New Research from Memorial Sloan Kettering Cancer Center Investigates Immunotherapy, Surgery Outcomes in Older Patients, AI in Oncology, and Cancer Trained Large Language Models

Strategic Insights -

New research from Memorial Sloan Kettering Cancer Center (MSK) is investigating whether introducing new mutations could make immunotherapy more effective against some cancers, showing that people in their 90s who underwent lung cancer surgery had positive outcomes, and sharing lessons on the responsible governance of artificial intelligence in oncology. Previous clinical research has shown that tumors with specific gene mutations or changes are more sensitive to immunotherapy, a treatment that helps the immune system recognize and attack cancer cells. MSK investigators are developing a new approach to induce these mutations in resistant cancer cells, a strategy that could lead to new treatment options.

Key Takeaways:

  • A clinical trial at MSK showed that people with mismatch repair-deficient rectal cancer saw their tumors disappear after treatment with PD-1 blockade immunotherapy.
  • Research led by MSK's Benoit Rousseau, MD, PhD, and Luis Diaz, MD, showed that combining temozolomide and cisplatin can induce mismatch repair deficiency in colon cancer cells in mice, making them sensitive to PD-1 blockade.
  • A retrospective study looked at outcomes among 118 MSK patients in their 90s who were diagnosed with non-small cell lung cancer during 2001-2021, 17 of whom underwent surgery, and found that the patients who elected to have surgery had a median survival of 43 months.
  • A team from MSK published a study reporting on the first year of the comprehensive cancer center's responsible AI governance model for clinical programs, operations, and research, which covered the registration and monitoring of 26 AI models, two ambient AI pilots, and a review of 33 nomograms.
  • A study from MSK, the Icahn School of Medicine at Mount Sinai, and their collaborators demonstrated the effectiveness of a computational tool, dubbed EAGLE for assessing EGFR mutations in lung cancer, which cut the number of molecular tests needed by more than 40% while maintaining current clinical standards for performance.
  • A team of researchers from MSK and the University of California, San Francisco (UCSF), has created Woollie - an open-source, cancer-specific large language model (LLM) trained on real-world data that can help doctors understand and predict cancer progression.
  • Woollie was validated on data from UCSF and achieved high accuracy in predicting cancer progression, with scores ranging from 88 to 98 depending on the type of cancer.

Statistics:

  • 118 MSK patients in their 90s who were diagnosed with non-small cell lung cancer during 2001-2021 were studied, with 17 of them undergoing surgery.
  • The patients who elected to have surgery had a median survival of 43 months.
  • The study covered the registration and monitoring of 26 AI models, two ambient AI pilots, and a review of 33 nomograms.
  • The computational tool EAGLE reduced the number of molecular tests needed by more than 40% while maintaining current clinical standards for performance.
  • Woollie achieved high accuracy in predicting cancer progression, with scores ranging from 88 to 98 depending on the type of cancer.

Sources:

  • NewsRx (2025)
  • Cancer Weekly (2025)
  • Cancer Cell (2022)
  • Lung Cancer (2022)
  • npj Digital Medicine (2022)
  • Nature Medicine (2022)