68～1.03,有较弱的“保护”作用,Cox回归模型拟合结果显示当临床分期未引入模型时,筛检对于肝癌有显著的“保护”作用:危险率为0.6617,95％CI为0.5234～0.8365;而模型经调整后,危险率即接近“1”,95％CI为0.74～1.26。     

FM sonography in diffuse liver disease: prospective assessment and blinded analysis

FM sonography - a signal-processing technique that uses frequency and phase information as well as amplitude data - shows promise in evaluation of patients with diffuse liver disease. In a prospective blinded review of 37 patients with biopsy-proved liver disease and 42 healthy volunteers, FM sonography was clearly superior to traditional amplitude-based (AM) sonography in distinguishing healthy from diseased subjects. Statistically significant differences were seen in accuracy (FM, 98.7%; AM, 84.8%), sensitivity (FM, 97.3%; AM, 70.3%), and negative predictive value (FM, 97.7%; AM, 78.8%). Our data also suggest that current FM sonographic techniques cannot differentiate among histologic findings associated with different hepatic parenchymal abnormalities. It is unclear, therefore, whether FM imaging can reduce the numbers of patients who require biopsy for diagnosis or the frequency of biopsy procedures in patients with known disease.