i2b2Blog

HAPPY NEW YEAR 2012 - Both DBP Meeting

2012-01-06T07:36:00.001-08:00

Shaw, Murphy, Plenge, Kohane, Karlson, Prilutsky, Doshi, Szolovits, Liao, Churchill, et al.

Reviewed the NLP on the cardiovascular data mart (340,000 patients).

Reviewed what is the right sample prep for our new studies (tending towards spinning down and storing the buffy coat and plasma fraction sepeartely and -70).

Kat presented results on PheWAS on the autoimmune panel.

All Hands - Physio-MIMI

2011-12-16T08:29:00.000-08:00

Susan Redline et al.,

Described the next version of this Sleep-Repository/Analytic Warehouse called Hybrid. Described a Ruby on Rails implementation.

Reconciliation of data types across multiple ontologies is done by local mapping of member data sources into a data dictionary. The decision was explicitly made to allow transparency into these source data at the cost of having the investigator determine the validity of the mappings and their semantics for each of the data sources.

Report back from the Psychiatry DBP's

2011-12-16T08:12:00.000-08:00

Perlis et al,

3000 blood samples so far on the bipolar project.

The identification of controls has turned out to be a big edge for EDGR as those are the most difficulty to ascertain in conventional cohorts (where the control for one study may be contaminated by disease for another study).

~1000 samples for the MDD study.

Multiple sclerosis

2011-12-09T07:25:00.000-08:00

Xia et al., Reviewed NLP oddities from prior presentation (i.e. different predictive weights from dysarthria and slurred speech). Yet by manually collapsing terms into manually identified superconcepts did not seem to improve performance significantly.

Diabetes

2011-12-09T07:15:00.000-08:00

Shaw et al., Reviewed NLP results for DM DBP. Seems that overall working well. Some descriptions of neuropathy are rarer than expected.

Crohn's and Ulcerative colitits

2011-12-09T06:53:00.000-08:00

Ashwin et al., Discussed the AUC for UC and Crohn's with NLP and codified data. In this domain, once the cohort is roughly identified with the ICD-9 codes (low specificity), the NLP terms are much better than the codified terms in accurately identifying who has disease and who does not (as measured by AUC). Based on these analyses, it looks like PHS has 12000 (UC + Crohn's) of which about 3600 samples can be accumulated in one year.

Review NLP processes for our DBP's

2011-12-02T06:50:00.000-08:00

Guergana et al,

Learning environment

1. Training/test set creation (labeling of data; currently using Knowtator (which itself used Protege 3.1))
2. Automated toolset (cTAKES + automated feature selection flow)
3. Loop 1-2

Inna Dubchak visit

2011-11-18T08:23:00.001-08:00

Inna Dubchak from the LANL Joint Genome Institute gave an overview of her VISTA i2b2 docking project. This allows the VISTA i2b2 cell to provide analyses of the "meaning" of variants based largely on conservation data. Also gave an update on the rviewer tool

Technical Futures

2011-11-18T06:41:00.001-08:00

Shawn, Kohane, NIch, Mike, Zak, Susanne, Bickel Discussed several important minimal commitment abstractions useful for temporal reasoning and for suggesting related queries.

Diabetes Mellitus + Autoimmune NLP definitions for cardiovascular disease

2011-11-04T06:50:00.001-07:00

Shaw, Liao, Plenge et al., discussed our common needs on cardiovascular disease. The question of how detailed to go as opposed to a broad definition was reviewed. The tendency was to go in both directions.

Distributed queries

2011-11-04T06:15:00.000-07:00

Griffin Weber, Shawn Murphy, Bill Simons, Susanne Churchill, Zak Kohane Discussed latest national developments for SHRINE queries. Very significant support and enthusiasm from the AUG. Reviewed temporal query capabilities and roadmap.

Inflammatory Bowel Disease

2011-10-07T08:11:00.001-07:00

Ashwin presented

Reviewed the NLP approach to date.

Showed the distinctions made based on terms of varying specificity. The NLP processing increased the accuracy as expected but probably by only 10% relative to the codified data. However the codified data alone had much less stable performance, probably because those are easier to overfit to local billing practice and demographics of the underlying hospital population.

Also reviewed when to start sample collection.

i2b2 Version 1.6 release preparations

2011-10-07T07:00:00.001-07:00

Kohane, Churchill, Murphy, Mendis, Wattansin Last minute preparation for documentation and squishing any remaining bugs.

DM/CVD

2011-09-24T20:43:00.000-07:00

Stan Shaw, Tianxi Cai, Raoul, Shawn, Zak, Susanne et al.,

Discussed whether to expand the data mart to include other hospitals.

Reviewed study design for measures of inflammation.

SMART integration with i2b2 reviewed

2011-09-23T06:30:00.001-07:00

Discussed how additional SHRINE influences future directions of i2b2. Then demonstrated the latest i2b2/SMART integration (quite impressive!).

MDD

2011-09-22T11:51:00.001-07:00

(minutes courtesy Caitlin)

Attendance: Jordan Smoller, Roy Perlis, Shawn Murphy, Susanne Churchill, Isaac Kohane, Tianxi Cai, Victor Castro, Alison Hoffnagle, Patience Gallagher, Sydney Weill, Caitlin Clements

Minutes:

-ICCBDà Refresh: Victor has performed a preliminary refresh of the data mart; however, this did not include the NLP cohort. Victor will finish NLP classification and will perform another refresh by the end of the following week that includes this data. The current updated numbers for the other cohorts may change a bit as well when he performs this second refresh; however, they will not change by much.

The numbers for the cohort sizes increased after the refresh, particularly because the group added McLean patients to the data mart (McLean patients must come to MGH/BWH for blood draws)
- While the cohort sizes are relatively large, the number of people the group has actually collected (through Crimson) is very lowàabout only 10% of the possible cohort size
- Cohort MRP/MRP-SV numbers are abysmal. PPV for these cohorts are getting worse and performing poorly. Could the group possibly run a simple regression for these cohorts? àNo, because the numbers are too low
Where does the group stand with projection?
- The group is in the 4^th year of our 5 year grant, so the group needs to figure out where we stand quickly.

Next Stepsà 1. Final refresh of data mart

2. The group needs to decide what we are going to do with the MRP and MRP-SV cohorts

StudyGroup	Cohort	ClassificationType	N	TP	FP	PPV	PPV 95% CI Lower	PPV 95% CI Upper
Case	95NLP	NLP+EMR	45	38	7	0.844	0.712	0.923
Case	NoNLP	EMR	26	24	2	0.923	0.759	0.979
Case	MRP	EMR	25	14	11	0.560	0.371	0.733
Case	MRP-SV	EMR	5	1	4	0.200	0.036	0.624

StudyGroup	Cohort	ClassificationType	N	TN	FN	NPV	NPV 95% CI Lower	NPV 95% CI Upper
Control	MDD	Advertising	11	10	1	0.909	0.623	0.984
Control	SCZ	Advertising	15	13	2	0.867	0.621	0.963
Control	Control	EMR	13	13	0	1.000	0.772	1.000

All hands meetings

2011-09-16T08:10:00.001-07:00

Topic: Local i2b2-initiated federally funded spinoffs.

1.Kat Liao presented the RA DBP and the spinoff RA-CVD project. What is the relationship with risk for CAD/CVD risk in the general population (and the risk alleles) and that in RA. Our of 4453 in RA cohort (i2b2), 335 have CAD.

2. Jordan Smoller presented the Bipolar Disease NIMH grant. Reviewed the challenges of a very specific case definition. Claims codes alone seem to give positive predictive values (PPV) in the 20-50% range and the PPV of NLP is about 85% (with specificity of 95%).

3. Roy Perlis spoke about his R01 derived from the MDD-resistant-to-SSRI DBP. He is studying a MDD clinical and genetic risk risk algorithm/classifier. He is on the way to a 1500 population which represented 1/2 of all the drug response GWAS currently published in this particular domain?

4. Robert Plenge described the spinoff of the i2b2 RA DBP to the PGRN project. The project looks at genetic informants of treatment response and treatment toxicities. Involves Vanderbilt, Northwestern and Partners. Early result shows the portability of the NLP RA classifier.

Review of drug exposure methodology

2011-09-16T08:00:00.001-07:00

Given intermittent recording of drug exposure and clinical events, there is going to be a lot of censoring in the EHR data stream. This kind of data censoring is a methodological challenge and we reviewed various heuristics and comparisons that can be used to correct/account for this censoring. A lot of focus on modeling the frequency of observations.

Discussion of which pieces have to be locally vs centrally hosted

2011-09-16T06:16:00.001-07:00

For the next generation of i2b2, we are trying to minimize how many cells have to be locally hosted. Even more crucially, how many cells have to be locally customized and supported and how many can be generic. In other words, can we or should we reposition any abstraction barriers?

Multiple sclerosis DBP

2011-09-09T08:13:00.000-07:00

Xia et al,

Very extensive discussion of randomization procedures in selecting patient samples.

Back for Summer: CVD DBP

2011-09-09T07:11:00.000-07:00

Shaw, Cai, Churchill, Liao, Murphy, Kohane, Sordo, Savova

Reviewed the subsamples to see if we are getting the right DM rate.

Distributed Queries Across the Nation—Reverb from the SHRINE meeting

2011-07-26T10:05:00.001-07:00

A useful overview from Rich Elmore.

First Annual SHRINE meeting

2011-06-30T07:50:00.001-07:00

After an illuminating keynote by David Blumenthal, we heard of SHRINE implementations at Harvard, West Coast, and in Europe (the latter embryonic) as well as large national registries (IBD and RA) powered by SHRINE. In the second day, with a kickoff keynote by Patrick Taylor, we addressed the thorny issue of the regulatory, ethical and institutional aspects of SHRINE data sharing. The video and slides from this meeting will be available shortly.

i2b2 AUG in Boston

2011-06-29T07:57:00.001-07:00

The first annual i2b2 meeting was kicked off today (6/28) at noon at Harvard Medical School. After my introduction, Shawn Murphy provided the current roadmap and answered specific technical questions. Robert Plenge described the genomic studies in rheumatoid arthritis, preliminary results regarding cardiovascular disease

Bill Adams described his HOME (Health Outcome Monitoring and Evaluation) cell for i2b2 and had the temerity to run a live demonstration. They developed 21 measures around healthcare outcomes (e.g. lipid control, smoking cessation) and implemented these within i2b2. There was a good sidebar conversation with Shawn Murphy of the role of the core i2b2 team in supporting these new developments.

Keith Marsolo described talked about chart review with i2b2 and the use of i2b2 as a registry (for liver transplant). He too ran a live demonstration.

The onco-i2b2 project was described by our colleagues from Unversity of Pavia.

Brian Wilson described a new data exchange infrastructure and message queues to support LIMS of various stripes as well as genomic annotation pipelines. He also bravely demonstrated his listener dipatching/queueing functionality.

There were then a flurry of very technical discussions which engaged the developer and user community in detail. By mid morning on Wednesday, we started to discuss the relevance the of the SMART project to i2b2 which independently is generating a large developer community.

SHRINE, next generation functionality

2011-06-24T09:02:00.001-07:00

Weber, Churchill, Kohane, Mendis, Murphy

Discussed how to augment the payload of SHRINE (for v2) to include 1 by 1 viewable limited data sets rather than merely aggregate counts to enable subject recruitment across multiple sites.

cTAKES web service implementation

2011-06-24T09:01:00.001-07:00

Guergana demonstrated a prototype webservice for cTAKES (the NLP pipeline) which will be available soon.

SHRINE enhancements

2011-06-24T05:57:00.000-07:00

Murphy, Kohane, Churchill, Simons, Weber, Mendis

Reviewed the differences between the XML payloads of i2b2 and the payloads of SHRINE and what additional calls to the underlying i2b2 instance would be required to support patient-by-patient limited data set access across i2b2 instances.

Developing the next generation of SHRINE functionality

2011-06-03T06:13:00.001-07:00

Murphy, Kohane, Churchill, Weber, Simons, Bickel, Mendis,

Discussed the next set of functionalities in SHRINE, the distributed query system across i2b2. Right now in production it returns aggregate numbers of patients meeting search criteria. There are several additional next steps that will be reviewed at the SHRINE (6/29-6/30—Keynote day 1 David Blumenthal, Keynote day 2 Patrick Taylor) meeting following the AUG meeting in Boston.

A review of electronic health record-driven genomic research

2011-05-27T07:08:00.001-07:00

I recently wrote a review published in Nature Reviews Genetics that discusses how electronic health recocrds can be used to drive genomics studies. Also includes a survey of international efforts.

Cardiovascular Disease DBP

2011-05-27T06:47:00.000-07:00

Shaw, Cai et al.

The performance of the diabetes filter based on 7 variables was reviewed. It was surprisingly good. We then discussed what features NLP would be best applied to and the agreement was that medications would be the highest value in that regard.

Pre-competitive data sharing between pharma and with academia

2011-04-29T07:46:00.004-07:00

As part of NIH's Public-Private Partnership Program, a meeting was held in Washington, DC (4/28/2011) that brought together many from industry (particularly the pharmaceutical companies) and academia around the idea of pre-competitive data sharing for opportunistic acceleration of discovery pipelines while remaining respectful of privacy and property. i2b2 serves as the foundational platform proposed for this effort, in its implementation within TransMart. It will remain to be seen whether the governance and competitive concerns can be managed successfully in this initiative triggered by Eric Perakslis.

Modeling Disease Activity in RA

2011-04-08T07:48:00.001-07:00

Karlson et al.,

Discussed the current "standard of care" for disease activity (DAS28) for which there is a straightforward calculation. Can we estimate a highly correlated measure using NLP on the clinical record? This will require extracting temporal relations (e.g. activity AFTER anti-TNF therapy). With regard to the disease activity/state itself, we will start by identifying four states: Remission, Low, Moderate, HIgh (also Indeterminate if the note is unclear or too short) which will first have to be identified by our "gold standard" reviewers and annotations (using Knowtator).

Several machine learning approaches to predicting the DAS28 using NLP were reviewed.

Cerner adopts the i2b2 model

2011-04-05T08:34:00.001-07:00

This is an interesting piece of news seen on a mailing list. We were surprised to see this announcement regarding Cerner using i2b2 for its clients. As we do not have any relationship with Cerner in this regard, the precise nature of the implementation and its license are not clear. Nonetheless, for those of us working on secondary use of healthcare data using i2b2, this is another signal that our community is growing.

---------------------------------------------------------------------------------------------------------------------

Cerner i2b2 Node - Enabling Research Illumination

A client session of this Illumination is scheduled for Wednesday, April 20, 2011 12:00 PM CT.

Description of Session

The Cerner i2b2 node is a Cerner-hosted solution that improves the performance of i2b2 and facilitates secure data collaborations across multiple institutions. I2b2 (Informatics for Integrating Biology and the Bedside) is a National Center for Biomedical Computing. The informatics initiative is funded as a cooperative agreement with the National Institutes of Health (NIH). Using the Cerner i2b2 node, clients can perform cohort discovery queries on a de-identified dataset, save the query results, access patient identifiers for the saved query with IRB approval, and partner with other participating organizations to share data for cohort discovery queries. The service uses proprietary tools to map client data and improve i2b2 performance. The Cerner-hosted model reduces client investment in IT infrastructure, support, and maintenance

Benefits:

• Data mapping and security capabilities improve performance of i2b2

• Cerner-hosted model facilitates inter-institutional research

• Eliminates costs related to data mapping, security, system maintenance and IT infrastructure

Registration

To register for the session, click the link below. You will need a Cerner.com user name and password.

https://applications.cerner.com/members/illuminations/IllumDetails.aspx?illumid=4158

NLP

2011-03-25T10:43:00.001-07:00

Guergana Savova led a discussion on the annotation tool, with a focus on functional status (e.g. SF 36). Pete Szolovits provided ongoing commentary on the applicability to specific UMLS relations to these annotations.

Diabetes and CVD

2011-03-25T10:39:00.003-07:00

Stan shaw led a discussion of inflammatory markers in the diabetes population.

i2b2 EAC

2011-03-25T10:39:00.001-07:00

March 24th, External Advisory Committee came to Boston for a visit.

The EAC is constituted of:

Daniel Masys (chair), Vanderbilt University

Elmer Bernstam, University of Texas at Houston

Lisa Cannon-Albright, University of Utah

Peter Tarczy-Hornoch, University of Washington, Seattle

George Hripczak, Columbia University

NIH representative: Valerie Florance, NLM project officer

Very productive meeting with useful directional advice from the EAC.

i2b2 All Hands Meeting

2011-03-20T03:32:00.000-07:00

Eric Perakslis PhD presented his work on i2b2 in the J&J context and beyond with tranSMART. Interestingly, this i2b2 instance is hosted on the Amazon EC2 cloud. He had the temerity to run a live demo which worked flawlessly. Good Karma! Also the involvement of tranSMART with the Innovative Medicines Initiative in Europe with significant uptake by pharmaceutical industry (i.e. GSK/ECLIPSE, AstraZeneca, Pfizer, Novartis) was intriguing and encouraging.

His slide show is available here.

Other i2b2 business reviewed including the very success i2b2/NCBO tutorial last week at AMIA in San Francisco and the other SHRINE implementations that are occurring nationally.

Epigenetics

2011-02-28T09:19:00.001-08:00

Shaw, Kohane, Kasif, Plenge, Churchill, Liao, Murphy, Savova

Extensive discussions about which epigenetics marks are best captured from clinical discards and under what hypotheses.

Autoimmune DBP

2011-02-25T08:09:00.000-08:00

Savova reported that the new cTAKES pipeline is up and running against the production system.

Plenge reported on the state on the new RA datamart.

Liao has finished the chart reviews of a random sample of the 4500 RA patients. 10% had coronary artery disease. Of that 10%, 41% have definite CAD and 27% have probable CAD.

Feena provided an update on the sequencing project: 500 cases and 650 controls. Discussed a lot of the travails of de-"noising" and de-"batching" the variation found in the pooled samples (done without barcoding).

i2b2 Mapping Cell

2011-02-25T06:29:00.000-08:00

Review of the annotation procedures for NLP (in context of RA-CVD and multiple sclerosis).

2011-02-04T08:16:00.001-08:00

Present: Murphy, Savova, Szolovits, Liao, Cai, Xia, Gainer, Raoul, Kohane, Churchill

In a discussion led by Guergana Savova, we reviewed the Knowtator package that is built on top of PROTÉGÉ. The focus of the discussion was on the "squishy" and detailed assessments of patient functioning (e.g. "bending", "grasping", "doing housework" etc). We also discussed comparing the "bag of words" classification approach vs. the fine-grained sentence-level or concept-level annotation.

i2b2 phenotyping challenges

2011-01-28T12:15:00.001-08:00

Plenge, Bickel, Weber, Kohane, McGaw, Liao

Discussed the effortful process required to train a NLP filter for a given phenotype. We

Currently:

Step 1: Experts galore: (clinical, NLP, modeling/statistics, programmers)

Step 2: Build study-specific data mart

Step 3: Extract information

Step 4: Define "Gold Standards" from the extracted knowledge

Step 5: Build filter algorithm and apply to study at hand

Step 6: Not remember very well and loss of institutional memory regarding phenotypes

We reviewed several alternative, more fully automated models.

Auto-immune CVD

2011-01-28T07:56:00.000-08:00

Autoimmunity and CVD

2011-01-14T08:04:00.001-08:00

Karlson reviewed the i2b2/PGRN project on predicting response to disease modifying drugs in rheumatoid arthritis. This included adding functional status assessment to cTAKES. She articulated the first task is finding the best combination of structured and NLP-derived clinical variables that are predictive of disease activity. As an aside, Elizabeth noted that "Biologicals" have become first line thereapeutics in RA. Quite a change from what is in our EMR from 15 years ago.

Most of the session was a review of the use of the Knowtator tool on the rheumatoid arthritis corpus.

The remainder was focused on a discussion of the selection of the cohort with multiple sclerosis (MS) and a radiologically isolated precursor of MS (i.e. a radiologically made incidental diagnosis).

CVD and Diabetes

2011-01-14T06:49:00.001-08:00

Present: Rich Grant, Stan Shaw, Rahul, Murphy, Vivian Gainer, Plenge

As the meeting was gathering, Robert Plenge asked the right question: Given how slow the NLP optimization process is, what can we do to make it faster? He drew an interesting analogy between the era of contigs, BAC's and YAC's that was boutique-like and the industrial whole genome process.

Discussed Richard Grants latest CVD algorithm which heavily uses the text of the clinician's problem lists (not the billing codes). This was implemented as a very large and complex logical predicate, rather than a probabilistic or statistical model.

Temporal queries

2011-01-14T05:42:00.001-08:00

Present: Murphy, Weber, Kohane, McGow, Wilson, Mendis, Bickel

Reviewed Griffin's extensive proposal for a user interface. Batted around the implications for the underlying tables (while maintaining backwards compatibility).

Rheumatoid arthritis and PGRN

2011-01-07T07:42:00.000-08:00

Discussed the NLP challenge for defining Low/Medium/HIgh Disease Activity Score (DAS).

CVD and Diabetes Mellitus

2011-01-07T07:36:00.001-08:00

Shaw, Kohane Gainer, Liao, Churchill, Margarita, Murphy, Savova

Discussed the logistics of loading clinical notes on the 380K patients. Also discussed several control populations.

Temporal Reasoning

2010-12-17T06:27:00.001-08:00

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.

NLP

2010-12-10T10:40:00.001-08:00

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.

Autoimmune-CVD DBP

2010-12-10T09:49:00.001-08:00

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.

Release schedule/Temporal Reasoning

2010-12-10T09:48:00.001-08:00

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.

CVD-DM DBP

2010-12-10T07:29:00.001-08:00

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).

Selection of patients by NLP: reproducibility across institutions

2010-12-03T07:50:00.001-08:00

Led by Rheumatoid arthritis DBP

Northwestern, Vanderbilt calling in on Skype.

Reviewed the remarkably good concordance of the performance across several systems.

NLP

2010-11-19T10:21:00.000-08:00

Temporal Reasoning

2010-11-19T06:07:00.001-08:00

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.

Autoimmune CVD DBP

2010-11-05T08:22:00.000-07:00

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.

CVD & DM DBP

2010-11-05T07:46:00.001-07:00

Shaw, Savova, Liao, Churchill, Murphy, Gainer, Sordo, Kohane

Discussed how to learn lessons from other NLP CVD efforts that Guergana has been involved in (e.g. the eMERGE applications of her cTAKES framework). Discussed the addition of echocardiogram data.

Open source collaborations

2010-11-05T05:55:00.000-07:00

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.

Diabetes and Cardiovascular Disease

2010-10-22T07:27:00.001-07:00

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.

Open source projects etc

2010-10-22T06:56:00.001-07:00

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.

All Hands Meeting

2010-10-15T08:26:00.001-07:00

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.

Academic Users Group (AUG)

2010-10-15T08:17:00.001-07:00

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

An outline of the i2b2 proposal's roadmap for the next 4 years.

The new process for integrating and hosting contributions from the AUG.
The new cell to manage the interaction between a laboratory information system for biosamples and the IRB relationship to samples and studies and patients (Lynn Bry)
New commercial and open source terminology mappings that are easily uploadable into i2b2.
Use of i2b2 for registries (e.g. Cincinnati Children's leadership of a new AHRQ grant to use i2b2 for registries, particularly for pediatric inflammatory bowel disease, across 30 sites, and the CARRAnet registry)
Temporal query cell to support point and interval temporal queries

GARLIC—Genomic Analysis Results Library Integration Cell

2010-10-13T09:26:00.000-07:00

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.

NLP kickoff

2010-10-08T09:52:00.001-07:00

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.

Kickoff meeting of DBP #1

2010-10-08T08:52:00.001-07:00

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.

Temporal Reasoning

2010-10-08T07:27:00.001-07:00

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.

New DBP: Diabetes and CVD

2010-10-08T07:22:00.001-07:00

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.

i2b2 for EPIC users

2010-09-19T17:41:00.001-07:00

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:

https://bmi.cchmc.org/svn/i2b2/i2b2/public/data/Documents/

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.

i2b2 in Japan

2010-08-20T05:06:00.001-07:00

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!

MDD

2010-05-31T09:11:00.001-07:00

Minutes (courtesy Patience Gallagher)

Minutes:

PV
- Reminder of the original concept:
- - Group patients on SSRIs into 3 groups based on whether their medication had a high, medium or low affinity for the serotonin transporter - determine if there is a dose response for bleeding events
  - - Use this design instead of a case-control
    - Decided against self-matched analysis because that approach is best when the exposure is intermittent and has immediate, transient effects
  - Doing this study is important, as there is limited data available in the literature, but the prior is high (Smoller et al., 2009, Archives of Internal Medicine)
  - Outcome of interest: Bleeds (e.g. stroke, GI bleeds)
- Vivian, Roy and Victor have worked on various iterations of the same general idea – the group needs to decide on final approach.
- The Plan:
- - Use a test of proportions (Zak has a reference for this that he can distribute)
  - - (This approach is kind of like a Chi Square)
  - Use only patients on monotherapy
  - - We are not looking at dose of medication, just where the prescription falls on the affinity spectrum, which will be divided into three groups (high, medium and low affinity)
  - Start with a patient’s first exposure to AD (not first event) à look forward 6 months. If event doesn’t happen in those six months, restart the clock.
  - - Although six months is the primary window of time, a sensitivity analysis of 30 days will also be done.
  - If a patient switches categories (goes from high to medium affinity drug) they are censored. However, if a patient switches from one drug to another within the same affinity category, they stay in the analysis.
  - As a control, we’ll look at patients with: MI, DVT, prostate cancer, colon cancer, asthma, and breast cancer (?)
  - The 3 groups (high, medium and low affinity) will be compared on visit intensity, age, gender
  - - As long as visit intensity isn’t associated with just one of the categories of affinities, it should not be a confounder.
- Victor has written most of the code needed for these analyses, so he will incorporate the ideas discussed today and bring the results to the meeting next week.
- Additional issues to consider:
- - Using another psychotropic comparator as a negative control would be good, but difficult to do.
  - Look at depression response (do patients actually get better while on AD?)
  - Collaboration with the Stroke Service at MGH (Dr. Furie) – They are interested in collaborating – Roy will follow up with them.
  - - They have a comprehensive stroke database (that includes imaging data) that could be incredibly useful for the PV component – And reciprocally, our AD exposure info/algorithms would be beneficial to them.
    - Protocol will need to be amended to incorporate their data in our analyses

Rheumatoid Arthritis

2010-05-07T08:21:00.000-07:00

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.

Technology updates

2010-05-07T06:13:00.001-07:00

Kohane, Murphy, Weber, Churchill, Wilson. Mendis

Reviewed plugin architecture and convergence between web and Java client.

Reviewed "normals" project.

Crimson Cell

2010-04-30T07:13:00.001-07:00

Wilson, Bry, Murphy, Kohane, Churchill

Discussed progress on the Cell. Includes support for approved protocols and specimen details.

Rheumatoid Arthritis

2010-04-09T07:52:00.000-07:00

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.

Planning for hands on i2b2 tutorial for AMIA NOW

2010-04-09T05:53:00.001-07:00

Mendis, Wilson, Savova, Weber, Kohane, Churchill,

Discussed the content for a hands on tutorial for the upcoming AMIA NOW.

New members of the i2b2 team

2010-04-02T06:23:00.001-07:00

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!

AMIA Translational Summit

2010-03-10T18:38:00.001-08:00

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.

Major Depressive Disorder

2010-02-26T06:57:00.001-08:00

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.

Rheumatology/Rheumatoid Arthritis

2010-02-12T08:26:00.000-08:00

Plenge, Karlson, Liao et al.,

Planning for Kat's maternity leave.

Improving smoking history.
- Discussed the challenge of inaccurate notes by "cut and paste" documenters.
Improving family history.
Starting gene-environment analysis

Large pharmaceutical companies interested in collaboration.

Major Depressive Disorder

2010-02-12T06:58:00.000-08:00

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.

T-con with Leicester

2010-02-05T12:28:00.001-08:00

We just had an interesting discussion with Nick Holden and his colleagues about the adoption in the UK of i2b2 for discovery studies.

Rheumatoid arthritis

2010-02-05T07:54:00.000-08:00

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.

Rheumatoid Arthritis

2010-01-25T07:25:00.001-08:00

Plenge, Karlsson, Liao et al.

Discussed paper under review and how different diagrams of the NLP process need to be improved.

Major Depressive Disorder

2010-01-22T07:17:00.001-08:00

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.

Interesting commercial implementation of i2b2

2010-01-20T10:00:00.001-08:00

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?

The burden of obesity inferred through high precision rules

2009-12-29T19:27:00.001-08:00

An interesting presentation by Ted Pedersen on finding obesity morbidities in i2b2 records.

Major Depressive Disorder

2009-12-14T19:57:00.001-08:00

German i2b2 implementations move forward

2009-12-14T08:45:00.001-08:00

Thanks to Sebastian Mate for this update on the first German Academic i2b2-Workshop.

They had visitors from the universities of Goettingen, Ulm, Hannover, Giessen and Leipzig. Some of them had to travel hundreds of miles (see attached map) to visit them in Erlangen. Goettingen and Leipzig have i2b2 instances running, the others will try it out.

Topics covered included at the meeting:
(1) Clinical Data Warehouse in Erlangen(2) i2b2 Overview, motivation and work in Erlangen(3) i2b2 in 30 Minutes - how the Erlangen Package works, with live-installation ;-)(4) The simple SQL-based Erlangen ETL approach - how we load data into the hive(5) i2b2 HIS-mapping - how we map hundreds of attributes from our HIS into the i2b2 instance (ONT and CRC)(6) TMF PID-Generator and i2b2(7) TMF Pseudonymization Service

RA

2009-12-11T08:01:00.001-08:00

Discussed the SNP's on the genotyped data and how the continent of origin and the PHS labels of ethnicity are highly concordant.

Open Source

2009-11-17T19:12:00.001-08:00

A very insightful response from Fred Trotter. He lays down the options in a very nuanced and clear fashion. Much appreciated.

Major Depressive Disorder

2009-11-12T08:17:00.000-08:00

Perlis, Smoller, et al.,

MInutes courtesy Patience Gallagher.

· Longitudinal Classifier

o Roy and Victor will finalize parameters of algorithm

o Victor will then report (and provide a visualization of):

§ % depressed, % well, # of all notes, etc

o To query Crimson: Victor will provide a list of medical record numbers within the two groups of interest (responsive and resistant) to Lynn Bry who can then report how many samples are currently available within Crimson

§ Parameters may need to be readjusted, depending on response from Crimson

· Discussion of Validation

o The issue with last week’s approach:

§ The algorithm is based on the text, so the first level of validation should not use information (i.e. clinician’s extensive knowledge of a patient) that is not in the text.

o New validation plan:

§ STEP ONE:

· GOAL: Determine if an expert clinician’s classification (based on notes only) is the same as the result of the algorithm

· Pull successfully classified notes

o All of a patient’s notes will be reviewed

o Clinicians will be blinded to the results of the classifier

o The sample of notes will reflect the results of the algorithm: “Random but representational”

o To keep the validation clean, it will be a “case-control” model - Treatment resistant vs. Responsive

o For now, only the electronic medical record will be used.

§ The consensus was that patient charts would be more annoying than beneficial, and the electronic records probably have sufficient information

§ Additionally, the information from the paper records is not integrated into the algorithm

§ May look at paper records down the road

§ STEP TWO: Compare list of patients that Roy knows are treatment resistant or responsive and run their notes through the classifier

· (Tianxi says this will be beneficial as it will give more power to the classifier)

§ STEP THREE: Use the Quick Inventory of Depression Severity (QIDS) as an external source of validation

· Many patients have QIDS scores in their charts – can determine if the algorithm classification is consistent with performance on the QIDS – this would be a cross-sectional measure

o The output of this approach would be: “Among patients classified s depressed, the mean QIDS score is ____”

§ NEXT STEPS:

· Do first level of the validation over the next few weeks.

o Victor will pass the notes to Roy.

o Roy will be the sole clinician reviewing the notes

· Manuscript:

o Victor and Tianxi have provided their input to Roy

o Roy will integrate this information and then re-distribute the manuscript to the group

· PV

o Update from Victor on obesity:

§ Compared the BMIs of this data set with all other patients and the distribution of the MDD sample is very similar, but right shifted compared to majority’s BMI distribution

· This makes sense! - Being depressed (and on antidepressants) leads to weight gain

Widening the Use of Electronic Health Records Data for Research

2009-10-30T05:59:00.000-07:00

A symposium hosted by the National Center for Research Resources (NCRR). Louise Ramm, Deputy Director of NCRR provided framing challenges and welcome. Zak Kohane introduced use cases, sources of and reviewed the false dichotomy between health-record based research and clinical trials..

Gary Gibbons provided a perspective of disease in the African-American population as an exemplar of a complex orphan disease in the sense that like rare orphan diseases, it is understudied and insufficiently treated. He also pointed out how in many parts of the country underserved minorities are located away from the academic health centers that have made the most inroads in the use of electronic health records.. Therefore, institutions such as Morehouse School of Medicine have their work cut out for them (and not a lot of resources) to integrate data from a large number of only lightly affiliated practices. That same challenge presents an opportunity to be even more impactful in an orphan disease of epidemic quality. Professor Gibbons also urged a broadening of the captured context beyond what is conventionally captured in a standard (brief) healthcare visit. Environmental variables that are highly penetrant, much more so than many genomic markers are poorly captures. He concluded by reviewing the current compelling information about pharmacogenomic differences, and population genetic risks and also the wide holes in our knowledge of these as they pertain to various groups within the USA.

Andrew Auerbach from UCSF addressed comparative effectiness research and its translation into "Health system innovation research" Described how much can be done with charge data, and how additional codified data types (e.g. medications) can further improve the quality of that data. Closed with a discussion of how the various stakeholders in using EHR data for research (.e.g NIH, Payors, health systems leaders, physicians, and patients) might be well aligned or not. Put us on notice that IRB's are unfamiliar about distributed query systems and/or grids and this is becoming at last an obstacle for many CER studies. Summarized several use cases such as optimal length of treatment of pneumonia? Can a patient-focused discharge checklist reduce risk for readmission?

Robert Plenge described his use of i2b2 and electronic health records for genotypic research and discovery of endophenotypes.
John Brownstein reviewed non-traditional public health research using institutional data and non-traditional, non-institutional healthcare data extraction and analysis.

i2b2 Academics Users Group—Natcher Building, NIH

2009-10-28T09:44:00.000-07:00

Zak Kohane summarized some of the new i2b2-based projects that recently were announced including a South Carolina consortium (a GO grant funds the automated consent component), a pediatric rheumatology research network including 60 sites (NIH GO grant), Shawn Murphy is working with an imaging consortium to better integrate images into i2b2 instances (CTSA administrative supplement) using XNAT/BIRN infrastructure, and B.U. and U. Mass received a GO grant to study health disparities using i2b2 as infrastructure. Lynn Bry received a 2 year R01 under ARRA for the Crimson-i2b2 integration project.

Susanne Churchill welcomed the group and noted that there is a consortium of European i2b2 users/implementors/refiners that are putting together a proposal for joint work across the European Union (for EU funding). She noted that the AUG now numbers over 100 and represents 30 healthcare/academic institutions including 5 internationally.

Shawn Murphy summarized several new developments including

Release Candidate 1.4 to support the Enterprise including: analysis views, improved role-based access and auditing, replacement of Gridsphere with webservices and AJAX client, Microsoft Active Directory integration, obfuscation of results for privacy purposes.
In the future, the distributions of i2b2 be via configurable VM's so that the functionality can be attached to local databases without requiring a full install. The full source code compile and install will still be available.
Eclipse plug-in "store" where developers can contribute their own plug ins and where users can download the plugins they want.
More support for derived data (e.g. to systematically return NLP concepts derived from the clinical notes

Lynn Bry described the Crimson system and how i2b2 discarded sample have far higher utilization rates than other samples (e.g. for biorepositories). She also described the Sample Ontology and how she is borrowing from WHO and SNOMED to standardization. The system includes an ontology manager to allow local ontology management and update samples. Also described are the IRB permissions data from RC 1.4. Will work towards multisite studies within the two year implementation time frame. Lynn described the Enterprise Master Specimen Index that tracks samples and patient relationships in various levels of identity (consented identified, de-identified, and anonymous samples).

Dan Housman and Peter Emerson from Recombinant were invited into the AUG for the discussion segment about sample management (because of the AUG's wish to keep companies at arm length) to discuss their own efforts in sample management. They made it clear that all their developments they are involved in will be contributed back to the i2b2 community as fully open source code.

Andy McMurry summarized the status of the distributed querying system called SHRINE that is now implemented at several Harvard-affiliated hospitals and several West Coast academic health centers (e.g. UCSF and UW) that is now fully IRB approved (at Harvard) for queries returning aggregate numbers (across demographics, laboratory results, medications and diagnoses). Andy also made a very clear several technical hurdles that were overcome including the ontology matching process (on the fly). Finally, he announced the availability of SHRINE code in a fully open source codebase.

i2b2 CICTR presented by Nick Anderson. They have been able to query muiti-institutional "anonymized PHI data". Application is in diabetes and cardiovascular disease. Described technical, governance, ontology and evaluation process that CICTR is driving. Nick described the heterogeneous systems that CICTR has to query across. Nick distinguished the need for high level institutional support which is a sine qua non requirement for success and the need for a broad range of paid technical personnel.

Keith Marsolo from Cincinnati's Children's reported on their Epic roll out and how that relates to their i2b2. Described their quality assurance efforts. Notes the challenge of the firehose and makes the acute observation that most investigators just want a spreadsheet and anything more complicated than that tends to get ignored. Keith also emphasized their goal to allow streamlined adding of research data to the clinical data. He makes the important point that "age at FACT" is essential for pediatric applications to allow them to be easily accessed in the i2b2 workbench. Keith mentioned using i2b2 for research databases for Eosinophilic esophagitis, and IBD.

Phil Reeder from UT Houston talked about medications mapping. It is a challenge and they have chosen to map to RxNorm and then manually had to map into SNOMED CT (perhaps their database was out of date). Started from an All Scripts database and had a semi-automated process. Notes that every year there are at least a 1000 new drugs (i.e. different packaging, pill sizes etc). Brought up the thorny (and annoying IMHO) of the proprietary mappings to standard vocabularies.

Ralph Zottola and Edward Westrick described the effort at U. Mass (data sourced from Meditech system, REDcap EDC, biorepository, EMPI, Allscripts, and departmental systems) where they are up to 2,000,000 patients. Edward described the managed care network (1000 physicians) that plugs into U. Mass and how quality measures inform the discussions and bargaining with payors. Reviewed different measures including HEDIS, patient experience, was well as the increasingly important Relative Resource Utilization (Efficiency). Demonstrated how knowing what is going on in the healthcare institution allows for a sober and leveraged discussion with payors. The healthcare system approached the medical school and settled on i2b2 and they already have seen that they can accurately forecast their performance and to provide a feedback loop (with financial incentives) to healthcare providers. Ralph pointed out that the fact that clinical operations are using i2b2 is also causing an improvement in the quality of the data being delivered to the data marts.

Iain Sanderson and Jihad Obeid. Iain started by describing a very comprehensive Informatics Initiatives in South Carolina. They have a unified IRB with a goal of clinical trials across the state. There is both a scientific and a funding motivation in this. There are three informatics initiatives have dovetailed (CTSA biomedical informatics, HSSC IT business plan, and a GO grant on consent). This has resulted in the South Carolina Integrated Platform for Research (SCIPR) that uses i2b2 for the clinical research data warehouse. In the process they are adopting a wide range of open source solutions including Sun Microsystems' JavaCaps. Iain reports that the data sharing agreements between the 6 centers across HSSC are under way and likely to result in an MoU in short order. Iain also described the beginnings of the consent management/gathering system, the permissions ontology and documenting the different consent processes at the institutional members of the HSSC. Finally, Iain discussed how personal patient health portals may be used to provide the patient-facing part of the network.

Rheumatoid Arthritis

2009-10-23T11:33:00.001-07:00

Plenge et al.,

3/4 of the genotyping is completed.

Manuscript to be submitted today regarding phenotyping accuracies.

What's next

2009-10-23T07:24:00.003-07:00

Discussed what might be the priority areas for i2b2 in Core 2 for the competitive re competition.

The RFA has not yet be announced so the discussion was, of necessity, wide-ranging.

Major Depressive Disorder (and Bipolar Disease)

2009-10-23T07:24:00.001-07:00

Smoller, Perlis, et al.,

Discussed the challenge of merging note-level NLP conclusions to wholistic patient evaluations.

Reviewed various Bayesian and (more broadly) machine learning approaches to defining which notes contribute most to the accurate classification of the patient phenotype.

Major Depressive Disorder: 10/16/09

2009-10-23T07:11:00.001-07:00

Courtesy Patience Gallagher

Minutes:

Collapsing terms

o McLean admission à change to psych admission

o List of terms that Jordan gave Margarita that we didn’t necessarily annotate, Margarita will add after.

o Terms that have the same regular expression will be filtered at the end

o Medication category: fga

We annotated as IW bipolar, but last time we said was CW, which one is it?
Sergey says right now doesn’t matter, because the computer will decide
We will keep it labeled as IW

o Li/vpa/lamtical à change to mood stablilizer

Add term mood stabilizer(s)

o Neuro/cognitive impairment includes

Confused and disoriented
Gross cognitive impairment
Significant cognitive deficits
dementia

o Agitation includes

Hyperactivity
Hyper
pacing

o dx depression includes:

depressive disorder
dsythymia

o bipolar disorder includes:

dx bipolar disorder
296.0, .1, .4, .5, .6, .7
- .2, .3 are MDD, so we cannot say 296.x = BPD

o Inappropriate behavior category, leave in:

Wanting to disrobe
Inappropriate sexual contacts (do not put with excessive pleasurable activities)

o Rapid cycling

4 or more per year

o Mania will include

Category now called “mania/manic”
Category now called “manic episode”
Cycling, cycles (not specified as rapid/less than 4 per year)

o Typos will include variations on spellings of:

Grandiose
distractibility

o “loose associations” will be its own category

o Depressed episode à put with hx depression

o “unable to read, study, concentrate” à put with distractibility

o “tx bipolar disorder” à add in term “rx”

o Hypomania will be own category

o hyper mood à mood elevation

o Delete:

§ Line 310: dx substance abuse, schizophreniaParanoid schizo-affected disorder

§ Out of control

Big group: 9:30-10:30

· Protocol in the grant

Are we doing what we said in the grant? For ex. Step #3
- In grant, describes that classic way of doing NLP
- You come up with list of terms from your head without looking at notes.
- Then expand these terms, add regular expressions, negation
Our method
- Is a hybrid of the 2. We annotated notes, but we also came up with a list of terms
- Annotate notes, generate list of terms, create regular expression, group, add in a priori terms, Tianxi goes through them and takes out terms that don’t matter (lasso), then feed to the computer
- The IRB will not really care that this is slightly different.
Which method is better?
- Unknown
- Classic model relies on what’s in your head, our method relies on # notes reviewed
- We could try to compare, but it’s a little too late because our list of terms wasn’t blind to the notes
Dr. Savova ) will be coming on boad as NLP team lead
- Would be good for her to give mini lecture about NLP so we are prepared to present at conferences
- Should consult with her about project
Negation
- So far Margarita has only added negation to some terms
- Should modify algorithm so that every term also has corresponding negation term
- Negation terms are very common in psych notes
- Sergey to see if this can be done, although a lot of work
- Would be useful for future i2b2 projects
- Margarita explained that she plans on conducting a small validation study
- - For a particular patient, she can provide an idea of how strong the diagnosis we assign (e.g. BP2) is by showing what are the arguments for/against placing a person in a particular class

· Next steps:

o Jordan, Vivian, Margarita, Sergey, Victor, Roy to meet on Tuesday, October 20^th 10:00 – 11:00 to finish collapsing term.

Rheumatoid Arthritis

2009-10-09T08:07:00.000-07:00

Plenge et al,

384 genotypes of risk alleles from prior studies.

A subset of the genes will shortly also have their exons resequenced.

Discussed adding antibody studies to the RA datamart. As a preliminary to adding the SNP and other data sets.

Major Depressive Disorder

2009-10-09T07:33:00.000-07:00

Perlis, Smoller, Iosifescu et al.,

Discussed the new privacy guidelines that come with the new Recovery Act. This may make it harder for those of us who are trying to advance medical science and it is unclear if it will slow down those who are trying to commercially exploit patient data. What it is certain is that it will increase the workload/opportunities for lawyers specializing in medical privacy.

Victor reported that he is running Tianxi's logistic regression model of the NLP features on the 2M notes in the MDD data mart.

Discussed the cross-DBP NLP challenges worth investing some hardening on. So far this includes cigarette smoking, alcoholism, obesity, and other substance abuses.