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

Research output: Contribution to journalArticle

Abstract

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 graph-theory and algebraic topology may contribute to finding solutions. Moreover, much biomedical data is sparse, noisy and time-dependent, 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
LanguageEnglish
Pages6-14
JournalThe IEEE intelligent informatics bulletin
Volume15
Issue number1
StatusPublished - 2014

Fingerprint

Medicine
Data mining
Learning systems
Human computer interaction
Computational methods
Entropy
Graph theory
Computer science
Pattern recognition
Topology
Health

Keywords

  • Machine Learning
  • Health Informatics
  • Knowledge Discovery
  • HCI-KDD

ASJC Scopus subject areas

  • Artificial Intelligence

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Review

Cite this

@article{a383e1c674f04801abfa4b8fb6d97203,
title = "Trends in Interactive Knowledge Discovery for Personalized Medicine: Cognitive Science meets Machine Learning",
abstract = "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 graph-theory and algebraic topology may contribute to finding solutions. Moreover, much biomedical data is sparse, noisy and time-dependent, 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",
keywords = "Machine Learning, Health Informatics, Knowledge Discovery, HCI-KDD",
author = "Andreas Holzinger",
year = "2014",
language = "English",
volume = "15",
pages = "6--14",
journal = "The IEEE intelligent informatics bulletin",
issn = "1727-5997",
number = "1",

}

TY - JOUR

T1 - Trends in Interactive Knowledge Discovery for Personalized Medicine: Cognitive Science meets Machine Learning

AU - Holzinger,Andreas

PY - 2014

Y1 - 2014

N2 - 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 graph-theory and algebraic topology may contribute to finding solutions. Moreover, much biomedical data is sparse, noisy and time-dependent, 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

AB - 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 graph-theory and algebraic topology may contribute to finding solutions. Moreover, much biomedical data is sparse, noisy and time-dependent, 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

KW - Machine Learning

KW - Health Informatics

KW - Knowledge Discovery

KW - HCI-KDD

M3 - Article

VL - 15

SP - 6

EP - 14

JO - The IEEE intelligent informatics bulletin

T2 - The IEEE intelligent informatics bulletin

JF - The IEEE intelligent informatics bulletin

SN - 1727-5997

IS - 1

ER -