Entropy Removal of Medical Diagnostics

Abstract

Abstract Shannon entropy is a core concept in machine learning and information theory, particularly in decision tree modeling. Decision tree representations of medical decision-making tools can be generated using diagnostic metrics found in literature and entropy removal can be calculated for these tools. This analysis was done for 623 diagnostic tools and provided unique insights into the utility of such tools. This concept of clinical entropy removal has significant potential for further use to bring forth healthcare innovation, such as the quantification of the impact of clinical guidelines and value of care and applications to Emergency Medicine scenarios where diagnostic accuracy in a limited time window is paramount. For studies that provided detailed data on medical decision-making algorithms, bootstrapped datasets were generated from source data in order to perform comprehensive machine learning analysis on these algorithms and their constituent steps, which revealed a novel thorough evaluation of medical diagnostic algorithms.