Hybrid bag of approaches to characterize selection criteria for cohort identification | Zendy

V. G. Vinod Vydiswaran | Zendy; Asher Strayhorn | Zendy; Xinyan Zhao | Zendy; Philip Robinson | Zendy; Mahesh Agarwal | Zendy; Erin Bagazinski | Zendy; Madia Essiet | Zendy; Bradley Iott | Zendy; Hyeon Joo | Zendy; PingJui Ko | Zendy; Da-Hee Lee | Zendy; Jin Xiu Lu | Zendy; Jinghui Liu | Zendy; Adharsh Murali | Zendy; Koki Sasagawa | Zendy; Tianshi Wang | Zendy; Nalingna Yuan | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Hybrid bag of approaches to characterize selection criteria for cohort identification

Author(s) -

V. G. Vinod Vydiswaran,

Asher Strayhorn,

Xinyan Zhao,

Philip Robinson,

Mahesh Agarwal,

Erin Bagazinski,

Madia Essiet,

Bradley Iott,

Hyeon Joo,

PingJui Ko,

Da-Hee Lee,

Jin Xiu Lu,

Jinghui Liu,

Adharsh Murali,

Koki Sasagawa,

Tianshi Wang,

Nalingna Yuan

Publication year - 2019

Publication title -

journal of the american medical informatics association

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 1.614

H-Index - 150

eISSN - 1527-974X

pISSN - 1067-5027

DOI - 10.1093/jamia/ocz079

Subject(s) - weighting , computer science , preprocessor , artificial intelligence , selection (genetic algorithm) , task (project management) , identification (biology) , test set , set (abstract data type) , machine learning , feature selection , test (biology) , cohort , natural language processing , data mining , medicine , statistics , mathematics , paleontology , botany , biology , radiology , programming language , management , economics

Our hybrid approach was able to identify all selection criteria with high F1 performance on both training and test sets. Based on our participation in the 2018 n2c2 task, we conclude that there is merit in continuing a focused criterion-specific analysis and developing appropriate knowledge resources to build a quality cohort selection system.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research