Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Aligning Subjective Ratings in Clinical Decision Making

Accepted at the ECML 2020 workshop on Machine Learning for Pharma and Healthcare Applications (PharML)
: Pick, Annika; Ginzel, Sebastian; Rüping, Stefan; Sander, Jil; Foldenauer, Ann Christina; Köhm, Michaela

Volltext urn:nbn:de:0011-n-6023714 (196 KByte PDF)
MD5 Fingerprint: f21ce0bdede26c643b3b6638be77e1de
Erstellt am: 17.9.2020

Online im WWW, 2020, arXiv:2009.06403, 6 S.
Workshop on Machine Learning for Pharma and Healthcare Applications (PharML) <2020, Ghent>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01IS18038B; ML2R
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()
Clinical Data; Ranking SVM; Data Integration

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.