Supercomputers combat bad drug events for Boston hospital

A new front is opening up in the ongoing effort to identify bad drug reactions, a major sore spot for drug companies and healthcare providers. Harvard doctors are using supercomputing technology to predict adverse reactions to drugs and hospital readmissions in patients with congestive heart failure, with an eye toward finding new ways to prevent such problems.

Cambridge, MA-based GNS Healthcare is providing the advanced analytics technology for the work, which is being done in collaboration with Dr. David Bates and Harvard-affiliated Brigham and Women's Hospital, where Bates directs the Center for Patient Safety Research and Practice. GNS's technology has found an audience in drug development and healthcare because it can extract causal relationships--such as how networks of genes drive diseases--from complex datasets.

In its latest collaboration, the company plans to analyze data from the electronic health records of patients treated in health system that includes Brigham and Women's, pharmacy data and claims information to find which factors or combination of factors contribute to adverse drug reactions and hospitalizations. Since GNS's system crunches huge amounts of complex data in an unbiased or "hypothesis-free" fashion, doctors are hoping to glean some new insights about what plays a role patients getting sick from drugs they take.

"GNS Healthcare has developed supercomputer-driven, hypothesis-free technologies to extract actionable insights from large, complex healthcare datasets," Bates said in a statement. "The hypothesis-free approach represents an exciting way to identify non-obvious combinations of conditions, drugs and other factors that lead to adverse events, and reveal what activities can mitigate them."

In the name of pharmacovigilance, governments and researchers have been employing new IT-enabled methods such as reporting systems and data-mining experiments to provide early identification of or rapid responses to adverse drug events. What makes the GNS-Brigham effort stand out, however, is the use of the firm's reverse engineering/forward simulation (REFS) technology to home in on the causes of such problems directly from electronic patient data, potentially leading to new ways stop the unfortunate episodes from happening.

- here's the release
- check out Xconomy's coverage

Suggested Articles

There's no evidence personal patient information leaked during the 11-week breach, but the same can't be said about Sangamo's own secrets.

Through a new online tracker, AllTrials names sponsors who fail to report clinical trial results on time per the FDAAA Final Rule.

The new solution aims to streamline the incorporation of human genomic data into clinical trial designs.