UC Davis to Develop AI for Breast Cancer Detection, Risk Prediction

UC Davis to Develop AI for Breast Cancer Detection, Risk Prediction

www.mgireservationsandbookings.co.uk

UC Davis has received a $15 million grant renewal to develop artificial intelligence for improved, more equitable breast cancer screening and risk prediction.

November 09, 2022 - University of California Davis researchers have received a $15 million, five-year grant renewal from the National Cancer Institute (NCI) to fund artificial intelligence (AI) projects aimed at improving breast cancer screening and risk prediction while reducing health disparities.

According to the American Cancer Society, breast cancer is the most common cancer diagnosed among United States women and is the second leading cause of death from cancer among women. However, the disease burden of breast cancer varies across racial and ethnic groups, with disparities reported in rates of diagnosis, second cancers, and deaths.

Regular screening aims to catch breast cancer early, but some patients are still diagnosed with advanced cancer despite regular mammograms and screenings. According to the press release, many of these patients may have benefitted from more intensive or accurate screenings, which aren’t always easily accessible.

Dig Deeper

? UPMC Leverages Artificial Intelligence to Improve Breast Cancer Treatment

? Using Machine Learning For Personalized Breast Cancer Screenings?

? Machine Learning Supports Breast Cancer Diagnosis Predictions

“The US Preventive Services Task Force recommends screening every two years, which is sufficient for most women. But some women could benefit from screening every year or with supplemental imaging,” said Diana Miglioretti, PhD, professor and division chief of biostatistics at the UC Davis Department of Public Health Sciences and a researcher at UC Davis Comprehensive Cancer Center, in the press release. “Still, we need to be very careful about the impact of additional screening on women.”

Additional screening has the potential to lead to more false-positive results and overdiagnosis of breast cancer, the press release states, indicating that these outcomes occur more often with annual versus biennial screening and screening with supplemental imaging. Using the new grant, Miglioretti’s research team will evaluate whether improvements in breast imaging quality and regular screening will help support more equitable breast cancer outcomes.

The team’s previous work has focused on advancing the science of risk-based screening and surveillance for breast cancer by studying safer and more personalized screenings. The team has also created models based on patient factors such as breast density and age, and the researchers are now shifting to integrate AI and imaging features to improve risk prediction models.

“We're at a point where we've developed risk models for women with or without breast cancer, and we now want to be able to use those models to better select those who need to undergo more intense screening or surveillance,” said Miglioretti. “What's exciting about this grant renewal is incorporating artificial intelligence into these models to identify women at high risk of advanced cancer despite regular screening or at risk of second cancer missed by annual mammography.”

The grant will fund three new projects, which will use AI to predict which patients with no history of breast cancer are at high risk of being diagnosed with advanced cancer, identify factors contributing to breast cancer screening inequities, and develop a risk-based approach to flag patients who may be at higher risk of a cancer recurrence surveillance failure.

This research is the latest effort to improve breast cancer detection and risk prediction.

Last year, Michigan Technology University researchers shared that they had developed a machine learning model capable of classifying breast cancer tumors more accurately in histopathology images and evaluating the uncertainty of its own predictions to help reduce the risk of false-positives and adverse outcomes.

AI in healthcare, NZ leading the world

AI is on the verge of making massive changes in New Zealand’s public health system which has been facing structural resourcing issues in the last two years, exacerbated by the covid pandemic.

The AI Forum NZ says pervasive nurse and doctor shortages means Aotearoa needs to find new ways to spend limited resources in the most effective manner. AI, or artificial intelligence, is the answer.

More effective digital tools are needed to help process diagnostics, amplifying the scarce experienced resources the public health sector has on the ground, AIForumNZ executive director Madeline Newman says.

“Let’s give doctors the best digital tools possible to help them do the best job they can. This will result in better, faster, more effective diagnosis, builds trust and better outcomes for patients and their communities.

“We all want better health outcomes for our ageing population. Better use of technology over longer periods for this large group of people will help contribute to economic growth for longer, putting less strain on the public system.

People who report being in good rather than poor health are more than four times more likely to be working between the ages of 50 and 65, and more than 10 times more likely between 65 and 74.

“A mere 0.1 percentage point increase in spending on preventive health measures, as a proportion of each country’s GDP, can unlock a nine percent increase in annual spending by people over 60 years of age.

“New Zealand has a fast growing number of cutting edge AI healthcare companies such as radiologist Dr Hament Pandya’s Sectaur business.

“AI is about to revolutionise the practice of healthcare and Dr Hament is looking to provide diagnosticians with peer-to-peer learning and knowledge sharing.

“He is passionate about doctors of the future, combining the best of human intuition and knowledge with the data processing capabilities of computers.”

AI is not about replacing medical specialists. It is how New Zealand can better use of precious resources especially at a time of massive health skills shortages.

The digital, data and artificial intelligence (AI) dividends of the fourth industrial revolution will create better healthcare outcomes.

To gain the trust required for broader adoption, AI in healthcare must follow three principles: responsible use of data and algorithms, functional competence and transparency around technology’s limitations.

Already, AI-driven health solutions have proven more efficient and have become more effective, though the challenge remains in scaling up these technologies.

Eighty percent of doctors say AI in healthcare is useful. It is already there in exam rooms. It’s triaging hospital and emergency department traffic, analysing patient risk scores and identifying potential new therapies by simulating chemistry with computers.