Duncan Allen, sales manager, InterSystems, discusses why interoperability is a must have for organisations creating AI-powered healthcare solutions.
The development of innovative AI-powered solutions is an exhilarating experience until the problem of scaling rears its head. One of the real barriers to progress can be a failure to understand how to scale applications or exchange data securely and efficiently with established health technology systems.
In healthcare, interoperability between applications and systems is fundamental to advances in research, diagnosis and treatment. It is why stand-alone solutions are comparatively rare, especially when they are driven by a technology such as AI. A new solution may have cutting-edge capabilities but it will struggle to get beyond the pilot phase unless it has the ability to integrate its data with that of other health systems and organisations. Those creating new solutions therefore need to engineer them with healthcare data standards compliance as a priority.
In England and Wales, for example, the NHS has been highly effective in introducing mandatory data standards HL7 V2 and FHIR which govern and enable interoperability. Any applications seeking uptake in the NHS or interaction with its systems must adhere to these standards. Although start-up and SME-owners and creators are often remarkably inventive and have robust business plans, they frequently overlook the challenges of scaling and interoperability that such standards present.
There is little doubt that medtech innovators and start-ups would save themselves a huge amount of difficulty and effort if they tackled the questions of scaling and interoperability early on. Primarily they would be well-advised to implement a data platform strategy. This will make their data secure, available and compliant with standards so they can optimise the AI capabilities of their solution.
The unified data platform approach takes care of the data donkey work that makes a new product operational. It leaves business owners and creative minds free to concentrate on driving their businesses forward. The UK-based digital tech company, Cognetivity, is an excellent example, not least because its solution has potential for very wide application which lack of interoperability would completely undermine.
The company spun out of Cambridge University and has commercialised and deployed with the NHS, a highly sensitive, AI-powered test that can detect signs of dementia many years before visible signs would normally occur. The solution is in use with ten NHS trusts in research form, and with two trusts on a commercial basis.
Diagnosis comes from a simple, five-minute test in which patients use an iPad. It is totally non-invasive, and results are not affected by cultural or educational bias or by the ability of patients to learn the test, all of which are common weaknesses in other methods. The test uses human’s evolutionary ‘food or fear' response to animals to stimulate large areas of the brain with images. An AI engine measures speed and accuracy of responses and analyses the data. It assesses the user's risk, achieving a previously unattainable level of accuracy for a non-invasive test.
Being able to achieve an accurate detection of Alzheimer’s years earlier than is possible with previous tests will enable healthcare providers to significantly improve deployment of resources and give individuals and families the opportunity to prepare better. It also makes effective intervention with emerging drug therapies more likely to succeed. The disease currently afflicts 54 million people around the world, a figure set to rise to 130 million by 2050. The US Alzheimer’s Association estimates early diagnosis of people with mild cognitive impairment could save more than $7 trillion in health and care costs through earlier clinical interventions.
The main point here is that through its use of a data platform, Cognetivity is able to integrate its solution with incumbent NHS healthcare data systems. This enables the solution to combine its data with demographic data and ensures that critical information gets to the right person at the right time in primary and secondary care. The creative and business minds behind Cognetivity understand that seamless interoperability is essential to the uptake of their solution across the NHS. In any health network, integration of data is necessary for efficient adoption and effective decision-making across the entire patient care pathway. In the near-future Cognetivity expects to combine its data with patient histories for more detailed analysis.
It is a fine example of how data management and integration enable ground-breaking technologies to achieve acceptance and implementation, bringing their very significant benefits to clinicians and patients at scale.
