Improving the Decision Support in Diagnostic Systems using Classifier Probability Calibration
Average rating
Cast your vote
You can rate an item by clicking the amount of stars they wish to award to this item.
When enough users have cast their vote on this item, the average rating will also be shown.
Star rating
Your vote was cast
Thank you for your feedback
Thank you for your feedback
Issue Date
2018-11-09
Metadata
Show full item recordAbstract
In modern medical diagnoses, classifying a patient’s disease is often realized with the help of a system-aided symptoms interpreter. Most of these systems rely on supervised learning algorithms, which can statistically extend the doctor’s logic capabilities for interpreting and examining symptoms, thus supporting the doctor to find the correct diagnosis. Besides, these algorithms compute classifier scores and class labels that are used to statistically characterize the system’s confidence level on a patient’s type of disease. Unfortunately, most classifier scores are based on an arbitrary scale but not uniformed, thus the interpretations often lack of clinical significance and evaluation criterion. Especially combining multiple classifier scores within a diagnostic system, it is essential to apply a calibration process to make the different scores comparable. As a frequently used calibration technique, we adapted isotonic regression for our medical diagnostic support system, to provide a flexible and effective scaling process that consequently calibrates the arbitrary scales of classifiers’ scores. In a comparative evaluation, we show that our disease diagnostic system with isotonic regression can actively improve the diagnostic result based on an ensemble of classifiers, also effectively remove outliers from data, thus optimize the decision support system to obtain better diagnostic results.Affiliation
HZI,Helmholtz-Zentrum für Infektionsforschung GmbH, Inhoffenstr. 7,38124 Braunschweig, Germany.Publisher
SpringerType
OtherLanguage
enISSN
03029743ISBN
978-303003492-4ae974a485f413a2113503eed53cd6c53
10.1007/978-3-030-03493-1_44
Scopus Count
The following license files are associated with this item:
- Creative Commons
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International