GTC reports validation of targeted transcriptome algorithms for diagnostic purposes

Molecular testing company Genomic Testing Cooperative (GTC) announced on Thursday that two of its artificial intelligence (AI) algorithms have been validated for use in the diagnosis and interpretation of molecular results through genomic profiling.

The validation results were published on Wednesday in the American Journal of Pathology.

GTC’s RNA analysis algorithm is used to distinguish 45 different diagnostic classes, providing probability scores. The algorithm is completed by a second called TraceWork. When needed, TraceWork is used to distinguish between two diagnostic entities determined by RNA analysis to have a similar high probability score, GTC said.

According to the study, RNA analysis demonstrated correct first-choice diagnosis in 100% of acute lymphoblastic leukemia cases, 88% of acute myeloid leukemia cases, 85% of diffuse large B-cell lymphoma cases , 82% of colorectal cancer cases, 49% of lung cancer cases, 88% of chronic lymphocytic leukemia cases and 72% of follicular lymphoma cases.

TraceWork distinguished between lung cancer and colorectal cancer with 97.2% sensitivity and 94.5% specificity; between Hodgkin’s lymphoma and the normal lymph node with a sensitivity of 95.4% and a specificity of 100%; between follicular lymphoma and diffuse large B-cell lymphoma with a sensitivity of 95.9% and a specificity of 93.1%; and between breast cancer and ovarian cancer with a sensitivity of 100% and a specificity of 94.2%.

“We believe that transcriptomic data, when combined with AI, provides effective and efficient information that can replace the need for a large number of immunohistochemical staining and flow cytometry tests, especially when samples of tissue are rare,” Dr. Maher Albitar, founder, chief medical officer, and CEO of GTC, said in a statement.

Sharon D. Cole