التفاصيل البيبلوغرافية
العنوان: |
Learning from Mistakes: Constructing and Mining Misdiagnosis Database to Reduce Cognitive Error. |
المؤلفون: |
Hui Fang, Hailiang Huang, Gujie Li, Yanhong Li |
المصدر: |
Proceedings of the International Conference on Information Systems (ICIS); 2018, p1-9, 9p |
مصطلحات موضوعية: |
DIAGNOSTIC errors, COGNITIVE bias, PATIENT safety, NATURAL language processing, DEEP learning, INFORMATION technology |
مستخلص: |
Diagnostic error is now a leading problem globally with the increase of mortality rate, financial cost and social burden. Existing IT artifacts mainly focus on tackling diagnostic errors caused by system flaws but fail to address users' cognitive biases. In view of it, we systematically design a two-phase framework to proactively enrich medical professionals' knowledge on diagnostic errors and to manage cognitive biases. Specifically, we first employ natural language processing techniques including BI-LSTMCRF to extract misdiagnosis relations from medical literature, which are then stored in the misdiagnosis database. Secondly, we conduct in-depth knowledge discovery, including rule-based reasoning, network analysis and exploratory analysis to uncover the hidden knowledge on diagnostic errors from the constructed database. The on-going experiment verifies the effectiveness of BI-LSTM-CRF on performing the misdiagnosis relation extraction task. Our proposed framework serves as a promising infrastructure in both Healthcare IS and medical research for improving patient safety. [ABSTRACT FROM AUTHOR] |
|
Copyright of Proceedings of the International Conference on Information Systems (ICIS) is the property of Association for Information Systems and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
قاعدة البيانات: |
Complementary Index |