PMID- 30474078
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220330
IS  - 2574-2531 (Electronic)
IS  - 2574-2531 (Linking)
VI  - 1
IP  - 2
DP  - 2018 Oct
TI  - Learning relevance models for patient cohort retrieval.
PG  - 265-275
LID - 10.1093/jamiaopen/ooy010 [doi]
AB  - OBJECTIVE: We explored how judgements provided by physicians can be used to learn 
      relevance models that enhance the quality of patient cohorts retrieved from 
      Electronic Health Records (EHRs) collections. METHODS: A very large number of 
      features were extracted from patient cohort descriptions as well as EHR 
      collections. The features were used to investigate retrieving (1) 
      neurology-specific patient cohorts from the de-identified Temple University 
      Hospital electroencephalography (EEG) Corpus as well as (2) the more general 
      cohorts evaluated in the TREC Medical Records Track (TRECMed) from the 
      de-identified hospital records provided by the University of Pittsburgh Medical 
      Center. The features informed a learning relevance model (LRM) that took 
      advantage of relevance judgements provided by physicians. The LRM implements a 
      pairwise learning-to-rank framework, which enables our learning patient cohort 
      retrieval (L-PCR) system to learn from physicians' feedback. RESULTS AND 
      DISCUSSION: We evaluated the L-PCR system against state-of-the-art traditional 
      patient cohort retrieval systems, and observed a 27% improvement when operating 
      on EEGs and a 53% improvement when operating on TRECMed EHRs, showing the promise 
      of the L-PCR system. We also performed extensive feature analyses to reveal the 
      most effective strategies for representing cohort descriptions as queries, 
      encoding EHRs, and measuring cohort relevance. CONCLUSION: The L-PCR system has 
      significant promise for reliably retrieving patient cohorts from EHRs in multiple 
      settings when trained with relevance judgments. When provided with additional 
      cohort descriptions, the L-PCR system will continue to learn, thus offering a 
      potential solution to the performance barriers of current cohort retrieval 
      systems.
FAU - Goodwin, Travis R
AU  - Goodwin TR
AD  - Department of Computer Science, Human Language Technology Research Institute, 
      University of Texas at Dallas, Richardson, Texas, USA.
FAU - Harabagiu, Sanda M
AU  - Harabagiu SM
AD  - Department of Computer Science, Human Language Technology Research Institute, 
      University of Texas at Dallas, Richardson, Texas, USA.
LA  - eng
SI  - Dryad/10.5061/dryad.pq0cs6h
GR  - U01 HG008468/HG/NHGRI NIH HHS/United States
PT  - Journal Article
DEP - 20180928
PL  - United States
TA  - JAMIA Open
JT  - JAMIA open
JID - 101730643
PMC - PMC6241510
OTO - NOTNLM
OT  - information storage and retrieval
OT  - machine learning
OT  - medical informatics
OT  - search engine
EDAT- 2018/11/27 06:00
MHDA- 2018/11/27 06:01
PMCR- 2018/09/28
CRDT- 2018/11/27 06:00
PHST- 2017/12/30 00:00 [received]
PHST- 2018/02/26 00:00 [revised]
PHST- 2018/09/05 00:00 [accepted]
PHST- 2018/11/27 06:00 [entrez]
PHST- 2018/11/27 06:00 [pubmed]
PHST- 2018/11/27 06:01 [medline]
PHST- 2018/09/28 00:00 [pmc-release]
AID - ooy010 [pii]
AID - 10.1093/jamiaopen/ooy010 [doi]
PST - ppublish
SO  - JAMIA Open. 2018 Oct;1(2):265-275. doi: 10.1093/jamiaopen/ooy010. Epub 2018 Sep 
      28.