Christopher G. Chute Credit: Johns Hopkins Medicine

“We’re in a profoundly information-intensive age,” says Christopher G. Chute, M.D., Dr.P.H., Bloomberg Distinguished Professor of Health Informatics, and a professor of medicine, public health and nursing at Johns Hopkins. “Clinical organizations will be able to use their data more effectively if they adopt and embrace standard ways of naming and labeling clinical information.”

Johns Hopkins Medicine alone has multiple petabytes of stored health information, says Chute, who also is chief research information officer for Johns Hopkins Medicine and deputy director of Johns Hopkins’ Institute for Clinical and Translational Research. A petabyte is the equivalent of 1.5 million compact discs, or about 100 billion times more than the complete works of Shakespeare.

Although electronic health records document many types of data, Chute says, it may not be easy to extract information needed to put patients into subgroups to deliver more tailored care, a goal of personalized medicine. Some information may become “trapped” in documents in a PDF format and therefore more difficult to transfer into other formats for analysis. Furthermore, some electronic record systems don’t have good interoperability with others.

The increasing use of wearable health devices and biomonitoring, as well as advances in medical digital imaging, will lead to even more growth in the volume of clinical data, Chute says. Ontologies can help organize and analyze vast quantities of data that are too large for individual physicians to manage.

“Think of ontologies like a hierarchy,” Chute says. If an ontology classifies a virus as an infectious agent, and infectious meningitis as a type of meningitis due to an infectious agent, it would conclude that viral meningitis is a subclass of infectious meningitis. “Physicians are overwhelmed with clerical data entry, and we need informatics tools and resources in the electronic health record to harvest that information to unburden physicians from entering it in a structured way,” he says. Some programs are becoming available to help cull information and summarize it automatically. For example, a conversation between a patient and physician could be recorded and put through a speech-to-text program to pull out relevant information about patient symptoms.

Johns Hopkins has historically been focused on precision medicine, and the Johns Hopkins inHealth program has launched several precision medicine centers of excellence, including centers for multiple sclerosis, prostate cancer, heart failure, genetics and arrhythmias. One part of inHealth, the Precision Medicine Analytics Platform, is a joint venture of Johns Hopkins Medicine and the Johns Hopkins Applied Physics Laboratory, which aims to apply rigorous data analysis and systems engineering practices to revolutionize the diagnosis and treatment of disease.

Chute is one of three authors of the NEJM review, with Melissa A. Haendel, Ph.D., of the Oregon Clinical and Translational Research Institute at Oregon Health & Science University, and the Linus Pauling Institute and the Center for Genome Research and Biocomputing at Oregon State University; and Peter N. Robinson, M.D., of the Jackson Laboratory for Genomic Medicine and the Institute for Systems Genomics at the University of Connecticut.