Sungkyunkwan University School of Medicine Researcher Discusses Research in Metastatic Cancer (Application of Transcriptome-Based Gene Set Featurization for Machine Learning Model to Predict the Origin of Metastatic Cancer).

A researcher from Sungkyunkwan University School of Medicine in Seoul, South Korea, has developed a machine learning framework called ONCOfind-AI that can predict the origin of metastatic cancers. Identifying the primary site of origin is crucial for guiding treatment decisions, especially for patients with cancer of unknown primary (CUP). The framework leverages transcriptome-based gene set features to enhance the accuracy of predictions and integrates data from different platforms to improve the accuracy of machine learning models. External validation results showed a top-1 accuracy ranging from 0.80 to 0.86 and a top-2 accuracy of 0.90. This research highlights the potential of incorporating biological knowledge to develop more effective machine learning prediction models for metastatic cancer. [Extracted from the article]