Detecting and resolving inconsistencies between domain experts鈥?different perspectives on (classification) tasks

详细信息	查看全文 | 推荐本文 |

• 作者：Derek Sleeman^a ; ^b ; ^{d.sleeman@abdn.ac.uk} ; Laura Moss^a ; ^b ; ^c ; Andy Aiken^a ; Martin Hughes^b ; John Kinsella^b ; Malcolm Sim^b
• 关键词：Classification ; Expertise capture ; Inconsistency resolution ; Intensive care unit ; Patient scoring system ; Physiological measurements
• 刊名：Artificial Intelligence in Medicine
• 出版年：2012
• 期刊代码：26_09333657
• 类别：med
• 出版时间：June, 2012
• 卷：55
• 期：2
• 页码：71-86
• 文件大小：784 K

摘要

Objectives

The work reported here focuses on developing novel techniques which enable an expert to detect inconsistencies in 2 (or more) perspectives that the expert might have on the same (classification) task. The high level task which the experts (physicians) had set themselves was to classify, on a 5-point severity scale (A-E), the hourly reports produced by an intensive care unit's patient management system.

Method

The INSIGHT system has been developed to support domain experts exploring, and removing inconsistencies in their conceptualization of a task. We report here a study of intensive care physicians reconciling 2 perspectives on their patients. The 2 perspectives provided to INSIGHT were an annotated set of patient records where the expert had selected the appropriate category to describe that snapshot of the patient, and a set of rules which are able to classify the various time points on the same 5-point scale. Inconsistencies between these 2 perspectives are displayed as a confusion matrix; moreover INSIGHT then allows the expert to revise both the annotated datasets (correcting data errors, or changing the assigned categories) and the actual rule-set.

Results

Each of the 3 experts achieved a very high degree of consensus (鈭?7%) between his refined knowledge sources (i.e., annotated hourly patient records and the rule-set). We then had the experts produce a common rule-set and then refine their several sets of annotations against it; this again resulted in inter-expert agreements of 鈭?7%. The resulting rule-set can then be used in applications with considerable confidence.

Conclusion

This study has shown that under some circumstances, it is possible for domain experts to achieve a high degree of correlation between 2 perspectives of the same task. The experts agreed that the immediate feedback provided by INSIGHT was a significant contribution to this successful outcome.