Baltimore researchers say AI can help reduce disparities and improve access to healthcare – The Baltimore Sun

Cervical cancer, like many diseases, can be cured if caught early, but every year Millions of women Missing out on getting routine Pap smears for the disease, which kills a disproportionate number of black women.

during a pandemic, Cervical cancer screening rates have gotten worseespecially for low-income women and women from racial and ethnic minority groups.

A group of recent graduates from Johns Hopkins Carey Business School believes a solution to this problem can be rooted in Artificial intelligence. For a class they taught last fall, they developed a concept for the “smart plug,” a home Pap test they hope will make screening for disease more accessible and ultimately reduce disparities.

Jeff Kurkewich, senior scientist on the genomics team at Delfi Diagnostics, is working on extracting DNA from tumor samples.  Delphi uses machine learning, a type of artificial intelligence, to analyze blood samples and determine if patients have cancer.

They are not the only ones who have high hopes for the role that artificial intelligence and machine learning technology will play in the future of healthcare.

A growing number of researchers in Maryland and across the country see the technology as something that will change the way patients are treated, making it possible to diagnose them earlier, with more accuracy, and with better local markers who may be at risk of developing a disease or condition.

In just the past few months, Johns Hopkins University and the University of Maryland have started centers to further integrate AI into medicine.

Besides healthcare, the market for AI technology is booming, reaching environments as diverse as the courtroom and classrooms. By 2030, the market is expected to be worth more than $1 trillion, according to Market researchers.

But a cloud of anxiety has followed the technology’s growing importance.

Just like people, AI algorithms — and the large data sets they rely on — He could be biased. If used irresponsibly, technology can do that strengthening the methods of those systems It already discriminates against marginalized groups, and may be making it worse.

But in medicine, some researchers believe that if technology is developed thoughtfully — and doctors are educated about its limitations — it could make health care more affordable and accessible, while easing inequalities.

“AI has the potential to be a transformative technology in the practice and delivery of medicine,” said Ritu Agarwal, co-director of the Center for Digital Health and Artificial Intelligence at the Curry School. “But a lot more needs to happen before we can fully realize its potential.”

Like a lot of college projects, the idea for the smart stopper started with a group of students sitting around a friend’s living room.

For a class they were taking with Tinglong Dai, a professor at the Business School, the students’ task was to pick a healthcare challenge and figure out a way to tackle it using AI technology.

While the group was brainstorming, someone asked, “What is the one thing bad about health care that everyone is afraid of?”

For Hayley Hoglund and Madeline Howard, the two women in the group, the answer came quickly: Pap smears, the often uncomfortable procedure used to diagnose cervical cancer by scraping cells from the cervix.

In the following weeks, the group—which also included Charlie Acosta and Thomas D’Elia—developed a concept for a device that could be inserted like a tampon and scan the cervix, much like an iPhone would scan a user’s face.

Examination will be It’s uploaded to an app that uses artificial intelligence software to compare it to other cervical scans in a database. If the software detects cell abnormalities in the patient’s images, it will notify the provider or the patient to seek additional testing.

The group believes the tests could be done every three years, possibly during routine medical exams or even at home. Its ease of use can help close the gaps in disadvantaged communities where cervical cancer death rates are high. One A recent study It found that black women are 41% more likely to develop cervical cancer than white women, and they are 75% more likely to die from it.

Cervical cancer kills about 4,000 people each year.

Ultimately, Hoglund said, the goal is to encourage more people who have had a cervix to get screened for cervical cancer — especially those who wouldn’t be able to get to a doctor’s office for a Pap smear, and those who have experienced sexual assault or abuse, making the current procedure potentially that leads to one.

The “smart stopper” is far from the pharmacy shelves. The students don’t have a prototype, and though Hoaglund said they’re interested in finding investors, the project has been on the back burner since they graduated.

Shannon Davis, assay development scientist at Delfi Diagnostics, prepares samples for quality control.  Delphi uses machine learning algorithms to analyze blood samples and determine if patients have cancer.

Elsewhere in Baltimore, researchers are already investing big money in launching a test that uses artificial intelligence to screen a patient’s blood for tumor markers.

Delfi Diagnostics — the biotech company started by Dr. Victor Velculescu, a professor at the Hopkins School of Medicine in 2018 — has brought in $225 million in its latest fundraising round.

The technology being developed by scientists at the company uses a type of artificial intelligence called machine learning to analyze segments of DNA to sense the presence of cancer and locate the tumor in a patient’s body.

Delphi is currently conducting large clinical trials across the country for its lung cancer detection technology, Velculescu said. Next, the company’s scientists hope to develop a similar technology that can detect liver cancer with similar tests.

Like cervical cancer, the earlier lung and liver cancers are detected, the easier the diseases are to treat. But unlike the more invasive procedures now required to test for these types of cancer, Delfi tests will be able to perform blood samples drawn in a doctor’s office, Velculescu said.

“The goal is to develop tests that are very inexpensive and easily accessible, so that everyone can be screened — regardless of socioeconomic levels and so on,” Velculescu said.

In early November, on a rooftop in North Bethesda, officials from a group of educational and medical institutions in Maryland announced the creation of a center to study the use of artificial intelligence in medicine and support developments in this field.

It will use patient data from the University of Maryland medical system that has been stripped of identifying information in a range of projects, with the goal of improving treatment statewide, said Dr. Mark Gladwin, dean of the University of Maryland 3 – Health Computing Institute. University of Maryland School of Medicine in Baltimore.

Along with the University of Maryland Medical System, the partnership includes the University of Maryland, Baltimore, and the University of Maryland, College Park.

The lab and offices for the center are under construction in North Bethesda, and are expected to open in 2028, the University of Maryland, Baltimore, said in a press release. But Gladwin said he expects scientists to be hard at work six months from now in rented offices.

Officials hope the institute can use artificial intelligence to track the performance of newly approved drugs among diverse populations, identifying patterns in electronic healthcare records that will help doctors detect diseases early.

The researchers also hope to use the technology developed at the center to train surgeons and medical students, and eventually conduct clinical trials.

Gladwin said he is well aware of how AI algorithms can leave or harm members of marginalized communities. But he said the University of Maryland medical system has one of the most diverse patient populations in the world.

“We hope that by having a more inclusive and diverse group of patients, we will help ensure that developments in AI are inclusive of the entire population,” he said. “This is really important.”

The Center for Digital Health and Artificial Intelligence at Hopkins also wants to develop AI technology that works for everyone.

It’s part of the center’s broader mission, Agarwal said: to find new ways to use artificial intelligence to improve healthcare outcomes, whether in quality, patient safety, equity, access or cost.

Another Hopkins business professor, Judong Gao, is the co-director with Agarwal of the center. He described some of its ongoing projects, including one that uses a type of artificial intelligence to study doctors’ clinical notes to determine whether race and socioeconomic factors influence the breast cancer treatments they recommend.

The center also wants to work on a way to remove stigmatizing language from clinical notes, deleting phrases — such as calling a patient “difficult” — that are often used to describe members of marginalized communities.

Agarwal said it will take a lot of hard work — and possibly a few years — to fully understand how to create value from AI technology in healthcare.

“Take these technologies and spread and apply them within a fairly rigid regime for decades?” She said. “That will be a challenge.”

Leave a Comment