AI Predicts Pancreatic Cancer Three Years in Advance
In Brief
A study published in the journal Cell Metabolism found that accurate third-party prediction of pancreatic cancer can be made 3 years before it occurs.
Researchers have developed a breakthrough AI model that can accurately predict people’s risk of developing pancreatic cancer. An AI developed by researchers from the University of Tokyo was able to accurately flag patients at risk of developing pancreatic cancer within the next three years. Doctors using current methods to diagnose pancreatic cancer are hesitant to recommend screenings despite it being a very deadly and hard-to-spot cancer.
Researchers found that AI models can help doctors screen for pancreatic cancer. Since it has always been hard to understand the risk of this particular disease, an AI tool that can zero in on those at the highest risk for pancreatic cancer could improve clinical decision-making. The American Society of Clinical Oncology estimates 56 percent of people diagnosed with pancreatic cancer die from the disease within five years of receiving the diagnosis.
Pancreatic cancer is hard to find and treat early, so early screening is crucial. Many types of cancer, including those hard to treat early, impact patients, families, and the healthcare system. In this study, In this study, 500 CT scans of people who have had lung nodules, that is, abnormal growths of cancerous tissue, were shown to help to alter the trajectory of the disease. In fact, the appearance of lung nodules may point to the spread of pancreatic cancer to the lungs. Using medical records, researchers were able to accurately identify people more likely to be diagnosed with pancreatic cancer.
The AI model was used to predict the likelihood of people suffering from pancreatic cancer in Denmark and the United States. The model used 6 million people from Denmark and 3 million Americans as data points. The model’s accuracy was gauged by generating an area under the curve, or AUC, score. Model scores are used to determine how accurate a test is. A score of 0 is worthless, 0.5 is as accurate as flipping a coin, and 1.0 indicates a perfect test.
The Harvard Model earned a score of 0.88 for estimating cancer risk in the next three years and 0.9 for detecting risk in the next 12 months. It was also tested to see if it would predict further intervention for people with lung nodules that would be considered a medium risk of developing cancer. Eighteen out of the 22 people with lung nodules who were later diagnosed with pancreatic cancer had been assessed as at high risk of developing the disease.
Doctors are hesitant to recommend MRI, CT, or endoscopic ultrasounds because they are expensive, uncomfortable, resource intensive, and inaccurate at finding cancer. While these tools are not accurate in all cases, it seems AI can help make doctors make the most use out of them.
- Healthcare professionals are wary of using AI and ChatGPT for medical advice as a recent study has revealed that AI generates false information when questioned about cancer. It is important to seek accurate and trustworthy sources for medical advice.
Read more related articles:
- GPT-3: Can it really predict the future for USA for next 5 years?
- Microsoft and Google in 2023: The year’s primary showdown between AI titans
- The Sandbox launches three new virtual neighborhoods
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Damir is the team leader, product manager, and editor at Metaverse Post, covering topics such as AI/ML, AGI, LLMs, Metaverse, and Web3-related fields. His articles attract a massive audience of over a million users every month. He appears to be an expert with 10 years of experience in SEO and digital marketing. Damir has been mentioned in Mashable, Wired, Cointelegraph, The New Yorker, Inside.com, Entrepreneur, BeInCrypto, and other publications. He travels between the UAE, Turkey, Russia, and the CIS as a digital nomad. Damir earned a bachelor's degree in physics, which he believes has given him the critical thinking skills needed to be successful in the ever-changing landscape of the internet.
More articles
Damir is the team leader, product manager, and editor at Metaverse Post, covering topics such as AI/ML, AGI, LLMs, Metaverse, and Web3-related fields. His articles attract a massive audience of over a million users every month. He appears to be an expert with 10 years of experience in SEO and digital marketing. Damir has been mentioned in Mashable, Wired, Cointelegraph, The New Yorker, Inside.com, Entrepreneur, BeInCrypto, and other publications. He travels between the UAE, Turkey, Russia, and the CIS as a digital nomad. Damir earned a bachelor's degree in physics, which he believes has given him the critical thinking skills needed to be successful in the ever-changing landscape of the internet.
