Towards our intelligent future: AI in health

Return to eHealthNews.nz home page

This is an extract from the report Towards our intelligent future, published by the AI Forum of New Zealand.

By using an AI-augmented screening programme, many deaths from breast cancer could potentially be prevented in New Zealand each year.

Reducing deaths from breast cancer

Over 600 women die from breast cancer each year in New Zealand. With an artificial intelligence- augmented screening programme, many of these deaths might be preventable.

Such a programme could pay for itself, given that the total cost of breast cancer in New Zealand is over $126 million per year, with $45,000 spent per diagnosed case. By 2021, the cost of cancer care is predicted to rise by 20 per cent.

Once proven such an approach to screening could then be generalised to other cancers. AI can be used to predict breast cancer, potentially five years in advance, diagnose it from medical images with comparable ability to radiologists and decrease the error rate of pathologists by 85 per cent.

Early detection of breast cancer dramatically improves the outcome for the patient. In New Zealand, improved screening for breast cancer over the past 20 years has reduced deaths from the disease by 27 per cent. If AI can further augment and improve breast cancer screening by even 10 per cent, this would result in saving 60 women’s lives each year and reduce the cost to the taxpayer by $12.6 million a year.

The need for early diagnosis underpins breast cancer screening. But rather than a one-size-fits-all approach, AI-driven predictive analytics could mean that screening in New Zealand is offered according to risk, thereby targeting more resources to those most in need and sparing those at very low risk from false positive results and unnecessary interventions.

Twelve per cent of women will develop breast cancer in their lifetime, but this does not mean that each woman has a 12 per cent risk. Risk is much higher with certain genes, such as the BRCA gene, and with a family history of breast cancer. There are potentially other patterns of risk that we don’t yet fully understand.

New Zealand has an opportunity to link and leverage our comprehensive health datasets and use this big data to train intelligent predictive models for breast cancer. Combining local and national datasets such as primary health records, electronic health records, the cancer registry, mortality collections, and adding new datasets over time such as a biobank, could yield a national-level predictive model for breast cancer risk that is able to provide far more granular and relevant predictions for high disease risk.

This model could be used by general practitioners and district health board oncology services to enable intensive monitoring and prevention or pre-emptive treatment of women at high risk for breast cancer, as well as reducing the screening frequency of those with vanishingly low probability of cancer, thereby minimising discomfort and anxiety around false positive results and freeing up resources.

Such a solution relies on AI foundations: skilled AI talent with domain knowledge and expertise building predictive models in health and medicine, research on applying AI to disease predictions and ensuring that data, algorithms and models employed are thoroughly evaluated (initially in parallel with usual care) and reviewed against ethical principles.

Volpara Solutions – tapping AI in the fight against breast cancer

Wellington-based Volpara Solutions’ mission is to reduce the mortality and cost of breast cancer by providing clinically validated software that underpins personalised, high quality breast cancer screening.

It can be difficult to isolate cancers in breast tissue that is particularly ‘dense’, as both cancer and dense breast tissue appear white on X-rays. Volpara’s software, built on Microsoft Azure, assesses more than 100 variables to help radiographers position the patient, capture higher quality images and automatically and objectively assess breast density.

These assessments mean that radiologists can quickly and objectively identify which women may benefit from supplemental imaging such as ultrasound. Not only does this enhance quality control, it also helps decrease costs by reducing the number of women recalled for repeat screening. This is important in the context of waiting lists and a global radiologist shortage.

The company recently reported annual recurring revenue growth of 86 per cent to NZ$6.63 million and full year cash receipts growth of 83 per cent to NZ$5.6 million. Volpara’s technology is now used by 7.1 per cent of the USA breast screening market.

Additionally, through Microsoft’s Co-Sell programme Volpara has arranged a trial of their technology with healthcare providers in Singapore.

This is an extract from the report Towards our intelligent future, published by the AI Forum of New Zealand.

If you want to contact eHealthNews.nz regarding this View, please email the editor Rebecca McBeth.

Read more views:

Scott Arrol Industry View: Standards are key to achieving the health data holy grail

Scott Arrol Industry View: The importance of health IT standards

Return to eHealthNews.nz home page