Statistical Methods in Disease Risk Assessment and Prediction

今年有两项重大成就。 首先，我们开发了一个非参数和半参数回归方法的双变量故障时间的结果。这是因为许多生物医学研究跟踪参与者的多种相关健康结果。同时对这些结果进行建模可能比单个模型更有效，并允许我们描述发展多种疾病的风险，以便于在个人有其他疾病史的情况下进行风险预测。除了两篇描述这些方法的期刊手稿外，我们还出版了Chapman & Hall关于这个主题的书。 其次，我们提出了一系列的工具来表征乳腺癌风险的空间和时间分布，姐妹研究的动机。我们首先开发了一个加速失效时间模型与空间随机效应，处理个人层面的失效时间的结果与空间变化。根据这些模型的结果，可以制作疾病地图。我们进一步提出了一个二级模型评估工具，将观察到的模式与空间区域水平的风险因素联系起来。我们进一步提出了一个加速失效时间模型，允许时间和空间的影响。这个模型使我们能够识别由于有影响力的事件，如自然灾害和政策变化的影响。这些方法适用于姐妹研究。

There are two major accomplishment this year. First, we developed a nonparametric and a semiparametric regression approach for bivariate failure time outcomes. This is motivated by the fact that many biomedical studies follow participants for multiple correlated health outcomes. Modeling these outcomes simultaneously can be more efficient than individual models, and allows us to characterize the risk of developing multiple diseases to facilitate risk prediction given individuals history of other diseases. In addition to two journal manuscripts describing these approaches, we also published a book by Chapman & Hall on this topic. Second, we proposed a series of tools for characterizing the spatial and temporal distribution of breast cancer risk, motivated by the Sister Study. We first develop an accelerated failure time model with a spatial random effect, to handle individual-level failure time outcomes with spatial variation. Based on results from such models, a disease map can be produced. We further proposed a secondary model assessment tool to connect the observed pattern with spatial-area-level risk factors. We further proposed an accelerated failure time model that allows both time and space effect. This model allows us to identify effects due to influential events, such as natural disasters and policy changes. These methods are applied to the Sister Study.