Microsoft, Doctors and AI: a powerful elixir improving patient outcomes in Europe

The potential for Artificial Intelligence (AI) when it comes to improving patient care and delivering better healthcare outcomes is huge. While its success hinges on the expertise of the clinicians and health professionals who use it, it can significantly ease pressure on resources and increase efficiencies.

Beyond research, AI can be applied in early disease detection and enable more precise diagnosis and accurate treatment for certain health conditions to increase the overall quality of people’s lives.

Having a laser focus
Making it easier for people to do what they do best is where AI can provide the biggest benefit. Clinicians at the General University Hospital in Prague, Czech Republic, are conducting joint research with Microsoft Project InnerEye to help doctors segment healthy anatomy and abnormalities in radiological images of prostate cancer patients.

Using machine learning, the solution can significantly speed up manual contouring processes. The tool will assist radiation oncologists in precisely delineating cancerous tissue and the organs at risk.

When done manually, using standard tools, a skilled specialist can take anywhere from 30 minutes to four hours to draw the outlines of these structures, depending on the type of cancer. The technology from Project InnerEye does this in a matter of a few minutes including the time needed for possible correction of the machine learning created contours.

Currently used in research, the solution has the potential to empower radiation oncologists to spend less time on labor-intensive processes and concentrate on their patients instead.

The right care at the right time
One of the areas where AI can provide potential benefits is oncology. Early detection and diagnosis of cancer is critical to improving a person’s chances of survival, as early-stage cancer is more responsive to treatment than late-stage cancer. However, some studies suggest that almost half of people who get cancer – with more than 3.7 million new cases of cancer each year – are diagnosed too late.

To support doctors in tackling this challenge, Russia’s Botkin.AI aims to improve the quality of analysis and recognition of diagnostic images for potential lung cancer patients. Through machine learning, the platform builds mathematical models for assessing the risks of developing cancer disease. The system can process a large volume of biomedical images and analyze medical data in a short amount of time. Currently used to detect lung cancer on CT scans, future models aim to include chest x-rays and mammography analysis, which can increase the number of recognizable pathologies.

The solution is already used in hospitals across Russia, particularly in the Novgorod region where the local administration is cooperating with the Skolkovo Foundation. In the case of chest and lung CT scans, Botkin.AI provides the relevant data to help doctors identify abnormalities earlier and make better informed clinical recommendations – with an accuracy of up to 95%. While AI can’t replace years of training and experience, Botkin.AI supports doctors in simplifying processes that would otherwise delay patient treatment.

Enabling early diagnosis and personalized medicine
AI is already being used to more accurately detect diseases at an earlier stage, but can also enable more precise and personalized treatment. Breathomix, a company based in the Netherlands, developed a new technology, BreathBase, which can analyze the complete mixture of molecules within a patient’s exhaled breath and provide a diagnosis within seconds.

The data allows doctors to diagnose and sub-type certain respiratory diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD) and lung cancer. The platform that was developed together with Tecknoworks in Romania analyzes patients’ exhaled breath in real-time, based on advanced signal processing and an extensive online reference database, infused with AI.

With the data instantly at their fingertips, physicians can provide on the spot care. Beyond that, AI can provide insights that are predictive in nature – pinpointing individuals who are more likely to respond to specific treatments, or who could develop lung disease in the near future.

There is no doubt AI is transforming healthcare. Europe’s healthcare providers have the opportunity to augment doctor ingenuity with data and AI to better treat diseases and in turn, make services more cost-effective. While the technology will open up new avenues for the industry, it is only ever as good as the people using it.

For more information on how AI is transforming healthcare in Europe click here.

This release was first published 11 June 2019 by Microsoft.