The role of artificial intelligence in personalized medicine

Scientists at Carnegie Mellon University and the University of Pittsburgh are using artificial intelligence in their quest to provide individualized treatments, according to a Computerworld article.

As part of the Pittsburgh Health Data Alliance, the University of Pittsburgh Medical Center has agreed to fund the project for six years at between $10 million and $20 million per year.

It's taking data from electronic health records, diagnostic imaging, prescriptions, genomic profiles, insurance records and even wearable devices to create healthcare plans not only by disease, but also for specific types of people.

Rather than have all of that data stored in various systems, it's like having a brain sort through it, Eric Xing, a professor in the machine learning department at Carnegie Mellon, told Computerworld.

"Uniqueness in lifestyle, environment and other health factors makes someone a unique individual," he said. "AI might take information from not just one doctor but many doctors' experiences and it can pull out information from different patients that share similarities."

The researchers hope to develop apps, machine learning tools and services each year of the project. A smartphone app to help people live healthier lives and ward off some illnesses is due out in about a year, according to Xing.

President Barack Obama's Precision Medicine initiative aims to develop treatments targeted to an individual's genetic makeup. That effort will require software that's transparent, and the data must be "exquisite," according to Francis Collins, director of the National Institutes of Health.

But while computers can quickly sort through reams of published materials, they're "notoriously bad" at understanding the nuances of the English language, according to Peter Szolovits, director of MIT's Clinical Decision Making Group.

To learn more:
- read the article