An A.I. from Harvard predicts who is most at risk of pancreatic cancer

Pancreatic Cancer is rising in young people.

Hey Everyone,

I have a strong interest in covering A.I. in healthcare and in finding the A.I. for Good stories of how A.I. will improve science, enable improved well-being for our descendents and so forth. Some stories keep me fixated, and keep popping up.

It wasn’t too long ago that I covered A.I. in Pancreatic Cancer.

🩺 A.I. Can Predict Pancreatic Cancer Up to 3 Years Before Diagnosis

I’m still amazed at the progress we’ve made in A.I. for early diagnosis across a spectrum of diseases and how this might impact the costs of healthcare as our developing country demographic pyramids begin to invert. The U.S. media age is now 38.9, and more years of obesity is also makes us more prone to certain diseases.

Researchers have used various AI-based techniques such as machine and deep learning models to detect the diseases such as skin, liver, heart, alzhemier, etc. that need to be diagnosed early. I keep coming back to Pancreatic Cancer, due to the deadliness of the disease.

Further Reading A.I. in Healthcare and Early Diagnosis

Hippocratic A.I. is First Safety Focused LLM for Healthcare

Artificial Intelligence will Augment Alzheimer and Dementia Detection & Early Risks Analysis

Google's A.I. in Identifying novel features for Colorectal Cancer

Pancreatic cancer is deadly; the five-year survival rate averages 12 percent.

I keep coming back to Pancreatic Cancer though due to the deadliness of the disease.

Pancreatic Cancer is Increasing in Young People

A new analysis (April, 2023) of data from the National Program of Cancer Registries database, covering around 65% of the US population, suggests that the incidence of pancreatic cancer among individuals younger than 55 years is increasing more rapidly than in those 55 years or older, and also more quickly in women than in men.

Numerous medical data sources are required to perfectly diagnose diseases using artificial intelligence techniques, such as ultrasound, magnetic resonance imaging, mammography, genomics, computed tomography scan, etc. How might early diagnosis evolve in the era of LLMs?

Somehow, researchers at Harvard Medical School and the University of Copenhagen have developed an AI that can identify which of a healthcare system’s patients are most at risk of pancreatic cancer based solely on medical records, flagging them for screening.

With the right data the A.I. is only going to get better.