Artificial intelligence (AI) can be used to identify thyroid nodules seen on thyroid ultrasound that are very unlikely to be cancerous, reducing a large number of unnecessary biopsies.
In this new study, researchers used machine learning, a type of AI, to analyze ultrasound images of thyroid nodules. Machine learning is the process of using mathematical models of data to help a computer learn without direct instruction.
More than 30,000 images from 621 thyroid nodules were used to train the machine-learning model that classifies thyroid nodules as “cancer” or “no cancer.” The model was tested on a different set of 145 nodules collected at another healthcare system.
The AI-based model achieved a sensitivity of 97%, and a specificity of 61%. The authors believed that this is a good next step to improving patient care and avoiding unnecessary procedures.
This study was presented at ENDO 2022, the Endocrine Society’s annual meeting in Atlanta, Ga.