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
AI Model Accurately Predicts Blood Loss Risk in Liposuction
A machine learning model predicts blood loss during high-volume liposuction with 94% accuracy.
•EurekAlert
AI-Driven CT Tool Predicts Cancer Spread in Oropharyngeal Tumors
Researchers have created an AI tool that uses CT imaging to predict the spread risk of oropharyngeal cancer, offering improved treatment stratification.
•EurekAlert
AI Model PRTS Predicts Spatial Transcriptomics From H&E Histology Images
Researchers developed PRTS, a deep learning model that infers single-cell spatial transcriptomics from standard H&E-stained tissue images.