Cardiovascular disease affects more women than all types of cancer combined. It is the leading cause of death, killing one in three women each year. It is also responsible for more than 30% of maternal deaths.

Yet when women seek treatment for heart disease, their treatment is often based on studies conducted on men.

“The need to improve cardiovascular care for women is probably one of the most pressing health issues worldwide – and certainly in the United States and India,” says Sandeep Gupta.

Gupta is a professor of computer science and engineering in the School of Computing and Augmented Intelligence, part of the Ira A. Fulton Schools of Engineering at Arizona State University. He also directs the Intelligent Mobile & Pervasive Applications & Communication Technologies Lab, known as the IMPACT Lab, where he works with Ayan Banerjee, a research associate at the Fulton Schools.

The couple researches applications of artificial intelligence (AI) in the medical field. They have received several grants, including from the National Science Foundation, to develop technical tools to improve treatment options for women.

Gupta explains that for decades, medicine assumed that men were the most at risk of heart attacks and heart disease. Doctors – and patients themselves – lack important information about preventive measures for women. Life-saving drugs such as statins were developed in clinical trials that predominantly involved male subjects. However, women are more likely to suffer from the side effects of these drugs.

This approach has created a world in which women are less likely to develop heart disease but far more likely to die from it.

“But AI has great potential to revolutionize women’s healthcare by moving from a one-size-fits-all approach to personalized and precise medicine,” says Gupta.

A team with impact

They say every person has a twin out there somewhere, but if Gupta and his team have their way, everyone will get a digital twin too. The researchers are developing tools that use a form of artificial intelligence known as machine learning. In these AI-based systems, software programs sift through, analyze, and compare massive amounts of data, recognize patterns, and draw useful conclusions. In the School of Computing and Augmented Intelligence, machine learning systems are used to virtually model new materials, discover new scientific laws, and combat social isolation among aging veterans.

The research team at IMPACT Lab is developing a new technology that combines expert medical knowledge, available research data and information from a patient’s medical history to create a profile that can be used by doctors and healthcare professionals to provide personalized treatment. The goal is to use the power of AI to fill the gaps in current medical research.

He says the collaboration his team gets with doctors and medical researchers at leading U.S. institutes such as Phoenix Children’s Hospital and the University of North Carolina at Chapel Hill is crucial.

“Solving these critical problems requires close collaboration between engineers, scientists and clinicians to find effective solutions,” says Gupta. “At IMPACT Lab, we are taking this approach and using AI to ensure that serious health problems affecting diverse populations, including women, are appropriately addressed.”

Because effective screening is one of the most important aspects of getting women at risk for heart disease the treatment they need, one of the first applications of IMPACT’s research is an electrocardiogram (ECG) reader. An ECG is a quick and simple test that doctors use to measure the electrical activity of a heart.

The AI-powered reader automatically analyzes the results of an ECG and provides the statistical probability that the patient has coronary heart disease (CHD). The project aims to address the gender disparity in CHD diagnoses. Gupta believes the work will achieve two important goals. It will eliminate the need for unnecessary and stressful cardiac imaging in low-risk women, and also ensure that doctors have accurate information when making decisions about their treatment recommendations.

IMPACT Lab researchers have conducted successful demonstrations of the system to teams of clinicians and are now busy implementing the experts’ feedback.

Pregnant women with type 1 diabetes have an increased risk

The IMPACT Lab team also deals with important topics in endocrinology.

Expectant mothers experience a whirlwind of emotions, from joy to nervousness to happiness to concern. Women with type 1 diabetes have especially much to worry about.

Type 1 diabetes is an autoimmune disease that often begins in childhood. The condition causes the pancreas to produce little or no insulin, a hormone the body needs to convert sugar into energy. To prevent sugar from building up in the bloodstream, diabetics require an external source of insulin, often given in the form of an injection.

Normal hormonal changes that expectant mothers experience during pregnancy can cause serious problems in women with diabetes. Blood sugar can fluctuate more in pregnant women with diabetes, and high blood sugar levels can lead to negative outcomes, such as high birth weight babies who need to be delivered via riskier cesarean sections.

An automatic insulin pump is a small portable device, often worn on the back of the arm, that automatically delivers the right amount of insulin at the required intervals. It is a good solution to the problem of ensuring that expectant mothers with diabetes get the insulin they need.

“However, there is currently minimal industry effort to develop a commercial, automated insulin delivery system for pregnant women with type 1 diabetes,” says Gupta.

Gupta points out that the medical community is understandably reluctant to conduct studies on pregnant women. The stakes are high, and no one wants to be responsible for unfortunate outcomes for babies or their mothers.

Here, too, he hopes that AI can help.

The IMPACT Lab team is using AI to simulate how much insulin pregnant women with diabetes need and creating algorithms that will help the pump deliver the right dose when needed. They are working with industry partners and hospital doctors to develop a pump prototype. The team can also use AI to conduct virtual testing, eliminating the need for pregnant women to participate in potentially dangerous trials.

Gupta is excited to see how this technology will be used in practice in the future. His team hopes that the automated insulin pump will soon be approved by the US Food and Drug Administration. They are also working with leading health organizations to explore the potential applications of their cardiology projects.

“Our goal is to develop intelligent healthcare systems that benefit under-researched populations,” says Gupta.