Development and prospective validation of a machine learning model to predict clinical laboratory measurements using genetic and registry data (VALID)

Project Aims

1. Develop a machine learning model that combines electronic health record and genetic data to predict commonly used clinical lab values and prospectively validate the model through recontacting.
2. To evaluate how recontacting individuals for one of these clinical lab values (eGFR) impacts medication prescription and disease diagnoses via nested randomized experiment.

Status

Currently largely pre-processing data in FinnGen Sandbox. This repo contains a selection of scripts/snippets used in Sandbox for data processing.