Weber, Griffin, Mendis, Kohane, Churchill, McGow
Griffin committed to elaborating the tempotral query workflow over the next two months using UI mockups intended to drive our back end architecting of the interval/point representations and episode of care. Goal is a firm perspective on the
Thin client UI extensions. Discussed workflow dependencies.
Visiting: John Pestian
Also: Ozlem, Guergana, Margharita, Szolovits, Kohane, Churchill
Discussed a clinical corpus of victims of suicide and how to approach the NLP task in this horribly at risk population. Also discussed several evaluation strategies.
Gainer, Cai, Savova, Ashwin, Plenge, Sordo, Kohane, Raychaudri, Karlson
Focus on Inflammatory Bowel disease today.
Reviewed disease itself: Peak incidence:14-24 (second peak between 50-70 years).
Not an autoimmune disease (auto-antibodiesa not found against human antigens) but the immune system plays an important pathogenic role. Smoking is an important risk factor for IBD but in very specific ways:
Past smoking increases risk of ulcerative colitis but current smoking increases the risk of Crohn's disease.
Reviewed previously implicated genes in linkage and GWAS studies. Reviewed clinical course and treatment. Reviewed epidemiological evidence regarding cardiovascular disease in IBD.
Concluded with a discussion of the IBD component of the auto-immune-CVD datamart.
Attending: Kohane, Murphy, Weber, Churchill, Mendis, McGow
Discussed the follow on of our prior discussions on the design of an episode table and an Episode-to-FACT mapping table.
Shaw, Kohane, Gainer. Churchill, Savova, Sordo, Iftikhar Kullo callinh-in from Mayo
Reviewed first how Dr. Kullo et al defined peripheral arterial disease. First without and then with NLP on clinical reports (mostly on interventional radiology and ultrasound to a lesser degree, CT and MRI angiograms). The performance described is remarkable (accuracy in the high 90's).
Led by Rheumatoid arthritis DBP
Northwestern, Vanderbilt calling in on Skype.
Reviewed the remarkably good concordance of the performance across several systems.
Mendis, Bickel, Kohane, Weber, Murphy
Lots of back and forth about representing multiple versions/depictions of episode in patient selection. Discussion of which tables will bear the additional complexity.
Murphy, Karlsson. Gainer, Shaw, Savova, Szolovits, Liao, Kohane, Churchill, Cai,
Discussed the NLP annotation pipeline (used by the "gold standard" annotators).
Discussed predictors of RA (by NLP and codified data) in patients who previously did not qualify as having RA.
Murphy, Kohane, Weber, Mendis, McGaw, Bickel
Reviewed the growing volume of AUG email related to installing i2b2 (multiple operating systems and RDBMS) and how to be responsive without overwhelming our other developer community support activities.
Discussed improvements to the i2b2 web client and incorporating contributions from the community.
Gainer, Murphy, Shaw, Liao, Kohane, Churchill
Extensive discussion of which case cohort definition we will adopt for cardiovascular disease. Projected that discussion into the eventual endgame for molecular physiological characterization.
Specifics around EKG and echocardiogram reports reviewed.
Murphy, Weber, Churchill, McGow, Wilson, Kohane, Mendis
Reviewed community.i2b2.org. Specifically the i2b2 webclient as a first instance (this is a project that was first started by Griffin to work on top of the .NET stack) of bringing in a non-core project. Discussed how to prioritize tasks within a sponsored project.
We had an important but tangential discussion about the definition of episodes of care.
More than 20 participants. First, Kohane went over the outline of what i2b2 (v2) is going to focus on. Then reviewed recent AUG meeting and introduced Robert Plenge and Stanley Shaw who described the new DBP's of which they are PI.
We tagged the AUG meeting onto the national CTSA meeting. As you see from the pictures below, we had good attendance along with the 27 others attending via WEBEX.
Topics included
Brian Wilson presented the roadmap for i2b2(v2) for representation of genome-scale data ranging from SNP arrays to assembled full genomes or the short reads from which they were assembled. This preliminary roadmap is outlined below. Given the general interest of the GARLIC application domain (i.e. querying for patient populations with specified genome-scale characteristics) there are likely to be several national groups and/or users which have experience and interest. We plan to contact those we know of and appreciate other groups reaching out to help, collaborate or inform.
Ozlem, Guergana, Margarita, Jiaping Zeng, Pete Zak
Reviewed the co-reference NLP challenge and what needs to be done?
Discussed the challenges of combining packages with different open source licenses. The webservice API is generally seen as a useful way to keep packages with different licenses working together. The cost is the increased installation/dissemination complexity.
Ashwin (IBD) Ananthakrishnan, Philip L. De Jager (MS), Beth Karlson, Helena Canhão, Kat, Sordo, Guergana, Stan, Peter Szolovits, Robert Plenge, Raoul Guzman, Vivian Gainer, Xia Zongqi (Neuro-rheumatology), LJ Wei, Peter Szolovits, Tianxi Cai
The PI's described how they propose to build on the experience of the RA DBP to go into further depth into the phenotypes (around RA) and drug effects/efficacy and see how far we can go with EHR-derived phenotypes. Further, we will be studying the shared and differing pathotypes across a larger range of autoimmune diseases, namely including inflammatory bowel disease and multiple sclerosis (for which we have expert representation in this DBP). We also reviewed the imperative to identify subcohorts (based on combinations of clinical and genomic stratification) that have distinguishing therapeutic efficacy and/or adverse events.
Present: Susanne Churchill, Ozlem, Zak, Guergana, Griffin Weber, Dan Nigrin
Welcome to my first blog post in the recompeted i2b2.
We discussed temporal reasoning requirements in the new i2b2. Requirements for interval and point logic and how we were informed by Nigrin's master thesis reviewed. Integration of NLP derived temporal relations was preliminarily reviewed.
Present: Stan Shaw, Vivian Gainer, Margarita Sordo. Kat, Susanne Churchill, Ozlem, Zak, Guergana
The new DBP led by Stan Shaw addresses the epigenetics (DNA methylation, histone acetylation, histone methylation assayed using full genome-scale resequencing) of heart disease in the context of diabetes mellitus.
Kat reviewed the overall approach that we take in DBP's in defining cohorts through billing code,
Ozlem gave an update on the new de-identification pipeline.
We reviewed which fellow we might find to do some of the heavy lifting with Stan.
Courtesy of Keith Marsolo, here is some very useful guidance.
We've posted some documentation that describes our work with the Epic Clarity database. It can be found at the following location:
The first document: "Moving Data from Epic to I2B2.docx" describes, well, our approach to moving data from Epic to i2b2. It's not complete, but it provides an overview of how we load demographics, diagnoses, and medications. There's some information on how we create metadata XML for each content type. This is similar to the upcoming "modifier" functionality in version 1.6. Until we release our code, it's more or less CCHMC-specific, but the content would be applicable to either approach.
The other document "epic_dw_master_tables.pdf" details some of the steps used to create our "Master" Epic datamart that we provide to users for reporting and other purposes. Not all of the tables are included, but we've provided a few of the more frequently used ones. The scripts provide an overview of what columns/tables to use to look for certain content.
Words of "wisdom":1. The tables/columns in Epic may have misleading names. Always check the Epic UserWeb/Clarity data dictionaries to determine the true purpose of the field.2. Never assume that the Epic documentation is accurate and/or complete. Each institutions Epic implementation is different, and data may be in unique locations, particularly if that data is fed by an interface. To verify the data you are working with is correct (i.e. what you think it means), I would encourage you to work with your Clarity Reporting Team or end users to ensure that the data in the database matches what appears on the screen.
As our Summer winds down, the various i2b2 core development teams are returning to Boston. Meanwhile our colleagues in Japan have been busy implementing their version of i2b2. Kudos!
Minutes (courtesy Patience Gallagher)
Minutes:
Cai, Kohane, Szolovits, Murphy, Goryachev, Savova, Churchill, Karlson, Plenge
Reviewed different NLP strategies for smoking (a crucial exposure risk for RA).
Discussed SNP validation manuscript.
Kohane, Murphy, Weber, Churchill, Wilson. Mendis
Reviewed plugin architecture and convergence between web and Java client.
Reviewed "normals" project.
Wilson, Bry, Murphy, Kohane, Churchill
Discussed progress on the Cell. Includes support for approved protocols and specimen details.
Beth Karlson provided an overall review of RA epidemiology so as to compare to our i2b2 work. Among the interesting facts I learned: In the Nurse's Health Study only 6% of the self-reported cases of RA were validated by the expert reviewers. Described relative risk of smoking with regard to RA is approximately 1.4 and is an effect that take appears to only taper off with about 20 years of smoking cessation.
Mendis, Wilson, Savova, Weber, Kohane, Churchill,
Discussed the content for a hands on tutorial for the upcoming AMIA NOW.
Brian Wilson (bioinformatics and statistical genetics) and Guergana Savova (natural language processing) both from the Mayo Institute have just joined the i2b2 team. Welcome to both!
Shawn, Zak, Susanne, Vivian, Mike, and Griffin attended the AMIA Translational Informatics Summit 2010 in SF. There were several i2b2 events including a) a packed three and half hour tutorial b) an overview of i2b2 applications c) an evening AUG meeting. Lots of interest, good questions and interesting developments.
Perlis, Iosifescu et al,,
Discussed the artifact that definitionally happens in clinical trials of assigning individuals to responder and non-responder categories when in fact the data always shows that the vast majority of individuals are oscillating in the spectrum in between. So unlike 8 week trial studies of antidepressants where there has to be an assignment of response vs no-response, these dense clinical data call for the application of other metrics such as proportion of days feeling "well." Unfortunately, such quality-of-life metrics don't go particularly well with many reviewers.
Plenge, Karlson, Liao et al.,
Planning for Kat's maternity leave.
Large pharmaceutical companies interested in collaboration.
Perlis, Iosifescu et al.
Dan Iosifescu announced he is moving to Mount Sinai School of Medicine. He had a great job offer there and we wish him well.
Victor discussed several tactics to increase the number of pertinent notes for NLP. There is quite a bit of validation effort required.
We just had an interesting discussion with Nick Holden and his colleagues about the adoption in the UK of i2b2 for discovery studies.
Kat presenting: RA and coronary artery disease risk and dissecting the contribution of risk factors in the non-RA population (for CAD) to CAD in the RA population. This will include a broad overview of the auto-immunity landscape.
Plenge, Karlsson, Liao et al.
Discussed paper under review and how different diagrams of the NLP process need to be improved.
Perlis et al.,
Perspective on how the original DBP relates to a new R01 that Perlis was awarded. The original DBP 2000 samples original goal of the DBP from which the GWAS would be drawn. The new R01 provides for additional samples and additional modeling. Long discussion about long-term curation of de-identified notes ensued. Several pitfalls were addressed.
J&J has made an interesting foray into creating a translational analytic platform using i2b2. This article from Bio-ITWorld summarizes an impressive bit of work led Eric Perakslis. They have pulled together multiple private and public data sources to help accelerate their discovery and validation process. Perhaps this presages a further push into trans-enterprise intelligence at the pharmaceutical companies?
