Few industries are more ripe for creative disruption than healthcare, which consumes huge sums of public and private funding while still battling to meet demand from growing and ageing populations around the world.
As a result, artificial intelligence is increasingly becoming a force to be reckoned with in the medical field. But, as in many industries, its full potential is only now starting to emerge, and uncertainty remains about exactly how AI can best be harnessed to deliver better, more efficient care — and improve the experiences of patients and healthcare staff.
Diagnostics and imaging
Perhaps the area where AI has provoked the greatest excitement is in its potential to improve the speed and accuracy with which diagnostic scans are interpreted.
For example, Imperial College Health Partners in the UK — which brings together NHS providers, universities and industry across north-west London — sees a big role for the technology in delivering health innovations using real-world evidence. Its chief executive, Axel Heitmueller, says AI systems already allow MRI and CAT body scans, and X-rays, to be read “perhaps more consistently than humans can”.
However, he cautions that clinical professionals should not be taken out of the equation: “The evidence emerging, despite all the hype, [is that it’s] when you combine human and machine that you get the best results.”
One area that needs more discussion is the baseline against which AI tools should be judged in the field of diagnostics, he says. “Everyone always focuses on the machine and complains that a machine is not perfect. But we have never had [perfection] with healthcare professionals, so that raises the question: what is an acceptable failure rate for humans?”
Pranav Rajpurkar — assistant professor of biomedical informatics at Harvard Medical School and co-founder of a2z Radiology AI, which has produced an AI model for abdominal and pelvic CAT scans — believes failure rates may, one day, be eradicated altogether. He says: “I think there [can be] a world in which, because of AI, we don’t make medical errors [and] in which no disease is missed.”
However, while the technology is already contributing to the earlier detection of time-sensitive conditions, it is not yet “making people faster at what they do”, he cautions.
His research mission is to build what are called generalist medical AI models that will be capable of achieving “the full spectrum of tasks that doctors can do in medical image interpretation”.
While, currently, AI can detect lung nodules on chest X-rays, or lesions on mammograms, for example, “the expert still has to do 200 to 400 other things as part of the interpretation and we don’t [yet] have algorithms that can do that”, points out Rajpurkar.
“The efficiency value proposition is one that still we have not delivered on in AI, but one that I think is something we’re on the cusp of being able to do with upcoming technology advances.”
Treatment
Another area where AI is already proving its worth is in the provision of more tailored treatment. Anna Sala, an allergist who heads the innovation unit at Vall d’Hebron Barcelona Hospital Campus, points to a European project called TRUSTroke aimed at optimising stroke treatment. The project recently completed a successful pilot co-ordinated at the Spanish hospital.
The system will be trained using data from medical records and other information provided by patients and healthcare professionals via a mobile app. Sala says the platform will “analyse all factors related to the pathology, the patient and their environment”.
The resulting information “will provide reliable guidance for clinicians, patients and caregivers to help personalise treatment as much as possible and prevent risks and complications”.
She adds that AI has also begun to show its mettle in the field of rare diseases, pointing to a platform that has arrived at diagnoses even doctors have been unable to make after being fed information about patients’ symptoms and medical histories.
Communication with patients
At the same time, AI is helping to make interactions between healthcare teams and patients easier and more productive. For example, it can power a tool that transcribes a patient’s consultation, allowing the doctor to maintain eye contact, confident in the knowledge that an account is being generated that can rapidly be shared with the patient.
More ambitiously, AI is helping to determine when patients need a follow-up visit. Sala cites a chatbot named Lola, also developed at Vall d’Hebron with two companies, AstraZeneca and Tucuvi. It provides personalised tracking to patients suffering from heart failure and chronic obstructive pulmonary disease by asking those who have had hospital treatment to respond on their phones to a number of questions about how they are feeling and their ability to manage everyday tasks.
Their answers are sent to the cloud to be analysed by AI and, if they suggest a reason for concern, patients are be asked to attend an appointment. This innovation is sparing patients unnecessary trips and also helping the environment, Sala points out, by reducing the carbon footprint.
Back office
The capacity of AI to improve administration may not attract the headlines, but it can be as transformative as more eye-catching developments in patient screening and care, suggests Heitmueller.
Most industries have not started with customer-facing innovations, he points out — citing the legal profession, which has used AI “to automate really boring, repetitive processes like database searches, and so on. But, in healthcare, it seems we always start with a conversation about ‘should we have an AI doctor?’ rather than ‘have we actually automated our back office?’”
In the UK’s NHS public healthcare system, at least, there may be little incentive to improve this aspect of operations, he acknowledges. “We have annual budgeting [so] any savings are taken away from you if you achieve success . . . and so, therefore, it doesn’t make a big difference whether AI has anything to offer.” But integrated care systems in the US, for example, could benefit from the technology, he suggests.
Investment remains a barrier, though. Despite the “huge potential for automation, it [this area] is not where the funding is, and it’s also not where the attention is” in the health field.
Read the full article here