Skip to main content
Premium Trial:

Request an Annual Quote

Windber Institute Taps Intelligence IT Firm to Co-Develop Translational Medicine Infrastructure


The Windber Research Institute said this week that it will use content-management software from Concentia Digital to support an IT infrastructure for managing and accessing patient information, tissue samples, and molecular-level data.

Concentia's flagship software, called the Media Archive System, is primarily used within the intelligence, defense, and broadcast markets to manage large amounts of images, video, and metadata. The WRI agreement marks the company's first foray into the life science sector.

The firms may eventually commercialize a version of the system they are co-developing, but have not yet finalized any plans to do so. "The current vision is that there would come a time when this would be infrastructure that would be commercially available," Richard Mural, WRI CSO, told BioInform. He did not elaborate.

Duane Shugars, CEO of Concentia, said that the company is interested in marketing MAS to other life science customers. "We may look at branding it with Windber to go to market together, but that would be up to them," he said.

Shugars said that the company began the collaboration a month ago, and found that "out of the box, we were able to give them 80 percent of what they wanted to index." The primary areas of development for the firm were in the data model, data standards, and interface, he said.

"What we'd like to do is develop the data model in such a way that as you move into a new disease area, you're reusing most of the infrastructure and just adding the things that are necessary for the disease-specific part."

Mural said that Concentia's experience in the defense and intelligence community proved to be a strong foundation for the WRI project. "As a result, they've built a lot of tools for dealing with very large data sets and filtering through very large data sets … particularly in the realm of storing images, storing video, and storing metadata with images and being able to quickly retrieve them," he said.

So far, Concentia has developed a prototype of the infrastructure that includes some of WRI's data. "By the end of the summer into the fall, we will have all their data and all the imagery that's associated with it in the system, and possibly viewable by outside organizations through a secure web interface," Shugars said.

Through a partnership with the Walter Reed Army Medical Center, WRI has access to more than 20,000 annotated breast cancer tissue samples, with more than 500 data fields on each patient. This information is integrated with genomic, proteomic, gene expression, and imaging data in an Oracle-based data warehouse that was co-developed with InforSense.

The institute's goal is to create a "translational medicine research infrastructure" that will enable researchers within the institute and those affiliated with its partner organizations to track, store, visualize, analyze, and mine clinical and experimental data.

Mural told BioInform that WRI is currently moving beyond its current focus on breast cancer and into other disease areas, including cardiovascular research and gynecological cancers, including cervical, endometrial, and ovarian cancer.

This goal required a complete overhaul of the institute's previous approach to its IT infrastructure, Mural said. "One of the things we became aware of was that we really need to develop a patient-centric data model, so that regardless of the particular disease you're looking at, you have a common data model in which to map the patient data."

Mural said that previous versions of the WRI system were built upon a disease-centric model, which would not have scaled with its expanding research goals. "What we'd like to do is develop the data model in such a way that as you move into a new disease area, you're reusing most of the infrastructure and just adding the things that are necessary for the disease-specific part," he said.

In line with this strategy, WRI is partnering with several research institutes working in different disease areas, but with similar goals. Last week, it announced a collaboration with the Shanghai Center for Bioinformation Technology in China, in which it will jointly develop data integration, data visualization, and data mining technologies for translational medicine research.

That agreement builds on a similar agreement WRI signed earlier this year with the Erasmus University Medical Center in Rotterdam, the Netherlands, to co-develop a translational medicine data warehouse for clinical, imaging, and proteomic and genomic data [BioInform 02-10-06].

Mural said that both institutes have a similar interest in the "patient-centric data integration problem" that WRI is sorting out. "They're all part of the same strategy," he said.

Through its work with InforSense, WRI has already developed much of the underlying technology for the data-management system, Mural said. Concentia will primarily contribute data-retrieval technology and an improved user interface that will enable researchers to search by any one or several parameters. The MAS technology will also manage requests and fulfillment of tissue samples and high-resolution images.

Mural said that WRI envisions "two major ways of accessing the data" through the system. The first would be in the research setting, in which a researcher might want to select patients for a further study based on very specific parameters. "You might, for a particular study, want to find all patients in the database for breast cancer that are African-American, pre-menopausal, with particular diagnoses that have had digital mammography and ultrasound, because you want to look at those two modalities," he said.

The second goal, which Mural described as much longer term, "is sort of a physician-support interface" in which a doctor would use the system to store and manage data in his or her own patients, but would also have access to large amounts of anonymized research data stored elsewhere in the network. "So they can say, 'For this patient that I'm looking at, where I've got all of these parameters, show me similar patients in the database and what their outcomes were.'"

Mural acknowledged that this latter goal "would be a different way of practicing medicine, and isn't something that is necessarily done now." However, he said, "I think as these databases grow that that ability should be something that the medical profession would find useful, so we're working to go in that direction as well."

Mural said that the WRI data warehouse and patient-model infrastructure should be in place by the end of the year, "so that at least for a couple of these diseases we will be able to cross-reference patients, retrieve images, do the research types of stratification in a fairly straightforward way — and to also have it at the point to be able to expand the data model into diabetes, for instance, meaning something that would take on the order of a few months, rather than something you might take a year to rebuild the data model so that it could accommodate a new disease modality."

— Bernadette Toner ([email protected])

Filed under

The Scan

Study Finds Sorghum Genetic Loci Influencing Composition, Function of Human Gut Microbes

Focusing on microbes found in the human gut microbiome, researchers in Nature Communications identified 10 sorghum loci that appear to influence the microbial taxa or microbial metabolite features.

Treatment Costs May Not Coincide With R&D Investment, Study Suggests

Researchers in JAMA Network Open did not find an association between ultimate treatment costs and investments in a drug when they analyzed available data on 60 approved drugs.

Sleep-Related Variants Show Low Penetrance in Large Population Analysis

A limited number of variants had documented sleep effects in an investigation in PLOS Genetics of 10 genes with reported sleep ties in nearly 192,000 participants in four population studies.

Researchers Develop Polygenic Risk Scores for Dozens of Disease-Related Exposures

With genetic data from two large population cohorts and summary statistics from prior genome-wide association studies, researchers came up with 27 exposure polygenic risk scores in the American Journal of Human Genetics.