How AI is being implemented in the medical world

Artificial intelligence (AI) is often depicted as harming humanity in science fiction. The Stanley Kubrick-directed sci-fi masterpiece “2001: A Space Odyssey” found the HAL 9000 killing off its space crew, while the “Terminator” franchise centers on AI-powered machines rising up and warring with humans. However, a major real-world use case for artificial intelligence has been medicine. Learn how AI is being implemented in the medical world!

What is Machine Learning?

Machine learning is the practice in artificial intelligence of training a system to learn and iteratively improve without the need for additional programming. Essentially, computer programs are fed data and, over time, may learn from that information through experience. A sample set of training data is used so that a machine learning algorithm may establish predictions sans additional programming.  

Machine Learning for Detecting and Identifying

Cambridge, UK and Imperial College of London researches created an artificial intelligence algorithm that, through machine learning, was able to detect and identify brain lesions. The neural network-based AI platform utilizes machine learning, or predictive analytics. After a sample data set of more than 600 CT scans was introduced featuring brain lesions of differing varieties and sizes, the tool was then successfully able to identify brain lesions. It’s a pretty neat application, and theoretically could allow for a more streamlined process for identifying medical conditions. 

But AI in medicine is more far-reaching than that. Stanford University studies discovered that a deep learning algorithm proved as accurate at identifying skin cancer in patients as a human dermatologist. The project was built with a Google-created algorithm that was trained to identify over 1 million images across more than 1,000 different categories. Next up came creating a data set of skin cancer that could be used to further train the AI application. Ultimately, the skin cancer data set was comprised of over 120,000 skin lesion pictures showing more than 2,000 distinct diseases. Then, dermatologists were tested on their ability to identify cancerous as well as non-cancerous abnormalities in almost 400 pictures. And impressively, the AI algorithm was able to identify skin cancer with the same accuracy as its human counterparts. 

AI in Healthcare Benefits

Artificial intelligence can be applied to medical purposes, such as identifying skin cancer or brain lesions, opening up several different possibilities. First, there’s speed. It can take a highly-trained professional hours to analyze medical data, versus a machine learning algorithm capable of crunching data in a much shorter time span. There’s also the ability to scale, since AI is faster at analysis than humans. Which means that medical applications of artificial intelligence could examine more patient data in a shorter period of time than medical professionals. 

What’s more, since an AI platform for analysis could lead to better home-based care. As smartphones and mobile devices become more powerful, it’s possible that a smartphone app may be able to diagnose various medical conditions. 

As telehealth and telemedicine become more popular, and patient monitoring much easier through the use of wearables, predictive analytics can identify various subtle changes otherwise unidentifiable by humans. AI predictive modelling of Electronic Health Records (EHRs) was even able to predict the course of diseases and treatments in patients. 

When applied to medicine, artificial seeks to augment, not replace, the human component. For instance, AI programs may be utilized as a means of disease identification. Then, doctors may focus on treatment rather than spending hours on diagnosing. And predictive analytics lead to insights and may be employed for preventative care. 

Doctor AI - Artificial Intelligence in Medicine 

There are many ways that artificial intelligence can be put into practice for medical purposes. AI algorithms may be trained to identify different diseases. Data from wearable devices can be analyzed, and artificial intelligence platforms may monitor real-time data for abnormalities, or patterns emerge that can be useful for identifying risk factors in preventative medicine. When used properly, AI serves as a tool that medical professionals can use to streamline various components of their jobs, freeing them up for patient care. 

How have you seen AI applied to medicine, and what are the top areas you see artificial intelligence being used for real-world purposes?