More than 1000 Western Health cancer patients have helped develop an artificial intelligence tool that could prevent future patients from receiving incorrect doses of chemotherapy.
Professor Justin Yeung – who is a consultant colorectal surgeon at Western Health and Head of the Melbourne Medical School’s Department of Surgery (Western Precinct) at the University of Melbourne – has spent six years working with colleagues to develop technology that more accurately calculates chemotherapy for individual patients.
The team’s AI algorithm, which uses image recognition technology and machine learning to better predict safer and more effective chemotherapy doses, has shown significant benefits in previously treated colorectal cancer patients. And now a clinical trial is being planned at Western Health and other health services.
Currently, a patient’s chemotherapy dose is calculated according to their estimated body surface area – based on height and weight measurements.
However, Prof Yeung and his fellow researchers say this calculation is often highly inaccurate because it doesn’t factor in body composition, including the ratios of fat, bone and muscle.
The result is that an estimated 60 percent of colorectal cancer patients who undergo chemotherapy are either overdosed or underdosed.
“It doesn’t make logical sense for two patients with significantly different fat and muscle ratios to be given the same chemotherapy dose just because they have similar body surface areas,” Professor Yeung said.
“For example, a sumo wrestler and a body builder who have comparable body surface areas, would theoretically be given the same chemotherapy doses, however as their body compositions are vastly different, they would likely develop different degrees of toxicities.”
Professor Yeung said overdosing could cause a raft of side-effects, from mild to severe.
“Major side-effects include immunosuppression, heart attacks and chest infections,” he said.
“Many incorrectly dosed patients stop treatment too early due to these debilitating side-effects, but if there’s no other cancer treatment available for them, this decision can drastically reduce their chance of survival.”
To train and test the AI algorithm, Prof Yeung’s team utilised data - including CT scans -from a cohort of more than 1000 colorectal cancer patients at Western Health over six years.
The algorithm analysed the scans and found the patients’ body compositions (percentages of fat, bone and muscle) determined how the chemotherapy drug was metabolised and stored in their bodies.
Using these findings, the algorithm can now calculate tailored chemotherapy doses for patients using their body compositions.
“Our algorithm was able to produce accurate chemotherapy dosing for 84 percent of those patients which is a significant improvement over current methods of dosing,” Prof Yeung said.
Recognising the clinical need for a patient tailored chemotherapy dosing solution, the team has formed a startup called 'PredicTx Health' to translate their research into a product.
The team recently secured $499,760 in grant funding through Australia’s Economic Accelerator program and a further $150,000 from a Victorian Government grant to fund an observational trial, the development of an AI algorithm and a prototype UI, as well as technology to integrate the solution into future health systems.
This followed earlier support from the Western Health Foundation, and a $50,000 grant from Telematics Foundation.
The next step – a clinical trial – will compare the AI technology with current chemotherapy dosing methodology.
Professor Yeung said that his team was "greatly appreciative of all the help that prior patients have done to allow for this new worldwide technology to be developed at Western Health".
