• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Aligning Subjective Ratings in Clinical Decision Making
 
  • Details
  • Full
Options
2020
Presentation
Title

Aligning Subjective Ratings in Clinical Decision Making

Title Supplement
Accepted at the ECML 2020 Workshop on Machine Learning for Pharma and Healthcare Applications (PharML). Published on arXiv
Abstract
In addition to objective indicators (e.g. laboratory values), clinical data often contain subjective evaluations by experts (e.g. disease severity assessments). While objective indicators are more transparent and robust, the subjective evaluation contains a wealth of expert knowledge and intuition. In this work, we demonstrate the potential of pairwise ranking methods to align the subjective evaluation with objective indicators, creating a new score that combines their advantages and facilitates diagnosis. In a case study on patients at risk for developing Psoriatic Arthritis, we illustrate that the resulting score (1) increases classification accuracy when detecting disease presence/absence, (2) is sparse and (3) provides a nuanced assessment of severity for subsequent analysis.
Author(s)
Pick, Annika  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Ginzel, Sebastian  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Rüping, Stefan  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Sander, Jil  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Foldenauer, Ann Christina
Fraunhofer IME-TMP, Fraunhofer CIMD
Köhm, Michaela
Fraunhofer IME-TMP, Fraunhofer CIMD
Project(s)
ML2R
Funder
Bundesministerium für Bildung und Forschung BMBF (Deutschland)  
Conference
Workshop on Machine Learning for Pharma and Healthcare Applications (PharML) 2020  
File(s)
Download (196.41 KB)
Rights
Use according to copyright law
DOI
10.24406/publica-fhg-408803
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • Clinical Data

  • Ranking SVM

  • Data Integration

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024