Etai Jacob

New Capabilities

Lead researcher on PBMF development

For decades, cancer drug trials have failed at a rate exceeding 95%, burning through $50–60 billion annually on treatments tested in patients unlikely to respond. On April 17, 2025, researchers from AstraZeneca and Tempus AI published in Cancer Cell results from the Predictive Biomarker Modeling Framework, a machine learning system using contrastive learning on existing clinical data. The system can identify which cancer patients will survive longer on immunotherapy versus chemotherapy. Applied retrospectively to completed phase 3 trials, it improved survival outcomes by 15% compared to traditional patient selection.

Updated May 27