Using Rule-Based Decision Trees to Digitize Legislation

This article introduces a novel approach to digitize legislation using rule based-decision trees (RBDTs). As regulation is one of the major barriers innovation, methods for helping stakeholders better understand, and conform to, are becoming increasingly important. Newly introduced medical device has resulted in an increased complexity regulatory strategy manufacturers, pressure on notified body resources support this process making increasing concern industry. paper explores real-world classification problem that arises manufacturers when they want be certified according In Vitro Diagnostic Regulation (IVDR). A modification existing RBDT algorithm (RBDT-1C) case study demonstrates how method can applied. The RBDT-1C used design decision tree classify IVD devices their risk-based classes: Class A, B, C D. applied demonstrated accurate in-line with published ground-truth data. should enable users understand legislation, informed policy makers about potential areas future guidance, allowed identification errors regulations have already been recognized amended by European Commission.