Decision Tools Aid in Categorizing Lung Nodules

Computerized decision support tools allow radiologists to be more efficient and accurate in categorizing lung nodules, according to a study published in the Journal of the American College of Radiology.

Researchers from University of Colorado in Denver, and University of Washington and VA Puget Sound in Seattle performed a study to assess the efficacy and accuracy of the Lung-RADS algorithm, implemented as a computer program, versus a table in categorizing lung nodules.

Two surveys were created, asking respondents to categorize 13 simulated lung nodules using the computer program and the Lung-RADS table as published. The researchers gathered data regarding how long it took for the survey to be completed, the accuracy of each nodule’s categorization, users’ subjective categorization confidence, and users’ perceived efficiency using each method.[[{"type":"media","view_mode":"media_crop","fid":"43389","attributes":{"alt":"decision tools","class":"media-image media-image-right","id":"media_crop_4232958097602","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"4727","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 111px; width: 161px; border-width: 0px; border-style: solid; margin: 1px; float: right;","title":"©Bloomua/Shutterstock.com","typeof":"foaf:Image"}}]]

The results showed that those who used the computer program had a significantly increased interpretation speed (median 80.8 seconds) compared with those who didn’t use the program (median 156 seconds). Classification accuracy was also improved with the program, 99.6% versus 76.5%.

The researchers concluded that computerized decision support tools helped radiologists be more efficient and accurate when categorizing lung nodules.