Predictive article recommendation using natural language processing and machine learning to support evidence updates in domain-specific knowledge graphs.

Autor:	Sharma B; IBM Watson Health, Cambridge, Massachusetts, USA., Willis VC; IBM Watson Health, Cambridge, Massachusetts, USA., Huettner CS; IBM Watson Health, Cambridge, Massachusetts, USA., Beaty K; IBM Watson Health, Cambridge, Massachusetts, USA., Snowdon JL; IBM Watson Health, Cambridge, Massachusetts, USA., Xue S; IBM Watson Health, Cambridge, Massachusetts, USA., South BR; IBM Watson Health, Cambridge, Massachusetts, USA., Jackson GP; IBM Watson Health, Cambridge, Massachusetts, USA., Weeraratne D; IBM Watson Health, Cambridge, Massachusetts, USA., Michelini V; IBM Watson Health, Cambridge, Massachusetts, USA.
Jazyk:	angličtina
Zdroj:	JAMIA open [JAMIA Open] 2020 Sep 29; Vol. 3 (3), pp. 332-337. Date of Electronic Publication: 2020 Sep 29 (Print Publication: 2020).
DOI:	10.1093/jamiaopen/ooaa028
Abstrakt:	Objectives: Describe an augmented intelligence approach to facilitate the update of evidence for associations in knowledge graphs. Methods: New publications are filtered through multiple machine learning study classifiers, and filtered publications are combined with articles already included as evidence in the knowledge graph. The corpus is then subjected to named entity recognition, semantic dictionary mapping, term vector space modeling, pairwise similarity, and focal entity match to identify highly related publications. Subject matter experts review recommended articles to assess inclusion in the knowledge graph; discrepancies are resolved by consensus. Results: Study classifiers achieved F-scores from 0.88 to 0.94, and similarity thresholds for each study type were determined by experimentation. Our approach reduces human literature review load by 99%, and over the past 12 months, 41% of recommendations were accepted to update the knowledge graph. Conclusion: Integrated search and recommendation exploiting current evidence in a knowledge graph is useful for reducing human cognition load. (© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu