The University of Oxford’s Nuffield Department of Primary Care Health Sciences has successfully developed a new model to predict the likelihood of a person developing and dying of breast cancer within ten years.

The new risk-based screening model works to identify those at the highest risk of deadly cancers.

Despite the ability of breast cancer screening to reduce deaths, it can sometimes lead to unnecessary treatments due to overdiagnosis when innocuous tumours are detected.

In the UK, for every 10,000 women aged 50 years invited to breast screening for the next 20 years, 43 breast cancer deaths will be prevented, but 129 will be overdiagnosed.

Researchers analysed anonymised data from 11.9 million women aged 20 to 90 years between 2000 and 2020 from the OResearch database.

The team tested four different modelling techniques to predict breast cancer mortality risk: two traditional statistical-based models and two artificial intelligence (AI) models, all of which included the same types of data, including age, weight, history of smoking, history of breast cancer and use of hormone therapy (HRT).

The models were evaluated across a diverse range of groups of women using a technique called internal-external cross-validation, which divides the dataset into structurally different parts.

Funded by Cancer Research UK, the study results showed that one statistical model developed using 'competing risks regression' performed the best overall after it accurately predicted which women will develop and die from breast cancer within a decade.

The machine learning models were less accurate, particularly for different ethnic groups of women.

Dr Ashley Kieran Clift, first author and clinical research fellow at Nuffield, department of primary care health sciences, University of Oxford, said, upon further studies, that the model "could be used to identify women at high risk of deadly breast cancers who may benefit from improved screening and preventative treatments".

"This paper took a new approach" when identifying women at the highest risk of deadly cancers, said Professor Stavros Petrou, co-author and health economics lead, Nuffield, primary care health sciences, University of Oxford.

The approach could also avoid unnecessary harm to women and reduce costs for the NHS.

https://www.pmlive.com/pharma_news/new_screening_model_shown_to_predict_ten_year_breast_cancer_mortality_risk_1497356