US EditionDeep Learning Algorithm Uses Mammograms and Age for Heart Disease Prediction
Researchers developed a deep learning model analyzing mammograms from nearly 50,000 women to predict cardiovascular events, matching traditional risk calculators in accuracy, study shows.
- Researchers at The George Institute for Global Health, with the University of New South Wales and the University of Sydney, developed a machine learning model analyzing routine mammograms to predict women's cardiovascular risk, published in the journal Heart.
- Because cardiovascular disease remains the leading cause of death worldwide, researchers aimed to repurpose routine mammography to better detect risk in women often underdiagnosed and undertreated for CVD.
- The team trained the algorithm on routine mammograms from 49,196 women aged 35–94 with a mean age around 60; nearly 3,400 events occurred during follow-up and it performed comparably with AHA and PREVENT calculator.
- The approach could provide a cost-effective 'two-for-one' screening option, with researchers saying it could soon be scaled globally but requires further validation in diverse populations.
- Transitioning the model into routine clinical use could revolutionize preventive cardiology by improving early risk stratification in women undergoing routine mammography, as the study linked imaging data to hospital and mortality records for precise correlation with major adverse cardiac events.
28 Articles
28 Articles
Deep learning algorithm uses mammograms and age for heart disease prediction
A new machine learning model developed by The George Institute for Global Health can successfully predict heart disease risk in women by analyzing mammograms. The findings were published today in Heart, the official journal of the British Cardiovascular Society.
Deep learning algorithm uses mammograms and age for heart disease prediction – RamaOnHealthcare
A new machine learning model developed by The George Institute for Global Health can successfully predict heart disease risk in women by analyzing mammograms. The findings were published today in Heart, the official journal of the British Cardiovascular Society.Developed in collaboration with the University of New South Wales and University of Sydney, this is the [...]
AI tool uses mammograms to predict women’s 10-year heart health and cancer risk
Scientists from Australian universities and The George Institute for Global Health have developed an artificial intelligence tool that uses mammogram images and a woman’s age to predict her risk of hospitalization or death from heart issues within the next 10 years. The tool was created to address the significant lack of routine heart disease screening for women, despite cardiovascular diseases being the cause of 35% of female deaths globally. T…
Coverage Details
Bias Distribution
- 42% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
