Home / Blog / Getting a little help from AI

Getting a little help from AI

Comparison of a radiographic assessment made by a medical doctor (left) with the assessment supported by AI (right). Image credit: Ji Hoon Kim et al, BMC Medical Informatics and Decision Making

I have always been amazed by the ability of radiologists to pinpoint a problem by looking at those black and white RX! It turns out that it takes years of experience to get the knack, seeing what we don’t see at all.

Medical doctors in general rely on radiologists expertise to decode the meaning of an RX, although they have an understanding and capability to read an RX. Most of them do not have the same level of expertise, something that comes after thousands and thousands of RX inspection. Yet, in some occasion medical doctors have to make do with their limited skill since a radiologist is not available.

This is where AI can step in and make a difference.

A recent study published on BMC Medical Informatics and Decision Making shows how artificial intelligence can help emergency department -ED- doctors to interpret an RX resulting in improved diagnoses. This comes handy in those ED (particularly in smaller areas) where no radiologist is available.

The AI application has been trained using Deep Learning algorithms, basically by having the application “reading” hundred of thousands of RXs already interpreted by qualified radiologists to learn how to read an RX. In other words the application has benefitted from experience that would never become available to the average medical doctor in an ED.

More than that. The application keep learning both from local and global experience (by connecting to the cloud), hence it becomes better and better. Notice that the final diagnoses, and the decision on what should be done rest on the medical doctor.

I find this example interesting because in a way it shows how AI will dominate the coming decades, not taking over human brains, rather flanking them to augment their decision making capabilities.

This will be affecting most sectors of human activities (including the artistic ones!) resulting in augmented humans. At the same time, in the same way that schools teach how to use a pencil, a lathe, a compass,  we will need to learn how to use AI on the job and in our personal life and school will need to teach the new generations how to use AI.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.