Computer aided translation of radiology reports for thyroid ultrasound to lay person


Encourage development & implementation of patient friendly radiology reports for thyroid ultrasound




Patient Facing

Define-AI ID



Patient Facing
Lead Andrea Borondy Kitts 

Panel Chair

Michael Moore
Non-Interpretative Panel Chairs Alexander J Towbin, Adam Prate

Panel Reviewers

Patient Facing


Creative Commons 4.0 
Status Public Comment

Clinical Implementation

Value Proposition

Radiologist reports are written in technical medical language intended for referring clinicians. However, with the advent of patient portals and empowered patients, patients are likely to be reading the radiologist report “unchaperoned” by their referring clinician or the reading radiologist. The language and terms used for example “can’t rule out malignancy” and the inclusion of comments about normal and expected findings (muscles/tendons:grossly intact; colon full of stool) can be confusing and cause anxiety for patients. Providing radiologist reports in easy to understand language, with key findings and what they mean, next steps and actions for the patient to take will help patients engage in their care. Patients will thus provide another layer of safety for follow-up care. These easy to understand summaries will also help referring clinicians as they sometimes find radiologist reports confusing and hard to understand.


A 55-year-old woman comes in for a thyroid ultrasound after her primary care physician feels a nodule during her annual health check. She requests a direct copy of the radiologist report and images as soon as available at the time when she checks in. She also indicates how she wants to receive her results; patient portal, e-mail, US mail, from her referring clinician) After the ultrasound is completed, the radiologist interprets the images and prepares the report including a patient friendly summary created by the AI.

Workflow Description

The algorithm identifies the type of imaging modality, the body part of interest, and the test objective. It then creates the patient-friendly option. The patient-friendly template is automatically populated with an illustration of the thyroid and as the radiologist notes the sizes and locations of the nodules, they are automatically added to the illustration of the thyroid. Future scaling of the approach for other body parts should be considered when developing the algorithm. Additionally, the text is translated into patient-friendly language and automatically populates the patient-friendly template. The patient-friendly summary includes a description of the findings such as the size and location of the nodules, an estimate of the probability of each of them being malignant, an illustration showing the relative size and location of the nodules, and a description of next steps for the patient. Examples of the next steps could include talking to your primary care physician about the need for an endocrinologist consult and/or thyroid nodule biopsy. The full radiology report, images, and the patient-friendly radiology report could be provided to the patient via the patient portal, or via HIPAA secure email or US mail per patient preference.

Considerations for Dataset Development

Identify most common terminology terms used for the thyroid (TI-RADS) and provide data dictionary of layperson language; assemble sets of radiology reports and translate using the layperson patient-friendly data dictionary. Check for accuracy and continue to refine. Develop standard template of sections that are common between the radiology report and the patient-friendly report. Translations will occur from radiology report template section to the corresponding patient-friendly report template section.

In this use case scenario, the imaging modality that would prompt this algorithm would be thyroid ultrasound, but this could be greatly expanded to other modalities and anatomic areas (such as right upper quadrant ultrasound for gallbladder disease).

Technical Specifications


Radiologist Report


Thyroid Ultrasound



Data Type

Structured Text



Body Region


Anatomic Focus


Primary Outputs

Patient Friendly Report

RadElement ID


Patient friendly summaries of thyroid ultrasound radiology reports to include summary of key findings such as the size and locations of nodules, an estimate of the probability of each of them being malignant, an illustration showing the relative size and location of nodules, and next steps including patient actions.

Data Type


Value Set




Future Development Ideas

  • Utilize AI to automate direct image findings onto the patient-friendly illustration.

Related Datasets

No known related public datasets at this time,  please alert us if you know of any.