Evaluating robustly standardized explainable anomaly detection of implausible variables in cancer data.

Journal: Journal of the American Medical Informatics Association : JAMIA

PMID: 39873664

Abstract

OBJECTIVES: Explanations help to understand why anomaly detection algorithms identify data as anomalous. This study evaluates whether robustly standardized explanation scores correctly identify the implausible variables that make cancer data anomalous.

Authors

Philipp Röchner

Information Systems and Business Administration, Johannes Gutenberg University, Mainz 55128, Germany.
Franz Rothlauf

Johannes Gutenberg University, Mainz, Germany.

Keywords

Algorithms Humans Lung Neoplasms Neural Networks, Computer Registries Urinary Bladder Neoplasms

External Resources

View on PubMed Access via DOI PubMed (39873664)

Evaluating robustly standardized explainable anomaly detection of implausible variables in cancer data.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals