Skip to main content
Premium Trial:

Request an Annual Quote

Windber Taps InforSense to Help Build Bedside to Bench Informatics Platform

Premium

The Windber Research Institute is aiming to move beyond the conventional concept of translational medicine, according to CSO Michael Liebman. "Translational medicine is always spoken of as going from the bench to the bedside," he said, "but we try to emphasize it also going from the bedside to the bench, because if we don't do it in that reverse direction, then the basic researchers don't know really what problems should be solved."

In designing an informatics infrastructure in line with this philosophy, Liebman said the WRI has had to integrate many types of data that are not traditionally included a typical research IT pipeline — such as image data, patient records, and clinical information — along with the various types of molecular-level data that have already confounded other integration efforts.

Last week, WRI said that it is partnering with workflow software provider InforSense to help develop its translational informatics platform, which Liebman said he envisions as "a command and control center for medical diagnosis and treatment."

WRI and InforSense will work together to expand the capabilities of the company's Open Discovery Workflow technology to handle the scope of the platform. Liebman said that two InforSense employees will work on site at WRI. Those employees will also work with informatics developers at Walter Reed Army Medical Center, WRI's primary clinical partner, to ensure that its clinical records are integrated with the rest of the system.

"Part of what we're looking at is really how to take what we've already built as a LIMS system with Cimarron and extend it to become the clinical laboratory workflow, so that it takes our clinical and molecular data … and building a whole environment around patient management," Liebman said. InforSense will be "a big partner in doing some of that."

The first phase of the project, which is expected to take around nine months, is a transition of WRI's data warehouse to Oracle from the Teradata platform. The Teradata system was installed in late 2003 [BioInform 10-27-03], and Liebman said that WRI is currently "in the process of building the models to move to Oracle." The conversion is necessary for "a variety of reasons," he said, one of which is a "compatibility issue" with the NCI's caBIG (Cancer Biomedical Informatics Grid) project, which has standardized on Oracle.

The new data warehouse will also be modeled on "more of a distributed manner as opposed to just a single data set," Liebman said. One reason for this is the project's plan to incorporate imaging data from a variety of platforms, including ultrasound, PET/CT, mammography, MRI, and pathology slides. "What you're using with images may be slightly different in terms of your needs at certain times than what you need with some of other information," he said.

Liebman said that WRI has a "unique relationship" with GE Healthcare that provides access to a number of state-of-the-art imaging technologies. "We have in mammography both film and digital, we just got in a 4D ultrasound, we have one of the few 16-slice PET/CT, and one of the few 3T MRIs," he said. "What we're doing is building or testing the ability to fuse existing technologies to understand how to further extend their sensitivity and specificity for diagnosis."

This goal involves "mathematically transforming the way we would use, say mammography and ultrasound, and then potentially [using] additional biomarkers to enhance the diagnosis of a patient."

Ultimately, Liebman said, WRI's informatics platform is intended to support research in a number of disease areas, including oncology and cardiovascular disease. While some of the platform's requirements are similar to those being developed in caBIG, "our model is bigger than their model," Liebman said. "We're very focused on adding the concepts of temporal data, and disease as an overall process, and they're more capturing a more restricted time event."

WRI intends to be compatible with caBIG, he said, "but not to let that limit us from studying disease as a process, which is the main focus of what we do."

— BT

Filed under

The Scan

Shape of Them All

According to BBC News, researchers have developed a protein structure database that includes much of the human proteome.

For Flu and More

The Wall Street Journal reports that several vaccine developers are working on mRNA-based vaccines for influenza.

To Boost Women

China's Ministry of Science and Technology aims to boost the number of female researchers through a new policy, reports the South China Morning Post.

Science Papers Describe Approach to Predict Chemotherapeutic Response, Role of Transcriptional Noise

In Science this week: neural network to predict chemotherapeutic response in cancer patients, and more.