Distributed multivariable modeling for signature development under data protection constraints

Data protection constraints frequently require distributed analysis of data, i.e. individual-level data remains at many different sites, but analysis nevertheless has to be performed jointly. The data exchange is often handled manually, requiring explicit permission before transfer, i.e. the number of data calls and the amount of data should be limited. Thus, only simple summary statistics are typically transferred and aggregated with just a single call, but this does not allow for complex statistical techniques, e.g., automatic variable selection for prognostic signature development. We propose a multivariable regression approach for building a prognostic signature by automatic variable selection that is based on aggregated data from different locations in iterative calls. To minimize the amount of transferred data and the number of calls, we also provide a heuristic variant of the approach. To further strengthen data protection, the approach can also be combined with a trusted third party architecture. We evaluate our proposed method in a simulation study comparing our results to the results obtained with the pooled individual data. The proposed method is seen to be able to detect covariates with true effect to a comparable extent as a method based on individual data, although the performance is moderately decreased if the number of sites is large. In a typical scenario, the heuristic decreases the number of data calls from more than 10 to 3. To make our approach widely available for application, we provide an implementation on top of the DataSHIELD framework.