Alexander T. Pearson, MD, PhD, Assistant Professor of Medicine at the University of Chicago, commended the artificial intelligence (AI)-augmented, ultrasound-based platform for screening and staging of thyroid cancer. 

“In this study, Dr. Chan and colleagues processed high-resolution ultrasound data collected over a 12-year span from a series of 784 patients, each of whom underwent a fine-needle biopsy,” said Dr. Pearson in an interview with The ASCO Post. “The authors processed the ultrasound data with a series of different quantitative data-extraction modalities and then combined those modalities using flexible AI techniques to predict a series of clinically relevant endpoints.”

Alexander T. Pearson, MD, PhD

According to Dr. Pearson, the advantage of such an automated, algorithm-based diagnostic approach is that an ultrasound user could capture images and then provide a rapid thyroid nodule diagnosis without special radiographic training—potentially sparing many patients unnecessary biopsies and diagnostic tests.

“The authors shared a series of interesting results, including predicting malignancy, clinical stage, and BRAF mutation status,” he continued. “If this algorithm performs at least as well as human interpretation of the same endpoints and can be replicated in prospective, multisite studies, it would provide an exciting step forward in the use of AI for thyroid cancer diagnosis and risk stratification.” 

DISCLOSURE: Dr. Pearson has served on advisory boards for Elevar, Ayala, and Prelude Therapeutics; and has received research funding from Kura Oncology and AbbVie.