The Future of Medicine: Artificial Intelligence

by Greg Eriksen 

What is Artificial Intelligence?
Have you ever wondered how self-driving cars work or how Google Home replies to you as if it were human? The answer is artificial intelligence (AI). AI explains the ability for a machine to process information and simulate cognitive functions in response. Through mechanisms such as neural networks and deep learning, a machine can be trained to learn through experience. Consequently, AI machines are able to adjust to new inputs and come up with an appropriate response or action.This ability to accommodate new information helps to explain why self-driving cars don’t shoot off to the side with every bend in the road!

What is a Neural Network?
One of the primary systems artificial intelligence machines use are called neural networks. A neural network is a computer system that is inspired by the biological inner workings of the human brain. These networks are composed by a series of layers starting at what is known as the input layer. For each input, the system can dynamically analyze the data, which subsequently fires down different pathways of the neural network. The input continuously passes down the layers of the network, with each layer becoming more detailed. Through this filtering process, the system eventually is able to recognize the input and produces an appropriate output or response.

What does AI have to do with medicine?  
Other than being able to sleep while a self-driving car takes you to work, there are plenty of other potential applications for artificial intelligence that are likely more useful! A major area that  AI can improve is the analysis of big data, especially in the context of medicine. Big data is data so voluminous that traditional processing mechanisms cannot efficiently analyse it. Using AI technology, big data analytics can examine large amounts of data to uncover hidden patterns and insights in an extremely time efficient manner. In medicine, there are many fields that contain large amounts of data stored deep within online files. These include the millions of images in radiology to the millions of chemical compounds created in drug analysis.

With the ever-growing database in medicine, AI machines can access this and run problem solving algorithms in a process that would take humans much longer. In recent development, an artificial intelligence company known as Atomwise has developed a supercomputer which is able to analyse big data more efficiently than ever before. The supercomputer known as AtomNet is particularly used for pharmaceutical analytics. AtomNet is the first structure-based AI system that can predict the biological activity of small molecules used for drug discovery applications. Consequently, the company is able to analyze millions of theoretical molecules without wasting any materials. One of Atomwise’s biggest discoveries came from their research on the Ebola virus. Once the structure of the Ebola virus was found, it was designed on the AtomNet supercomputer. Following this, millions of simulations took place analyzing the different effects of molecules on the virus. In what would have taken traditional analytical processes months, the AtomNet AI system found two potential Ebola fighting treatments in less than one day!

The fundamental principle in biology that AtomNet exploits is that structure is largely associated with function. Therefore, the ability to determine where chemical bonding can take place is essential for the discovery of new drugs, and so AtomNet uses a convolutional neural network system that incorporates structural information in its analysis. By doing so, the system can assess how different molecular structures chemically fit together. In similar research to the Ebola virus, AtomNet investigated almost 82 million molecules and eventually discovered a protein-protein inhibitor for a treatment of the autoimmune disease multiple sclerosis!   
​
Pharmaceutical analytics is not the only medical field that AI can improve. An AI platform known as Arterys has been developed to assist radiologists in analyzing various medical images! Furthermore, another company known as 3Scan has created a system to efficiently analyze tissue pathology. Perhaps the most exciting partnership with AI technology is with the gene-editing CRISPR CAS-9 system. In short, this system is derived from a bacterial immune response against viruses. The CRISPR CAS-9 complex is able to take the genetic information of a virus and alternatively code for the destruction of that specific virus. With the new advances in genome editing, the CRISPR system can potentially synthesise any DNA molecule. One of the only barriers affecting its prosperity is the problem of off-target effects. To test these potential effects without stepping over ethical boundaries, Microsoft wants to turn to AI technology! The partnership between AI and genome editing may soon revolutionise disease prevention.
​
Artificial Intelligence is making a very strong case for its influence in the medical world. With its major advances in pharmaceuticals, radiology, and genome editing it is paving a very promising future. Although self-driving cars may be awesome, a disease-free world sounds a whole lot better.