AI Can Identify Heart Attack Risk by Providing Quick Analysis of Routine Osteoporosis Screening Results

A routine osteoporosis screening bone density test can tell if you are at increased risk for a heart attack because of the presence of calcium in the aorta.  

Now, this calcification test score can be calculated quickly by using machine learning, without the need for a person to grade the scans. 

“This development paves the way for use in routine clinical settings with little or no time to generate the useful calcification score that predicts heart attacks,” said Douglas P. Kiel, M.D., MPH, director of the Musculoskeletal Research Center at Hebrew SeniorLife’s Hinda and Arthur Marcus Institute for Aging Research and professor of medicine at Harvard Medical School.

This finding is documented in the article “Machine Learning for Abdominal Aortic Calcification Assessment from Bone Density Machine-Derived Lateral Spine Images,” published in the journal eBiomedicine.  The joint first author is Naeha Sharif of the Nutrition & Health Innovation Research Institute, Edith Cowan University, Perth, Australia; Centre for AI&ML, School of Science, Edith Cowan University, Perth, Australia; and the Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia.

“During DXA scans obtained for bone mineral density testing, vascular calcification of the aorta can be seen and quantified.  This study developed a machine learning algorithm to automatically determine the severity of the calcification that corresponds closely with the manual reading that is far more time consuming to perform,” said Sharif.

The scoring of abdominal aortic calcification scores from bone density machine images is laborious and requires careful training. As a result, AAC scoring is not routinely performed when these images are acquired in clinical practice.  This study developed, validated and tested machine learning algorithms for AAC assessment called ML-AAC-24, and evaluated it in a real-world setting using a registry study of 8,565 older men and women. Greater ML-AAC-24 scores were associated with substantially higher cardiovascular disease risk and poorer long-term prognosis.

Collaborating institutions are:

• Nutrition & Health Innovation Research Institute, Edith Cowan University, Perth, Australia
• Centre for AI&ML, School of Science, Edith Cowan University, Perth, Australia
• Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia
• Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Canada
• INSERM UMR 1033, University of Lyon, Hospices Civils de Lyon, Lyon, France
• Department of Radiology, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada
• George and Fay Yee Centre for Healthcare Innovation, University of Manitoba, Winnipeg, Canada
• Medical School, The University of Western Australia, Perth, Australia
• Department of Endocrinology and Diabetes, Sir Charles Gairdner Hospital, Perth, Australia
• MRC Lifecourse Epidemiology Centre, University of Southampton, Southampton, United Kingdom
• NIHR Southampton Biomedical Research Centre, University of Southampton and University Hospital Southampton NHS Foundation Trust, Southampton, United Kingdom
• Park Nicollet Clinic and HealthPartners Institute, HealthPartners, Minneapolis, USA
• Division of Health Policy and Management, University of Minnesota, Minneapolis, USA
• Departments of Medicine and Radiology, University of Manitoba, Winnipeg, Canada
• Centre for Kidney Research, Children’s Hospital at Westmead School of Public Health, Sydney Medical School, the University of Sydney, Sydney, Australia.

Funding information or grantor requirements:

• Dr. Kiel’s time was supported by a grant from the National Institute of Arthritis, Musculoskeletal and Skin Diseases (R01 AR 41398). 

About Hebrew SeniorLife
Hebrew SeniorLife, an affiliate of Harvard Medical School, is a national senior services leader uniquely dedicated to rethinking, researching, and redefining the possibilities of aging. Hebrew SeniorLife cares for more than 3,000 seniors a day across six campuses throughout Greater Boston. Locations include: Hebrew Rehabilitation Center-Boston and Hebrew Rehabilitation Center-NewBridge in Dedham; NewBridge on the Charles, Dedham; Orchard Cove, Canton; Simon C. Fireman Community, Randolph; Center Communities of Brookline, Brookline; and Jack Satter House, Revere. Founded in 1903, Hebrew SeniorLife also conducts influential research into aging at the Hinda and Arthur Marcus Institute for Aging Research, which has a portfolio of nearly $85 million, making it the largest gerontological research facility in the U.S. in a clinical setting. It also trains more than 1,000 geriatric care providers each year. For more information about Hebrew SeniorLife, visit our website or follow us on our blog, Facebook, Instagram, Twitter, and LinkedIn.