A machine learning technique was noninferior to traditional immunohistochemistry in predicting molecular biomarker expression.
The pathological review of tumor samples, even for common molecular biomarkers such as estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2), is time consuming. Moreover, there is not always concordance between pathologists on the interpretation of samples. For example, it has been estimated that there is a discrepancy of up to 19% for ER estimation between central laboratories and local pathology laboratories.
Artificial intelligence (AI) and machine learning technologies are being applied to address this variation as well as to improve reliability and add efficiency. Currently, such technology can differentiate between cancerous and noncancerous tissue as well as determine presence of metas…
Reviewing Author
DisclosuresConsultant/Advisory BoardLilly; AstraZeneca; Gilead
Grant/Research SupportBreast Cancer Research Foundation
Editorial BoardsClinical Breast Cancer; Oncology; Annals of Surgery; Breast Cancer Research and Treatment
Leadership Positions in Professional SocietiesNational Comprehensive Cancer Network (Chair, Breast Cancer Panel); American Board of Internal Medicine (Medical Oncology Board)
DisclosuresConsultant/Advisory BoardLilly; AstraZeneca; Gilead
Grant/Research SupportBreast Cancer Research Foundation
Editorial BoardsClinical Breast Cancer; Oncology; Annals of Surgery; Breast Cancer Research and Treatment
Leadership Positions in Professional SocietiesNational Comprehensive Cancer Network (Chair, Breast Cancer Panel); American Board of Internal Medicine (Medical Oncology Board)