Artificial intelligence in the form of machine learning and deep learning is changing how we live and work continuously as it evolves at a rapid pace. The use in medicine and diagnosis is growing at an increasing pace.
I have already posted on the use of AI in the form of machine learning in drug development, medication adherence, healthy behavior, support for caregivers, as well as how machine learning was outperforming pathologists in diagnosing breast cancer tumor progression predictions.
AI in the form of deep learning has recently been shown to outperform humans in breast cancer detection when cross-referencing X-ray, MRI scan, and ultrasound. Andrew Bradley from UQ, Australia, has created a prototype system cross-referencing these data sources automatically using deep learning. This will be presented at the International Conference on Medical Image Computing and Computer Assisted Intervention in Munich Germany in October.
In addition to the work of Prof Bradley, we have also seen that AI deep learning, when used to analyze X-Rays, can distinguish between enlarged hearts, and fluid build-up around the lungs. Similar algorithms are being used to detect cancerous growths on the spine with superior results to existing non-AI approaches.
So where are we now with diagnosis?
* straightforward health and illness diagnosis being performed automatically with Cue,
* the detection of disease being performed with superior results to humans with AI deep learning,
* progression of disease being performed with superior results to humans with AI machine learning.
Where will this leave the doctors of the future?
The AI algorithms we use in our own work are so complex that, although they can be explained, you do really need a strong AI mathematical background to follow them. These medical diagnostic algorithms will be equally complex.
Will physicians of the future feel comfortable trusting machines without a strong understanding of the algorithms?
It is hard to say but one thing is for sure, Artificial intelligence will transform the medical space quite profoundly in the coming years. Watch this space.
Machines have already transformed healthcare. MRI scanners can peer inside the body, for example, and blood samples are analysed automatically, but human skill has always been an integral part of the process: a scan reveals a shadow – the oncologist recognises its significance. But doctors are often busy and overworked; they can make mistakes or overlook telltale symptoms. If computers could understand health on their own terms, perhaps they could speed up diagnosis and even make it more accurate.