WALTHAM, Mass. — BostonGene announced new clinical data highlighting its AI-driven approach to disease modeling in oncology during an oral presentation at the United States and Canadian Academy of Pathology (USCAP) 115th Annual Meeting.
The presentation, delivered in collaboration with leading academic investigators including Weill Cornell Medicine, focused on a multimodal AI framework designed to improve understanding of complex cancers and support treatment decision-making.
The USCAP meeting, held March 21–26 at the Henry B. González Convention Center in San Antonio, Texas, is a major global forum for pathology professionals, bringing together clinicians and researchers to share advances in molecular diagnostics and artificial intelligence in clinical practice.
The study, presented by Dr. Juan Miguel Mosquera, Professor of Pathology and Laboratory Medicine at Weill Cornell Medicine and Director of Research Pathology at the Englander Institute for Precision Medicine, evaluated an AI framework trained on approximately 20,000 tumor samples.
According to the findings, the platform integrates whole exome sequencing and transcriptomic data to address cancers of unknown primary (CUP), a category of malignancies where the original tumor site cannot be identified. In real-world cases, the model was able to determine tumor origin while identifying actionable therapeutic targets in more than 65 percent of patients, including treatments already approved by the U.S. Food and Drug Administration.
BostonGene said the results underscore a broader shift from traditional tumor classification methods toward AI-based disease modeling, enabling more precise patient stratification and improved treatment selection through deeper biological insights. (Source: IANS)
