Experts from the University of Portsmouth have utilised Artificial Intelligence and data analytics to improve bowel cancer patient care by predicting their stay in hospital.
This new algorithm also considers potential patient readmission after surgery and their likelihood of death over a one to three-month period. Thus, this development could not only improve bowel cancer patient care – by helping patients feel better prepared for the longevity of their treatment – but could also save the NHS millions of pounds.
Therefore, the intelligent model will allow healthcare providers to design the best patient care and prioritise resources.
The full article of this study has been published in Discover Oncology.
What does this algorithm mean for bowel cancer patient care?
Bowel cancer is one of the most common types of cancer diagnosed in the UK, with more than 42,000 people diagnosed every year.
Adrian Hopgood, Professor of Intelligent Systems at the University of Portsmouth, and one of the lead authors on the new paper, explained: “It is estimated that by 2035 there will be around 2.4 million new cases of bowel cancer annually worldwide. This is a staggering figure and one that cannot be ignored. We need to act now to improve patient outcomes.
“This technology can give patients insight into what they are likely to experience. They can not only be given a good indication of what their longer-term prognosis is, but also what to expect in the shorter term.
“If a patient is not expecting to find themselves in hospital for two weeks and suddenly, they are, that can be quite distressing. However, if they have a predicted length of stay, they have useful information to help them prepare.
“Or indeed if a patient is given a prognosis that is not good or they have other illnesses, they might decide they don’t want a surgical option resulting in a long stay in hospital.”
How was this algorithm developed?
Bowel cancer – also known as colorectal cancer – impacts the large bowel, which is made up of the colon and rectum. The cost of both diagnosing and treating patients is substantial and the economic impact on healthcare systems is immense.
The study utilised data taken from a database of over 4,000 bowel cancer patients who underwent surgery between 2003 and 2019. It looked at 47 different variables, including age, weight, fitness, surgical approaches, and mortality.
Additionally, researchers sought insights from consultant surgeon Jim Khan and his colleagues Samuel Stefan and Karen Flashman, as well as the analytical expertise of Dr Shamsul Masum, under Professor Hopgood’s direction.
Professor Hopgood commented: “We used a full set of data that included the 47 variables, but also predicted outcomes with just some of the most significant ones and found the two approaches showed very little difference. This is useful in itself because it shows that the algorithm is just as effective using a streamlined set of variables.”
When will this technology be introduced into healthcare settings?
In principle, this technology could be launched straight away. Although, it would first need to be approved for use in a clinical setting, and Professor Hopgood is keen to work with an even bigger dataset to improve the accuracy of predictions, which is already above 80%.
“If we could attract funding, we would love to get together with other bowel cancer centres, so we have access to even bigger datasets. With machine learning, the simple rule is the more data the better,” Hopgood concluded.
“Everyone I have spoken to in the health domain thinks that Artificial Intelligence will help them do a better job and we hope this research will do exactly that – by providing more accurate predictions, the health service can allocate the best resources to each patient and improve patient care.”
