Healthcare is in the midst of a revolution and Artificial Intelligence (AI) is leading the charge. Just as patients increasingly assert their right to quality, accessible care, the provision of healthcare services has shifted from reactive to preventative care. With chronic diseases now posing the biggest threat to developed nations – causing 550,000 premature deaths in Europe in 2016 and costing EU nations 115 billion dollars annually – the need for technological innovation is palpable. Luckily, Dr AI has just the solutions.
From speeding up patient diagnosis, to enhancing accessibility to healthcare and tightening up the cyber security of sensitive patient data, AI has the potential to create valuable changes at all levels within the sector. Its biggest challenges so far can be found in public perception, the transparent and anonymous use of medical data and infrastructural setbacks. However, progress is being made – and fast.
“As health services struggle to cope with the strain of growing numbers of patients presenting with chronic diseases, the application of AI technologies will help doctors to assess and care for patients with increased efficiency and cost effectiveness”
In November, GE Healthcare* announced partnerships with both Nvidia* and Intel to further accelerate the adoption of AI in healthcare and boost digital imaging – bringing the most sophisticated AI to GE’s 500,000 imaging devices globally. GE will use Intel technologies to boost patient care and reduce hospital costs via edge to cloud imaging technologies. The Intel® Xeon® Scalable platform will lower the total cost of ownership for imaging devices by up to 25 percent. It is testament to the fact that radiology is proving to be an area ripe for developing algorithms that can interpret images.
So the progress is real, but how does it work? From MMR scans, to cardiograms and X-rays, medical imaging is exploding. With so much data available, AI can be trained to identify key patterns at superhuman speeds, which will ultimately be used to augment the decision making of our doctors. The result is more accurate and efficient diagnosis, which is critical to maintaining a high standard of care. What’s more, these abilities democratise the provision of healthcare by making the optimum standard of care accessible to all.
The benefits of AI-based decision-making are most obvious when it comes to the hardest medical cases. For example, distinguishing whether a patient is suffering from cardiomyopathy or pericarditis. An echocardiogram – a scan which looks at the heart and nearby blood vessels – might determine that symptoms such as breathing difficulties and swollen ankles are to be attributed to the patient’s heart muscle, but the doctor needs to ascertain which of the two ailments is the key offender. A skilled and experienced cardiologist can make an accurate diagnosis three out of four times, but for other physicians it’s 50:50. However, in a recent experiment using AI, the difference between the two conditions was spotted 9 out of 10 times.
These kinds of studies are reshaping healthcare as we know it. In this case, the data from 50 patients with constrictive pericarditis and 44 patients with cardiomyopathy was loaded into the Intel® Saffron™ AI. This amounts to 90 measurements taken from six locations in the heart and 20 times in a single heartbeat for a total of 10,000 attributes per patient per heartbeat – a lot of data! Notably, the AI reached its accuracy rate after ingesting data from only a third of patients, boasting a shorter learning curve than other machine learning approaches.
Gayle Sheppard,VP and GM, Intel® Saffron™ AI explains: “Before, for these types of diagnoses, you had to know what you were looking for; focus in on a few attributes—and in the process, human bias was introduced. The revolution here is being able to deliver higher accuracy based on all 10,000 attributes per heartbeat. It’s a no-compromise scenario, which results in the best outcome.”
As health services struggle to cope with the strain of growing numbers of patients presenting with long-term, chronic health conditions, the application of AI technologies will help doctors to assess and care for patients with increased efficiency and cost effectiveness. But AI is also helping patients to fight back themselves, equipping them with health apps that put them in charge of their health, from the comfort of their own homes.
Healthcare apps like the UK and Berlin based Ada*, encourage potential patients to take charge of their healthcare by screening their symptoms through the app first – which drills into the answers from a series of diagnostic questions , before receiving recommendations as to whether it is necessary to go to the doctors or simply remedy harmless symptoms at home. This in turn alleviates busy local healthcare services, while making healthcare accessible to all, from their smartphones and devices. The UK-based app Babylon*, offers a similar service with a symptom-checker function, using a mix of AI and video and text consultations with doctors and specialists. The UK government health service (NHS) has been trialling the app as a replacement for its telephone service, through which patients describe their symptoms.
With interest in the power of AI in healthcare growing, our future health is set to be turbo-charged. By enhancing our human abilities with machine learning, not only will the mire of chronic diseases be better understood, but health care providers will be better positioned to provide the necessary care as their services are increasingly streamlined. Thanks for waiting, Dr AI will see you now.
*Other names and brands may be claimed as the property of others
For more information:
Stay connected to technologies, trends, and ideas that are shaping the future of the workplace with the Intel IT Center.