AI applications in the healthcare system
The application of artificial intelligence (AI) in healthcare has become very relevant during the pandemic, playing an important role from the analysis of scientific documents about coronavirus to the search for the symptoms of Covid-19 in CT scans.
In which areas will AI have the greatest impact? In this article we will analyse growing trends in AI. Some of them have been accelerated by Covid-19 and we should pay attention to see what they will bring next.
MRI and CT scans
One of the main drivers of AI business in healthcare is the use of computer vision in radiology. We can use AI to detect abnormalities in medical examinations and assist in the diagnosis of diseases. The market is full of AI products for radiological diagnosis. Many companies have quickly reoriented their products to look for signs of Covid-19 on lung CT scans.
AI-enhanced imaging, along with AI-assisted diagnostics, has the potential to dramatically reduce costs. Theese costs are associated with radiology examinations, while improving safety and accessibility.
Blood tests: instant and at home
Computer vision is turning smartphones into very powerful diagnostic tools and reducing the need for expert interpretation of some test results. Gauss Surgical, an AI company that started with an blood loss monitoring platform for operating rooms, expanded its technology to consumer diagnostics during the Covid-19.
Gauss partnered with biotech company Cellex to develop rapid diagnostic kits for Covid-19. To carry out their antigen test, consumers need to apply a nasal swab using one of Cellex’s home test kits. Gauss states that the new Gauss-Cellex in-home antigen test, with its AI layer, allows non-expert users to perform and interpret the test with an iPhone or Android phone.
Reviewing pathology slides is a very complex task. It even requires years of training to gain the expertise and experience to do it well. Instead of analysing the slides under a microscope, a pathologist can view the images remotely on a computer. This is thanks to AI, as well as being able to collaborate with other medical experts through cloud-based software. Medical experts can also take advantage of algorithms to help with image analysis and diagnosis.
In 2017, Google published research on the use of deep learning for the detection of tumours from microscopic samples.
AI-driven passive surveillance
Passive contactless biometrics are reducing the workload of healthcare professionals. This technology has the potential to become one of the most widely used beyond the current health crisis.
An AI device is able to differentiate between patients in a room by their movement patterns, can sense people through some walls, and is sensitive enough to capture subtle movements such as the movement of a patient’s chest to analyse breathing patterns.