cleveland night

Healthcare Reform

$21.5 Million Big Data Project Aims to Improve Medical Care

, , ,

cleveland night

Three Major Cleveland Healthcare Institutions are Teaming Up to Share Data

Every patient and every visit to the doctor’s office adds, in some small way, to a doctor’s medical knowledge. Whether it’s an unexpected reaction to a medication or a disease presenting in an unusual way, every person’s health history can hold a wealth of important information. Now, three major medical institutions in Cleveland are teaming up to combine their individual troves of clinical data into one big data gold mine.

“By being able to aggregate tremendously large amounts of data from hundreds of thousands — if not millions — of patient visits to the different hospitals, we may be able to look at things that people haven’t been able to look at before,” says Jonathan Haines, chair of the Department of Epidemiology and Biostatistics at Case Western Reserve University School of Medicine, and the leader of the consortium.

Called the Institute of Computational Biology, the consortium is a $21.5 million joint venture between Case Western Reserve University, the Cleveland Clinic, and University Hospitals. The goal of this institute is to develop an enormous set of clinical data, accessible to doctors and researchers from all three places.

So far, the institute is still in the planning stages, and a large part of that involves forming the necessary computational infrastructure. The institute plans to bring together all kinds of medical information – like clinical notes, lab tests, billing records, and genomic data – and, seeing as each of these places has their own unique system for data storage, this is an ambitious goal.

The process will involve aggregating data, de-identifying it and then organizing it in a secure, user-friendly fashion.

“By having this all organized and integrated, doctors will have better access to data about patients that will impact their care,” says Haines’ Case Western colleague, Anthony Wynshaw-Boris, Chair of the Department of Genetics and Genome Sciences at the School of Medicine and University Hospitals Case Medical Center. Although he is not personally involved in this consortium, Wynshaw-Boris says it is the kind of collaboration he’s heard doctors and researchers talking about for years. Now is the first time he’s seeing a significant attempt at bringing the idea to fruition.

Three major medical institutions in Cleveland are teaming up to combine their individual troves of clinical data into one big data gold mine.

The innovative and complex nature of this project is one reason Haines was recruited from Vanderbilt University to lead the way. At Vanderbilt, he helped created a biological repository for their medical records database, and founded the Center for Human Genetics Research. Well aware of the challenge ahead of him, Haines says not to expect results from the Institute in mere months. However, once the initial infrastructure is ironed out, the sharing should become fairly simple.

By combining this data, researchers hope to enhance the work at each of the participating institutions. Although, bringing these records together is complicated, the logic for doing it is simple: Making larger sets of numbers available has the potential to bring out trends and associations that would have gone unnoticed in the institutions’ individual datasets. The result is then more detailed knowledge, which doctors can use to better understand the intricacies of their patients’ health. “The Holy Grail would be to have very much personalized medicine,” says Paul DiCorleto, Chair of the Cleveland Clinic Lerner Institute.

“An individual will be treated because of everything known about that individual, instead of everybody who has a particular disease being treated the same way.”

Although the Institute of Computational Biology is largely a computer-based collaboration, Haines says symposia, meetings, and seminars will likely accompany it. The consortium is just the beginning. In the future, the Institute of Computational Biology is designed to go much further.

“Ultimately all the systems around the country are going to have to talk to each other, I mean that’s part of the whole change in health care,” says Haines. “Right now, nobody really knows how to do that. So, we start with Cleveland and then we’ll work out from there.”