Time to embrace predictive models?

Lucy Mackillop, Sensyne Health CMO, analyses the role of predictive models and algorithms in healthcare, and why new technologies are key for the future. 

Since the pandemic began the healthcare industry has transformed – and technology has been at the core. At the time of writing, over 47 million people in the UK have received at least one dose of a COVID-19 vaccine – a vaccine that was developed and tested in a matter of months.

Research into tackling SARS-CoV-2 has been carried out at phenomenal speed, and technology adoption has accelerated to keep health services running while minimising the risk of infection.

Embracing modern technologies and embedding new processes also presents an opportunity to look at further innovation – in the form of machine learning (ML). With ML techniques the vast quantities of data generated by technology adoption in healthcare can be analysed rapidly and the insights presented to the clinician to aid decision-making.

The government has pledged an additional £250 million to boost the role of Artificial Intelligence (AI) – a clear indicator of the growing confidence in, and importance of these technologies. Its potential role in enabling medical professionals to work with greater efficiency, better understand individual patients and provide more personalised care is exciting. There are numerous examples of where technology is already having a positive impact in the development of sophisticated algorithms that have significantly changed the way clinicians provide patient care during the pandemic.

The benefits of predictive models

Predictive models and algorithms are generated through analysis of large sets of real-world data, such as electronic patient records. One benefit of this is being able to predict the likelihood of certain health conditions developing in particular patient groups. This can potentially facilitate earlier intervention and help to identify treatments that are likely to be most effective for a particular patient.

There are many reasons why the healthcare sector has sometimes been slow to embrace these kinds of technology. For example, the fact that human interaction, not technology, is at the heart of clinician-patient relationships. However, the use of technology has become widely accepted by clinicians as capabilities have developed and evidence of their clinical impact becomes apparent.

One example of this in practice is SYNE-COV, a clinical AI algorithm launched by Sensyne Health, which provides real-time decision-making support to NHS clinicians. Developed in collaboration with Chelsea & Westminster NHS Foundation Trust, SYNE-COV provides a risk score for three potential outcomes when a COVID-19 patient enters hospital; intensive care admission; invasive mechanical ventilation and in-hospital mortality.

The pandemic highlighted to clinicians that using modern technology can augment the decision-making process, enable clinicians to provide preventative care and relieve pressure on healthcare services – something that is going to be critical if we are to recover from the millions of GP appointments missed because of the pandemic.

Technology to support maternal health

Maternal health is a great example of where technology has already been embraced by clinicians and patients and is helping to ensure the safety of expectant mothers and their babies.

Regular check-ups and monitoring are a key part of the care of pregnant women. With the government advising a reduction of in-person appointments during the pandemic, virtual processes were put in place meaning pregnant women were supported through remote check-ups.

As with much of our lives during lockdowns, video calls became the norm in healthcare. UK research found that over half (57%) of people believe the ability to see a healthcare professional remotely during the pandemic has been important and helpful. And for maternal health, these continued virtual connections have been critical in the ongoing support for women during their pregnancy.

In addition to remote monitoring, predictive modelling and algorithms have made it easier and safer for clinicians to identify when a pregnant woman may need a specific treatment or care pathway. They can better predict which women are likely to need medication to control diabetes during their pregnancy, or which women should adopt certain lifestyle measures and take earlier intervention to help them.

What’s next for predictive healthcare?

Beyond maternal health, we will likely see this predictive healthcare model applied to other areas in the future. Chronic diseases like diabetes, obstructive pulmonary disease and heart failure will start to routinely benefit from predictive modelling and remote patient monitoring, not only making it quicker to identify illnesses, but also improving patient care.

Being able to manage long-term care remotely is a challenge, but specific short-term intensive support can be well addressed for patients suffering with chronic diseases, particularly when new treatments need starting. For example, for patients with type 2 diabetes who are transitioning to using insulin therapy or heart failure patients post discharge from hospital, short term monitoring can provide intensive support and care.

COVID-19 has caused technology to become an invaluable asset for the healthcare sector more than ever. As understanding around these technologies and acceptance of them increases, there are more opportunities for it to make a difference and revolutionise the way healthcare is delivered and received. Healthcare may have been slower to embrace new technology than other sectors, but AI and ML are now helping to drive a digital healthcare revolution.