Trends in Interactive Knowledge Discovery for Personalized Medicine: Cognitive Science meets Machine Learning

A grand goal of future medicine is in modelling the complexity of patients to tailor medical decisions, health practices and therapies to the individual patient. This trend towards personalized medicine produces unprecedented amounts of data, and even though the fact that human experts are excellent at pattern recognition in dimensions of ≤ 3, the problem is that most biomedical data is in dimensions much higher than 3, making manual analysis difficult and often impossible. Experts in daily medical routine are decreasingly capable of dealing with the complexity of such data. Moreover, they are not interested the data, they need knowledge and insight in order to support their work. Consequently, a big trend in computer science is to provide efficient, useable and useful computational methods, algorithms and tools to discover knowledge and to interactively gain insight into high-dimensional data. A synergistic combination of methodologies of two areas may be of great help here: Human–Computer Interaction (HCI) and Knowledge Discovery/Data Mining (KDD), with the goal of supporting human intelligence with machine learning. A trend in both disciplines is the acquisition and adaptation of representations that support efficient learning. Mapping higher dimensional data into lower dimensions is a major task in HCI, and a concerted effort of computational methods including recent advances from graphtheory and algebraic topology may contribute to finding solutions. Moreover, much biomedical data is sparse, noisy and timedependent, hence entropy is also amongst promising topics. This paper provides a rough overview of the HCI-KDD approach and focuses on three future trends: graph-based mining, topological data mining and entropy-based data mining.