Cracking the 60% problem: AI tailors chemotherapy dosing for Aussies with bowel cancer

University of Melbourne and Western Health researchers have pioneered an innovative artificial intelligence (AI) tool aimed at preventing inaccuracies in chemotherapy dosing for cancer patients.

Presently, approximately 60% of colorectal (bowel) cancer patients receiving chemotherapy experience either underdosing or overdosing. Chemotherapy dosages have traditionally been calculated using body surface area, a method deemed highly flawed due to its omission of crucial body composition factors. Height and weight alone fail to account for variations in muscle, fat, and bone percentages among patients.

Professor Justin Yeung, a colorectal surgeon at Western Health, highlighted the severe consequences of such errors, including immunosuppression, heart attacks, and respiratory infections.

“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,” Professor Yeung emphasised.

In response, the researchers developed an AI algorithm leveraging advanced image recognition and machine learning (ML) technologies. This breakthrough allows precise determination of chemotherapy quantities based on individual body compositions.

The research team incorporated data from over 1,000 colorectal cancer patients at Western Health, utilising CT scans to train and validate their algorithm.

“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,” Professor Yeung remarked. “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.”

To address the pressing clinical need for personalised chemotherapy dosing, the team founded PredicTx Health, a startup dedicated to translating their research into practical solutions. Recently securing $499,760 in funding through Australia’s Economic Accelerator program, they plan to conduct further trials, develop the AI algorithm and user interface prototype, and integrate the solution into future healthcare systems.

Initially focusing on colorectal (bowel) cancer patients, the team aims to advance to clinical trials at multiple health services, including Western Health, to compare their technology against current dosing standards.

In reimagining healthcare across the entire patient journey, Health Industry Hub^TM is the only one-stop-hub uniting the diversity of the Pharma, MedTech, Diagnostics & Biotech sectors to inspire meaningful change.

The Health Industry Hub^TM content is copyright protected. Access is available under individual user licenses. Please click here to subscribe and visit T&Cs here.