Imputation

Imputation refers to statistical methods for creating data when it is missing from a data set. Missing data is often not random (and can therefore lead to different forms of bias). Imputation theoretically improves research outcomes as opposed to simply discarding incomplete data subsets. Several methods have traditionally been used to impute single missing values which included linear regression i.e. replacing the missing value with a value that would fit a linear regression line and substituting the missing value with the mean of the entire data set, but various AI models can be used as well.  Multiple imputation methodologies are increasingly reported in academic medical research generally ¹ and have been utilized in radiology research specifically ³. In AI models, imputed data could be considered a subset of synthetic data.