Radiology patient portals are a feasible means to automatically structure and combine radiology reports with corresponding imaging studies, consequently giving patients access to high quality information about their disease or condition, according to a study published in the November issue of the Journal of the American Medical Informatics Association.

With the lack of quality online material about cancer, there’s a need for trusted information sources for patients. Measures haven’t been taken to make the full range of radiology content available to patients in an understandable manner, despite the prevalence of this information’s use in making diagnosis and treatment decisions.

“Even though radiology test results are one of the most difficult portions of the clinical record for lay people to understand, they are one of the most frequently accessed pieces of information via patient portals when available,” wrote the study’s author, Corey W. Arnold, MD, of the University of California-Los Angeles, and colleagues. “This suggests the need for new methods of sharing radiology information with patients.”

Arnold and colleagues decided to demonstrate the feasibility of a radiology patient portal by creating a Java-based web application and presenting it to patients with brain cancer.

The researchers created an electronic portal with an “interpretive layer” between clinically generated information and consumer-centric disease explanations. The portal interface was composed of four parts: a panel with the patient’s salient imaging findings; an information panel with patient-oriented explanations of imaging techniques, disease concepts and salient image findings; an interactive panel with key slices from imaging studies and associated extracted findings from radiology reports; and a study viewer displaying a full image series with an annotated conclusion section from the corresponding report.

2,883 brain MRI reports from 277 patients were processed, with 448 unique concepts extracted. Retrieved data were fed into image and natural language processing (NLP) modules, and resulting analyses were stored in a database on the portal server.

“Portal access allows the consumer to consolidate information that has historically been dispersed across sources, an important concern in medical imaging,” wrote Arnold and colleagues. “The presented system offers a novel solution to sharing radiology information with consumers, and is driven by imaging informatics tools to transform clinically-generated information into educational views that may be customized by patient and disease.”

A possible addition to the portal would be the integration of treatment information so patients could have a more comprehensive understanding of treatment effects. The researchers recommended that the application be used during office visits so practitioners are present to avoid any misunderstandings of results or an accidental improper disclosure of medical information.