AI in Healthcare Virtual Summit Session Recordings-Artificial Intelligence and Statistical Genetics for Diagnosing Thyroid Cancer

Video Transcription

Video Summary

In his presentation, Dr. Nikita Pazdeev from the Lodz Academic Center, an endocrinologist specializing in thyroid cancer, detailed the complexities of diagnosing and managing thyroid nodules. He highlighted the importance of distinguishing benign from malignant nodules using clinical ultrasound-based risk stratification schema like THARADS, which uses features such as composition and margin to assess the need for biopsies. Despite the method's decent sensitivity, it faces specificity issues due to human interpretation inconsistencies.<br /><br />Dr. Pazdeev discussed leveraging artificial intelligence (AI) to improve diagnosis accuracy, showing that AI's deterministic nature could eliminate subjective human errors. However, challenges persist, particularly with certain thyroid cancer variants difficult to diagnose even with tissue samples.<br /><br />He also addressed improving diagnosis by integrating genetic risk assessments through analyzing both common and rare genetic variants that influence thyroid cancer risk. His findings revealed prevalent thyroid cancer-associated syndromes, suggesting high-risk individuals could be more efficiently identified and managed.<br /><br />Furthermore, Dr. Pazdeev proposed using genomic data to predict the development of different thyroid nodule types, advocating for its potential to enable a more personalized and effective approach to managing thyroid conditions.<br /><br />Overall, he underscored the necessity and potential of combining advanced technology and genetic insights to enhance thyroid cancer diagnostics, also raising considerations for economic and practical implementation challenges. This comprehensive approach could eventually refine and personalize therapeutic strategies, optimizing patient care in endocrinology.

Asset Subtitle

Nikita Pozdeyev, MD, PhD
Assistant Professor, Biomedical Informatics
University of Colorado, Anchutz School of Medicine

Keywords

thyroid cancer

endocrinology

thyroid nodules

THARADS

artificial intelligence

genetic risk assessment

genomic data

personalized medicine

diagnostic accuracy

patient care


EndoCareers \| Contact Us \| Privacy Policy \| Terms of Use	CONNECT WITH US
© 2021 Copyright Endocrine Society. All rights reserved.	2055 L Street NW, Suite 600 \| Washington, DC 20036 202.971.3636 \| 888.363.6274