Oncospace Abstract: eScience Technology and Opportunities for Oncology
Radiation Oncology is based on past experiences and clinical trials for the understanding and advancement of
patient care. In the current practice we study the effects of radiation on our patients through controlled trials.
These trials represent less than 5% of our patient population, take years for results, and are controlled with more
rigor than the standard clinical practice. Our clinical workflow can be viewed as an assembly line process that we
optimize to insure the optimal care for our patients. For this to occur, a system that enables the collection of
relevant information and the assessment of the quality of our processes is required.
The clinical workflow in radiation oncology has multiple stages from simulation to treatment planning, to daily
record of treatments and follow-up visits. Throughout this process there are multiple opportunities to capture
meaningful information that is relevant to the complications and successes of the treatment. Current practices lack
the organized collection of much of this data, and few tools exist to evaluate and analyze the data in order to
re-apply the new knowledge at the point of care.
Today we have many studies looking at anatomical, functional and molecular image data to better characterize our
patient’s disease. We use pathology, and in the future, genetic information to better understand the nature of a
specific patient’s disease. We look at radiation dose distributions, fractionation patterns and patient motion to
understand how it impacts treatment outcome. We complicate the practice further with concurrent chemo- and hormonal
therapies in addition to surgery. A vast amount of untapped knowledge is contained within the clinical data and
eScience provides an opportunity to access it.
eScience refers to the practice of studying immense amounts of data through the use of computer networks and well
organized data bases. Such systems enable distributed collaboration among colleagues in the specified discipline.
In radiation oncology, we are very good at the immense amount of data part, but we are lacking in the management of
that data to practice eScience. Oncospace is an initiative to apply eScience concepts to radiation oncology for both
a physician’s tool for personalized medicine and a collaborative tool for multi-institutional research on clinical
data.
Oncospace is composed of several components: Data Collection and Workflow where the clinical workflow is altered to
inherently collect information on our patients relevant for future analysis; Data Warehouse design to create the
active database model for efficient analysis, and Web Services to support web-based access with security levels
in place to protect patient privacy; Human Interface design to make it easy to ask clinically relevant questions of
the data and present the answers in ways the physician think about the problems. And lastly, Statistical Analysis
tools to allow us to better understand the relative importance and validity of the clinical data that is a less
controlled than a typical clinical trial; and Decision Support tools to allow us to apply knowledge from the system
to our clinical practice.
Imagine if physicians could query out the rectal dose distributions for all of their patients experiencing
complication and compare them to patients with the same disease classification but without the complication.
Retrospective clinical studies on a clinic’s data could be done in minutes with database queries rather than
months of manual data collection.