• Aucun résultat trouvé

Applying Information Retrieval to the Electronic Health Record for Cohort Discovery and Rare Disease Detection

N/A
N/A
Protected

Academic year: 2022

Partager "Applying Information Retrieval to the Electronic Health Record for Cohort Discovery and Rare Disease Detection"

Copied!
1
0
0

Texte intégral

(1)

Applying Information Retrieval to the Electronic Health Record for Cohort Discovery and Rare Disease Detection

William Hersh

Department of Medical Informatics & Clinical Epidemiology Oregon Health & Science University

Portland, OR, USA hersh@ohsu.edu

KEYNOTE ABSTRACT

The last decade has seen rapid adoption of electronic health records in the United States and elsewhere. This has resulted in vast amounts of data that can be re-used for other purposes such as clinical research. However, most of this data is non-standardized and unstructured, making retrieval and other uses challenging. This talk will describe recent research applying and evaluating information retrieval techniques to two use cases: discovering cohorts for clinical research studies and detecting rare diseases.

.

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).

HSDM’20, February, 2020, Houston, Texas USA

Copyright © 2019 for this paper by its author. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Références

Documents relatifs

With improved prospects for automatically ex- tracting arguments from text, we are investigat- ing whether and how argument extraction can im- prove legal information retrieval (IR).

To characterize the coverage of rare diseases studied in PCORnet, we estimate the number of precise and equivalent matches in the three clinical classifications

Online access panels with panelists representing the desired target group or with even real end-users of existing products could help to speed-up the recruiting

In the CLEF 2005 Ad-Hoc Track we experimented with language-specific morphosyntactic processing and light Natural Language Processing (NLP) for the retrieval of Bulgarian,

In particular, it ig- nores: that people interact with information objects during the course of information seek- ing episodes; that people have other goals dur- ing information

Performance on the Similar Seg- ments in Social Speech Task at MediaEval 2013 was well above baseline, showing the value of prosody for

FCART allows the user to load structured and unstructured data (texts and various meta- information) from heterogeneous data sources, build data snapshots, compose

The input is a chief complaint and a brief history, and the output is top-1 course and treatment selected from the historical NTUH medical records.. Recall that examination,