Document Detail


Learning medical diagnosis models from multiple experts.
MedLine Citation:
PMID:  23304367     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
Building classification models from clinical data often requires labeling examples by human experts. However, it is difficult to obtain a perfect set of labels everyone agrees on because medical data are typically very complicated and it is quite common that different experts have different opinions on the same patient data. A solution that has been recently explored by the research community is learning from multiple experts/annotators. The objective of learning from multiple experts is to model different characteristics of the human experts and combine them to obtain a consensus model. In this work, we study and develop a new probabilistic approach for learning classification models from labels provided by multiple experts. Our method explicitly models and incorporates three characteristics of annotators into the learning process: their specific prediction model, consistency and bias. We show that in addition to building a superior classification model, our method also helps to model behavior of annotators. We applied the proposed method to learn different characteristics of Physicians labeling clinical records for Heparin Induced Thrombocytopenia (HIT) and combine them in order to obtain a final classifier.
Authors:
Hamed Valizadegan; Quang Nguyen; Milos Hauskrecht
Related Documents :
16370867 - Comparison of tat and free speech techniques for eliciting source material in computeri...
15064537 - The effect of dropping low scores on ability estimates.
15459287 - Adjust quality scores from alignment and improve sequencing accuracy.
18834547 - A new scoring system in cystic fibrosis: statistical tools for database analysis - a pr...
8523907 - Comparison of different oxygen exchange models.
21095967 - Assessment of waist-worn tri-axial accelerometer based fall-detection algorithms using ...
Publication Detail:
Type:  Journal Article     Date:  2012-11-03
Journal Detail:
Title:  AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium     Volume:  2012     ISSN:  1942-597X     ISO Abbreviation:  AMIA Annu Symp Proc     Publication Date:  2012  
Date Detail:
Created Date:  2013-01-10     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101209213     Medline TA:  AMIA Annu Symp Proc     Country:  United States    
Other Details:
Languages:  eng     Pagination:  921-30     Citation Subset:  IM    
Affiliation:
Department of Computer Science, University of Pittsburgh, email: hamed@cs.pitt.edu, quang@cs.pitt.edu, milos@cs.pitt.edu.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  An Evaluation of the NQF Quality Data Model for Representing Electronic Health Record Driven Phenoty...
Next Document:  ReadySteady: App for Accelerometer-based Activity Monitoring and Wellness-Motivation Feedback System...