The RGT Digital Twin system revolutionizes personalized treatment for Uterine Carcinosarcoma (UCS) by integrating molecular profiling and large language model (LLM) capabilities. The study examined a 77-year-old patient with recurrent UCS, utilizing genomic panels (TSO 500 and TST 170) to reveal therapeutic targets such as high PD-L1 expression and intermediate tumor mutational burden (TMB). Treatment options were refined through a Molecular Tumor Board (MTB) discussion, leveraging institutional and literature-derived data for comprehensive insights. Data was extracted from electronic health records (EHR) and web repositories while ensuring ethical compliance. The LLM-assisted process identified 9 analogous cases that met inclusion criteria for immune checkpoint inhibitors, enhancing treatment strategy modeling. This dynamic system continuously updates with outcomes to refine future predictions, driving personalized care decisions. Overall, the RGT Digital Twin proves vital for informed treatment selection, cost-coverage justification, and clinical trial matching, significantly contributing to UCS management.
Source link
