Published • loading... • Updated
AI tool predicts lung cancer risk years in advance
The tool analyzes one low-dose CT scan and was reported in 2023 to identify high-risk patients with 86% to 94% accuracy.
- Researchers at the Mass General Brigham Cancer Institute and MIT have developed an artificial intelligence tool called Sybil, which analyzes a single CT scan to predict lung cancer risk up to six years in advance.
- Standard screening guidelines limit CT scans to individuals aged 50 to 80 with specific smoking histories, yet only about 20% of eligible people actually undergo screening for the disease.
- Medical oncologist Dr. Lecia Sequist noted that "50% of people diagnosed with lung cancer in the US every year would not have met the criteria for screening," highlighting the diagnostic gap.
- Sybil uses pattern recognition trained on tens of thousands of scans to identify biological signals invisible to radiologists, achieving 86% to 94% accuracy in distinguishing high-risk patients within one year.
- While not yet approved for routine clinical use, Sybil is being tested in research projects at about one dozen US hospitals and in more than 30 countries, with researchers hoping the tool could help mitigate future cancer risks.
Insights by Ground AI
12 Articles
12 Articles
Coverage Details
Total News Sources12
Leaning Left0Leaning Right0Center12Last UpdatedBias Distribution100% Center
Bias Distribution
- 100% of the sources are Center
100% Center
C 100%
Factuality
To view factuality data please Upgrade to Premium
