Kevin Davies of Bio-IT World wrote the article “Running tranSMART for the Drug Development Marathon”, an overview of a translational medicine data warehouse project at Johnson & Johnson, led by Eric Perakslis, VP of R&D informatics, managed by Sándor Szalma, senior research fellow, and delivered by Recombinant during an 18-month implementation.

Davies wrote: “TranSMART helps investigators mine drug target, gene and clinical trial data to aid in predictive biomarker discovery, chiefly in immunology and oncology. Perakslis says it is an ‘amazingly advanced’ data warehouse that compares favorably with many such efforts he’s seen in the Pharma world.”

Davies highlighted the open platform approach by Recombinant: “Perakslis is currently having discussions [with Recombinant] about a Red Hat approach where a lot of the advanced analytics is made open source. ‘I’m not running a commercial software company,’ he says. He’s already offered the software to Guna Rajagopal, a colleague at the Cancer Institute of New Jersey. In addition, St Jude Children’s Research Hospital, UCSF and other centers are all considering the adoption of the i2b2-based platform.”

Labels: Data Warehousing, i2b2, Open Source, Translational Research

The American Medical Informatics Association (AMIA) honored Zak Kohane yesterday with the Donald A.B. Lindberg Award for Innovation in Informatics for his work with Informatics for Integrating Biology and the Bedside (i2b2). Dr. Kohane is the director of the Children’s Hospital Informatics Program and Lawrence J. Henderson Professor of Pediatrics and Health Sciences and Technology at Harvard Medical School.

Labels: i2b2

I had the pleasure to attend the PHIN conference in Atlanta last month. PHIN refers to the Public Health Informatics Network, a Centers for Disease Control and Prevention (CDC) initiative to improve the exchange of health data.

Recombinant was somewhat of a duck out of water in regards to public health because our focus revolves around clinical research and quality reporting through data warehousing. However, there were quite a few conversations where public health considered themselves uninvited to the table where data was being served.

Our knowledge about i2b2 and the capabilities of clinical systems for data management at hospitals led to some lively discussions and a handful of new opportunities. For example, the CDC has struggled to connect with chronic diseases and i2b2 would be an ideal way to connect to healthcare delivery networks with data management strategies around conditions such as coronary artery disease (CAD), hypertension, diabetes, and chronic obstructive pulmonary disease (COPD).

I met some vendors of interest that intersect with the clinical data warehousing world. A company in the Boston area called Diagnosis One has invested in developing a service including thousands of validated clinical decision support rules. We discussed combining their rule sets with the content that gets extracted and loaded into the Recombinant Data Trust. If anyone is interested in combining both a data warehouse and a privately maintained decision support rule library that is curated by physicians, give me a holler and we will pull together a collaboration with the folks at Diagnosis One!

Another vendor, Trizano, developed an open source public health application that could be a powerful tool linked with a data repository to handle the workflows for public health issues. Given that they focus on the beekeeper model like Pentaho, their licensing model should be compatible with research frameworks such as i2b2. Trizano’s tools might be another key application to drive value out of existing data sets.

The drive for meaningful use has also pushed a lot of interest in HIEs, thus these sorts of tools were well-represented at the conference. I was pleased to encounter the booths focused on IHE-HIE systems. The exhibitors clearly conveyed the message that an HIE doesn't ensure the sort of interoperability that is typically suggested. To ensure one will scale to a national level like an NHIN, the HIE must be implemented to satisfy IHE standards. Among the frustrating and somewhat odd outcomes from the rushed drive toward meaningful use by healthcare systems, is that many HIEs may never be interoperable because even the integration systems have put barriers in front of interoperability.

Based on the PHIN tour of HIE technology, it is now my preference to see more IHE-based HIEs. The Europeans and Canadians are rapidly adopting IHE, but in the United States we haven't wholeheartedly engaged in the standards and efforts at the healthcare-network level. Perhaps it isn't too late for national legislation or state initiatives to include requirements that satisfy international standards.

Dan Housman
Managing Director, Analytical Applications

Labels: Data Warehousing, i2b2

The i2b2 and related Crimson team recently published an article titled "Instrumenting the health care enterprise for discovery research in the genomic era". The article describes the potential to acquire large-scale samples needed for genetic studies by integrating data warehousing with lab systems.

Hospital network infrastructure for phenotyping and collecting biospecimens for biorepositories and omics data acquisition has so much more scale than current methods. New ideas and pioneering work in this area are likely to make a substantial impact in how translational research evolves over the next few years.

Recombinant expects to see both consented and non-consented/discarded sample models for high-scale phenotype-genotype matching. Ideally these models will integrate with translational research stacks such as i2b2, caBIG (caTissue/caGRID), and frameworks like GenePattern for analytics.

Recombinant is working on multiple projects to bring some of these ideas into an open source tool set that can be implemented across sites via the same model as i2b2.

Dan Housman
Managing Director, Analytical Applications

Labels: i2b2

Marcia Gulesian wrote a blog post titled “Functional Design of an Ontology” which provides a helpful introduction and analysis of i2b2.

Dan Housman
Managing Director, Analytical Applications

Labels: i2b2

Recombinant presented two posters at the 2009 caBIG® Annual Conference in Washington, D.C. last week. Both posters are now available for download from our website.

• A Proposed Architecture for Connecting caIntegrator2 and i2b2
  By Dan Housman, Joseph Adler, and Aaron Mandel
  Download
  
• Ontomapper: A Tool to Integrate i2b2/SHRINE and caGrid
  by Aaron Mandel, Aaron Abend, and Rob Wynden
  Download

Recombinant was also quoted by Vivien Marx in the BioInform article “caBIG Support Service Providers Sorely Needed, but Also Sorely Need More Business” on July 23, 2009. The original article is available online (registration required), or as a PDF download.

Labels: caBIG, i2b2, SHRINE