AI/Machine Learning Byte Buzz Healthtech

How AI is used today in healthcare?

Rapid advances in AI helping both doctors and patients.

There had been huge advances in the field of medicine in the past few decades: joint replacement, live donor liver transplant, DNA sequencing, MRI scan, stem cell transplants, etc. And now, there is Artificial Intelligence. AI has already produced impressive technologies that altered the healthcare landscape and enabled smarter and faster ways to diagnose, treat, and prevent diseases. Despite the advancements of AI in healthcare, and other fields as well, people believe that AI may turn on us and eliminate all our jobs. But in reality, technology is only as good as the humans who create it, direct it, and use it. And when it comes to healthcare, AI is crucial for reinventing and reinvigorating the healthcare system for the better.

Machine learning – neural networks and deep learning

Medical data is a high dimensional data; very vast and with thousands and thousand of attributes. Deep learning is a type of machine learning that uses layered algorithms architecture to  process and analyze data of this dimension and solve complex problems. This multi-layered strategy allows deep learning models to complete classification tasks such as identifying subtle abnormalities in medical images, clustering patients with similar characteristics into risk-based cohorts, or highlight relationships between symptoms and outcomes within vast quantities of unstructured data. 

Imaging analytics and diagnostics

One type of deep learning, known as convolutional neural networks (CNNs), is well-suited for analyzing images, such as MRI results or x-rays. CNNs are designed with the assumption that they will be processing images, allowing the networks to operate more efficiency and handle larger images. Researchers at the Mount Sinai Icahn School of Medicine have developed a deep neural network that takes just 1.2 seconds to process images, analyze its contents, and alert of problematic findings. By using these technologies to screen images and identify abnormalities in patient scans, radiologists can significantly reduce the risk for both misdiagnosis and oversight in their analysis. With AI algorithms detecting abnormalities quicker than the human eye, AI has the ability to drive more efficient workflows for radiologists.

Natural language processing

Making sense of human language has been a goal of AI researchers since the 1950s. This field, NLP, includes applications such as speech recognition, text analysis, translation and other goals related to language. Because neural networks are designed for classification, they can identify individual linguistic or grammatical elements by “grouping” similar words together and mapping them in relation to one another. For example, all mentions of fatigue would show on a timeline at the top of the page, and the notes about the word would show in a box at the bottom of the page. The interface makes it easier for clinicians to find buried data and make diagnoses they might have otherwise missed. 

Artificial Intelligence is estimated to contribute over $15 trillion to the world economy by the year 2030 and the greatest impact of AI will be in the field of healthcare. Besides the boost in the economy, both doctors and patients will benefit from the advancements in AI. Earlier and more accurate diagnostics, powered by AI, means earlier treatment of life-threatening diseases. Given the rapid advances in AI for imaging analysis and speech and text recognition, AI will help doctors by cutting documentation time and improving report quality.