Using video to elaborate test results to sufferers

Researchers at the institute of University of Illinois are in the initial stages of establishing a computer-generated physician or nurse that can elaborate test results to sufferers and next steps in treatment through patient portals available through an electronic health records (EHRs) system.

For now, the work is in the proof-of-concept stage, with researchers explaining the project in the March issue of the Journal of Biomedical Informatics. The work of showing test results to sufferers is being done at the institute of University of Illinois’ Beckman Institute for Advanced Science and Technology, and the Carle Foundation Hospital’s Research Institute.

While several sufferers today have access to their electronic health records (EHRs) when they log into their portal, they analyze a bunch of test results, often represented as numbers that can be complicated to understand, claims Dan Morrow, lead author and educational psychologist at the University of Illinois. “You see a table of numbers and scores but you do not get context on ranges and risks, and you don not know if a low score is normal or a high one is normal,” he explains. For now, the numbers are generally a basis for having a conversation with your doctor.

And for now, a computer-generated doctor has to wait as researchers take baby steps and develop up to that kind of technology. For starters, they are working on attempting to enhance the presentation of tests results whether get in the mail or through a portal, by color-coding scores. A low score for cholesterol, for example, would be green, a medium score would be yellow, and a high score would be red.

But work is underway to develop a more realistic patient-physician dialogue. A retired physician recorded scripts for the sufferer portal messages and other text required to develop the avatar clinician’s commentary. Multiple scripts have been established to emulate how various kinds of test results would be explained to sufferers.

Researchers also testing whether patients’ “gist memory,” which is fuzzy representations of an event, differs relying on whether the avatar speaks in a natural voice or a computer-generated voice.

As a 1st step, researchers brought older adults into the lab and had them go through various mock patient scenarios that affect the heart disease. Few of the adults, acting as patients and presented with mock test outcomes, would see a list of numbers or the similar numbers but color coded. Another group would see a video of a provider presenting results and told how they should think about the numbers, then assess how well the older adults understand and retain those outcomes.

The reality is that most individuals like information in a video but most physicians will not use video to explain results so the idea was to develop an avatar physician or nurse that appears in the video, in accordance to Morrow. “We need to emulate best practices in a real-life face-to-face atmosphere.”

The avatar clinician is programmed to display suitable facial expressions, gestures and other cues that promote patient understanding as if findings were being presented by a human.

Having got a grant to begin the project, the attempt recently got another grant to generate other clinician avatars, and now is seeking grants for pilot studies with patient portals next year.

If everything goes well, Morrow considers a first-generation product could be a reality in 2 or 3 years.