|
 내용
|
Special Focus Issue on Electronic Health Records-Driven Phenotyping
March 31, 2013: Manuscript submission deadline
May 31, 2013 (expected): Initial decisions sent to authors
June 30, 2013 (expected): Revised manuscript submission deadline
August 31, 2013 (expected): Final decisions sent to authors
홈페이지: http://jamia.bmj.com/site/misc/JAMIA-Special-Issue-Phenotyping-FINAL.pdf
JAMIA Call for Papers: Special Focus Issue on Electronic Health Records-Driven Phenotyping
Guest Editors
• Jyotishman Pathak (Mayo Clinic, Rochester, MN, USA)
• Joshua C. Denny (Vanderbilt University, Nashville, TN, USA)
• Abel N. Kho (Northwestern University, Chicago, IL, USA)
Description of the Special Issue
The identification of patient cohorts for clinical and genomic research is a costly and timeconsuming
process. This bottleneck adversely affects public health by delaying research findings,
and in some cases by making research costs prohibitively high. To address this issue, the
leveraging of electronic health records (EHRs) to identify patient cohorts has become an
increasingly attractive option. With the rapidly growing adoption of EHR systems due to
Meaningful Use, and linkage of EHRs to research biorepositories, evaluating the suitability of
EHR data for clinical and translational research is becoming ever more important, with
ramifications for genomic and observational research, clinical trials, healthcare delivery research
and comparative effectiveness studies.
A key component for identifying patient cohorts in the EHR is to define inclusion and exclusion
criteria that algorithmically select sets of patients based on stored clinical data. This process,
commonly referred to as EHR-driven phenotyping, allows the definition of phenotypes over
structured data (e.g., demographics, diagnoses, medications, and laboratory measurements) as
well as unstructured clinical text (e.g., radiology reports, encounter notes, discharge summaries).
In general this process can be quite complex, involving heuristics encoded as rules or machine
learning algorithms. The goal of this special issue of the Journal of American Medical
Informatics is to provide a forum for presenting methodologies, tools, and algorithms to enable
high-throughput phenotype extraction from EHR data. Submissions from outside the USA
describing generalizable experiences are highly encouraged.
Topics of Interest
Possible topics include, but are not limited to:
- Novel architectures for facilitating high-throughput phenotyping from EHRs
- Natural language processing (NLP) and text mining methods for phenotype extraction
- Cost-benefit analyses of electronic phenotype identification in healthcare settings
- Evaluation of transportability of phenotyping methods and reuse of existing phenotype
algorithms across different healthcare settings, EHR systems, and component systems
(e.g., different NLP systems when applied to EHR data)
- Standards-based representation and modeling of phenotyping algorithms
- Machine learning approaches to developing and validating phenotyping algorithms
- Data mining of EHR data for clinical discovery
- Methods and platforms for semi-automated execution of phenotyping algorithms
- State-of-the-art surveys in phenotyping methods, tools and techniques
- Secondary uses of EHR data for genomics, epidemiology, comparative effectiveness
research, healthcare quality and deliver research, clinical decision support, etc.
- Evaluation of EHR data extraction accuracy (e.g., accuracy of structured billing codes)
and data cleaning methods
- Quality of patient-reported outcomes that are incorporated into the EHR, data
harmonization across various healthcare institutions
- Comparison of different EHR systems in terms of how various coding systems can be
accommodated, how flexible the systems are in allowing users to structure clinical
information, etc.
- Ethical aspects of utilizing EHR for research, informed consent practices, standardized
data use agreements, differences in regulations across institutions, states and countries
Authors should make sure to place their work in the context of biomedical research or healthcare,
and to carefully review the relevant literature. Research articles, case studies, and brief
communications should describe clear evaluation strategies and quantitative or qualitative results,
and discuss how results could be generalized to other settings. Reviews should be systematic.
Perspectives should provide consensus of a group of experts who are highly experienced in the
topic, and should demonstrate command of the existing literature. Open-source software code and
data should be submitted, as well as data when appropriate.
Important Dates
March 31, 2013: Manuscript submission deadline
May 31, 2013 (expected): Initial decisions sent to authors
June 30, 2013 (expected): Revised manuscript submission deadline
August 31, 2013 (expected): Final decisions sent to authors
Submission and Peer Review Process
To ensure consideration in the special issue, authors should note in a cover letter that their
submission is for the “Special Issue on Electronic Health Records-driven Phenotyping”. Detailed
information for online submission to JAMIA is available via http://jamia.bmj.com.
All manuscripts will be subject to the rigorous JAMIA peer-review process. Manuscripts that are
considered within scope and meet quality expectations will be reviewed by a minimum of two
experts for scientific merit. Assistance of a native English speaker is highly recommended prior
to submission. Authors should format and structure their manuscripts according to the guidelines
specified at: http://jamia.bmj.com/site/about/guidelines.xhtml. Accepted articles may appear in
print or in an online JAMIA issue.
Questions Regarding the Issue
Please direct any questions regarding the special issue to jamia-phenotyping@googlegroups.com.
|
SNUBI >