How to Optimize Radiologist Reporting and Interpretation as Validated by Eye Tracking

Purpose: The purpose of this study is to validate a new reporting style with the intent to maximize radiologist’s interpretation time, increase accuracy and minimize dictation time as validated by eye tracking. The goal is to provide a clinically relevant, concise, and accurate reporting style.

Methods/Materials: The positive findings only dictation style using the Blue Yeti- Stand Alone microphone (n=76) was compared with the standard check-list dictation style using the Nuance Powerscribe- Handheld microphone (n=81). Two experienced board-certified diagnostic radiologists used each style for various imaging modalities including Coronary Calcium Score, Bone X-Ray, Chest X-Ray, Coronary CTA, Chest CTA, Cardiac MRI, PET CT, Abdominal Pelvis CT, and Chest CT. The number of voice recognition corrections per case was kept track by medical students. The Tobii Eye Tracker 3 Device was used to capture radiologist dictation time, interpretation time, and total examination time. This device was also utilized to generate thermal heat maps for each style. The statistical difference between the two methods was assessed by using descriptive analysis and inferential statistics.

Results: The percentage of cases that had at least one voice recognition correction was significantly decreased using the new positive findings dictation style versus the standard check-list style (5.26% vs. 14.81%; p=0.0240). The positive findings dictation style significantly decreased the average dictation time (16.54 seconds [s] vs. 29.39s; p=0.0003) without impacting interpretation time (70.90s vs. 64.30s; p=0.7799) or total examination time (87.45s vs. 93.69s; p=0.3756) compared to the standard style.

Conclusions: Positive findings only dictation style significantly decreased dictation time and enhanced accuracy, without compromising total interpretation time.