Enabling the Future of Medical Reports
Background
Despite great progress in the field of medical technology over the past five decades, some things remain relatively unchanged. One being the process of writing and collaborating on medical reports and diagnoses for imaging exams.
Reports are commonly written or dictated in plain text and then saved in proprietary systems or and even Word files. To prevent repetition, files detailing common diagnoses are often used as templates.
A radiologist's learning curve is long and writing reports is a process that takes years to become natural. Given the different writing styles across individuals or instituions, extracting and comparing reliable data or statistics from a large volume of reports is practically impossible.
Learning curve • Scale • Productivity • Errors and imprecisions • Research • Data
Product
Smart Reporting was born from academic research in the field of structured reports. In this model, a decision tree for each type of exam, body part and diagnosis is used to write the report.
The reception at events, fairs and demos for professionals and domain experts proved to be extremely positive and the company received its first rounds of investment.
This initial idea turned into an outstanding product with incredibly powerful features, but it also had limitations that had to be overcome.
Some constraints were technical, such as making the the content more scalable and fixing usability issues, but others were cultural or conceptual: some advantages of the product did not seem to outweigh such a paradigm shift among more experienced radiologists.
This was the context in which I joined the company.
Interviews • Demos • User journeys • Stakeholder mapping • Empathy map
Product Discovery
We learned that in order to suceed, accomodating for a broad spectrum of professionals, the starting point should always be the blank sheet. Content should be the star while support for speech recognition and writing structure facilitate in a way that is as adaptable, intelligent and integrated as possible.
The sidebar was redesigned to be an interface element entirely based on progressive disclosure: selected or inserted content can lead to new questions and to more details that weren't initally visible. It works either as an interactive content input element, as a text navigation menu or as a summary of that report.
As the majority of radiologists have one hand busy while operating a SpeechMike-like microphone, the entire system should not rely on the classic mouse/keyboard pairing, and instead be usable by any combination of these devices.
The editor also provides contextual guidance as the doctor types or dictates text, behavior similar to a modern code editor.
Different parts of structured text also have different superpowers: in some cases, a measure or value is expected, in others, one or multiple values can be selected. Additionally, there are interactive images to help find certain diagnoses.
Full or partial reports can be inserted or extracted in real time through multiple types of integrations (FHIR, HL7). This allows the Report Editor to be seamlessly embedded into RIS/PACS user interfaces and transfer data - such as measures, patient information and diagnostic suggestions by AI.
User Testing
User testing sessions were conducted at Smart Reporting's usability lab by a third-party company.
Participants were gathered from different hospitals and clinics in Bavaria and varied in their resposibilities and levels of experience.
In addition to the final reports with recommendations, the sessions were recorded from three perspectives - particpants, screen and eye tracking - which provided us with important insights for the next iterations.
Outcomes
SmartReports has been successfully integrated into GE and Siemens Healthineers systems.
Other vendors are in the process of integration. The report editor is also being integrated with other Smart Reporting product lines.
