Utilizing Machine Learning to Identify Multimodal Signatures for Patients Who Would Benefit from the Addition of Tremelimumab to Durvalumab and Chemotherapy (TRIDENT).
Clin Cancer ResOct 1, 2026
Ferdinandos Skoulidis, Salma K Jabbour, Edward B Garon et al.
✦ AI-curated · Sources linked
In 30 seconds
The TRIDENT analysis, a post hoc study of the POSEIDON trial, utilized machine learning to identify patients with metastatic non-small cell lung cancer (NSCLC) who may benefit from adding tremelimumab to durvalumab and chemotherapy. The model indicated that the top 50% of patients with nonsquamous tumors had a hazard ratio of 0.56 for overall survival benefit.
Key findings
- The model predicted treatment benefit with a hazard ratio of 0.56 for the top 50% of patients with nonsquamous tumors.
- Factors associated with higher overall survival benefit included EGFR wild type and KRAS mutations.
- The analysis leveraged clinical, genomic, and radiomic data from the POSEIDON trial.
Why it matters
Identifying specific patient subpopulations that may benefit from additional therapies can enhance treatment precision in metastatic NSCLC, potentially improving patient outcomes and optimizing resource use in oncology.