Lily Peng, MD, PhD, a product manager on the Google Brain artificial intelligence research team, presented “promising, but early” findings of a study in collaboration with the National Cancer Institute and Northwestern University during the keynote. The study’s results will soon be published in Nature Medicine.
Using CT scans of lung cancer patients, the model’s AI was trained to identify malignancies “with a performance that meets or exceeds that of trained radiologists,” Dr. Peng said.
In one particular case, the model was able to detect a miniscule malignancy in a CT scan taken one year before a patient was diagnosed with late-stage cancer. When six radiologists were shown the same scan, only one identified the early-stage malignancy.
According to Dr. Peng, the technology could increase early detection for the 80 percent of lung cancers that are not caught until their later stages, increasing survival rates by an estimated 40 percent.
More articles about AI:
FDA clears AI-powered, cloud-based heart murmur detection system
Mammogram-reading AI can detect breast cancer risk 5 years before onset
AI detects anxiety, depression in children’s speech patterns
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.