Memorial Sloan Kettering researchers report advancements in AI governance, biomarker analysis, and language models for improved cancer care.
Key Details
- 1MSK implemented governance covering 26 AI models, two ambient pilots, and 33 nomograms, demonstrating scalable AI oversight.
- 2AI tool EAGLE analyzed over 8,000 lung cancer slides, reducing molecular testing by over 40% while maintaining standards.
- 3A cancer-trained LLM ('Woollie') was built from 40,000+ radiology reports; achieved predictive scores of 97 (MSK) and 88 (UCSF) overall.
- 4Study on 118 nonagenarians showed lung cancer surgery can be safe and effective, with no patients dying within 90 days.
- 5Drug combination shown to induce mutation (MMRd) in colorectal tumors, potentially sensitizing resistant cancers to immunotherapy, but no clinical responses observed yet.
Why It Matters
Robust governance and real-world validation are crucial for integrating AI into oncology workflows. New computational tools, especially those leveraging radiology and pathology data, show promise for improving clinical decision-making and operational efficiency in precision cancer care.
Source
EurekAlert
Related News
•EurekAlert
Deep Learning AI Outperforms Clinic Prognostics for Colorectal Cancer Recurrence
A new deep learning model using histopathology images identifies recurrence risk in stage II colorectal cancer more effectively than standard clinical predictors.
•EurekAlert
AI Reveals Key Health System Levers for Cancer Outcomes Globally
AI-based analysis identifies the most impactful policy and resource factors for improving cancer survival across 185 countries.
•EurekAlert
Dual-Branch Graph Attention Network Predicts ECT Success in Teen Depression
Researchers developed a dual-branch graph attention network that uses structural and functional MRI data to accurately predict individual responses to electroconvulsive therapy in adolescents with major depressive disorder.