Industry Insights AI: 23/05/25
In this week’s insights post, we discuss some of the latest developments regarding the potential application of artificial intelligence (AI) tools in oncology care.
Machine learning can recognise hydroxyurea resistance in blood cancer
In a recent report published in Leukemia, researchers presented a machine learning (ML) model that can identify patients with polycythaemia vera who may not respond well to hydroxyurea treatment. Polycythaemia vera is a rare blood cancer in which early identification of treatment resistance helps avoid disease progression. According to the researchers, the model used clinical and genomic data to pinpoint specific markers of hydroxyurea resistance. This could potentially support timely and personalised treatment decisions for patients with polycythaemia vera.
Personalising diet recommendations for patients with cancer
A recent study published in Nutrients highlighted the role of artificial intelligence (AI) in personalising nutrition plans for patients undergoing cancer treatment. Malnutrition is a common issue in oncology care. In an interview conducted at the American Association for Cancer Research Annual Meeting 2025, Julia Logan, BS, main author and MD candidate at Sidney Miller Medical College, elaborated on the study’s findings. According to Logan, AI tools can generate tailored nutrition recommendations by analysing electronic health records, dietary habits and treatment responses. This level of personalisation can help address weight loss, manage side effects and improve patient quality of life.
Link to interview (part 1; part 2)
AI can use smartphone images to diagnose malignant skin lesions
Researchers have trained a deep learning model to analyse smartphone images of skin lesions with remarkable accuracy. In a study from the International Journal of Intelligent Systems, Oyedeji et al. explained that their model can classify lesions as benign or malignant with performance comparable to that of dermatologists. This innovation opens the door to fast and accessible skin cancer screening. According to the researchers, their discovery promises to reduce diagnostic delays and support early interventions.
Want to get in touch? Contact us at https://elion.nz/get-in-touch/
