As I checked in at a Manhattan radiology clinic for my annual mammogram in November, the front desk staffer reviewing my paperwork asked an unexpected question: Would I like to spend $40 for an artificial intelligence analysis of my mammogram? It’s not covered by insurance, she added.

I had no idea how to evaluate that offer. Feeling upsold, I said no. But it got me thinking: Is this something I should add to my regular screening routine? Is my regular mammogram not accurate enough? If this AI analysis is so great, why doesn’t insurance cover it?

I’m not the only person posing such questions. The mother of a colleague had a similar experience when she went for a mammogram recently at a suburban Baltimore clinic. She was given a pink pamphlet that said: “You Deserve More. More Accuracy. More Confidence. More power with artificial intelligence behind your mammogram.” The price tag was the same: $40. She also declined.

In recent years, AI software that helps radiologists detect problems or diagnose cancer using mammography has been moving into clinical use. The software can store and evaluate large datasets of images and identify patterns and abnormalities that human radiologists might miss. It typically highlights potential problem areas in an image and assesses any likely malignancies. This extra review has enormous potential to improve the detection of suspicious breast masses and lead to earlier diagnoses of breast cancer.

While studies showing better detection rates are extremely encouraging, some radiologists say, more research and evaluation are needed before drawing conclusions about the value of the routine use of these tools in regular clinical practice.

“I see the promise and I hope it will help us,” said Etta Pisano, a radiologist who is chief research officer at the American College of Radiology, a professional group for radiologists. However, “it really is ambiguous at this point whether it will benefit an individual woman,” she said. “We do need more information.”

The radiology clinics that my colleague’s mother and I visited are both part of RadNet, a company with a network of more than 350 imaging centers around the country. RadNet introduced its AI product for mammography in New York and New Jersey last February and has since rolled it out in several other states, according to Gregory Sorensen, the company’s chief science officer.

Sorensen pointed to research the company conducted with 18 radiologists, some of whom were specialists in breast mammography and some of whom were generalists who spent less than 75% of their time reading mammograms. The doctors were asked to find the cancers in 240 images, with and without AI. Every doctor’s performance improved using AI, Sorensen said.

Among all radiologists, “not every doctor is equally good,” Sorensen said. With RadNet’s AI tool, “it’s as if all patients get the benefit of our very top performer.”

But is the tech analysis worth the extra cost to patients? There’s no easy answer.

“Some people are always going to be more anxious about their mammograms, and using AI may give them more reassurance,” said Laura Heacock, a breast imaging specialist at NYU Langone Health’s Perlmutter Cancer Center in New York. The health system has developed AI models and is testing the technology with mammograms but doesn’t yet offer it to patients, she said.

Still, Heacock said, women shouldn’t worry that they need to get an additional AI analysis if it’s offered.

“At the end of the day, you still have an expert breast imager interpreting your mammogram, and that is the standard of care,” she said.

About 1 in 8 women will be diagnosed with breast cancer during their lifetime, and regular screening mammograms are recommended to help identify cancerous tumors early. But mammograms are hardly foolproof: They miss about 20% of breast cancers, according to the National Cancer Institute.

The FDA has authorized roughly two dozen AI products to help detect and diagnose cancer from mammograms. However, there are currently no billing codes radiologists can use to charge health plans for the use of AI to interpret mammograms. Typically, the federal Centers for Medicare & Medicaid Services would introduce new billing codes and private health plans would follow their lead for payment. But that hasn’t happened in this field yet and it’s unclear when or if it will.

CMS didn’t respond to requests for comment.

Thirty-five percent of women who visit a RadNet facility for mammograms pay for the additional AI review, Sorensen said.

Radiology practices don’t handle payment for AI mammography all in the same way.

The practices affiliated with Boston-based Massachusetts General Hospital don’t charge patients for the AI analysis, said Constance Lehman, a professor of radiology at Harvard Medical School who is co-director of the Breast Imaging Research Center at Mass General.

Asking patients to pay “isn’t a model that will support equity,” Lehman said, since only patients who can afford the extra charge will get the enhanced analysis. She said she believes many radiologists would never agree to post a sign listing a charge for AI analysis because it would be off-putting to low-income patients.

Sorensen said RadNet’s goal is to stop charging patients once health plans realize the value of the screening and start paying for it.

Some large trials are underway in the United States, though much of the published research on AI and mammography to date has been done in Europe. There, the standard practice is for two radiologists to read a mammogram, whereas in the States only one radiologist typically evaluates a screening test.

Interim results from the highly regarded MASAI randomized controlled trial of 80,000 women in Sweden found that cancer detection rates were 20% higher in women whose mammograms were read by a radiologist using AI compared with women whose mammograms were read by two radiologists without any AI intervention, which is the standard of care there.

“The MASAI trial was great, but will that generalize to the U.S.? We can’t say,” Lehman said.

In addition, there is a need for “more diverse training and testing sets for AI algorithm development and refinement” across different races and ethnicities, said Christoph Lee, director of the Northwest Screening and Cancer Outcomes Research Enterprise at the University of Washington School of Medicine. 

The long shadow of an earlier and largely unsuccessful type of computer-assisted mammography hangs over the adoption of newer AI tools. In the late 1980s and early 1990s, “computer-assisted detection” software promised to improve breast cancer detection. Then the studies started coming in, and the results were often far from encouraging. Using CAD at best provided no benefit, and at worst reduced the accuracy of radiologists’ interpretations, resulting in higher rates of recalls and biopsies.

“CAD was not that sophisticated,” said Robert Smith, senior vice president of early cancer detection science at the American Cancer Society. Artificial intelligence tools today are a whole different ballgame, he said. “You can train the algorithm to pick up things, or it learns on its own.”

Smith said he found it “troubling” that radiologists would charge for the AI analysis.

“There are too many women who can’t afford any out-of-pocket cost” for a mammogram, Smith said. “If we’re not going to increase the number of radiologists we use for mammograms, then these new AI tools are going to be very useful, and I don’t think we can defend charging women extra for them.”

KFF Health News is a national newsroom that produces in-depth journalism about health issues and is one of the core operating programs at KFF—an independent source of health policy research, polling, and journalism. Learn more about KFF.

Subscribe to KFF Health News’ free Morning Briefing.

Anthony Stumbo’s heart sank after the doctor shared his mother’s chest X-ray.

“I remember that drive home, bringing her back home, and we basically cried,” said the internal medicine physician, who had started practicing in eastern Kentucky near his childhood home shortly before his mother began feeling ill. “Nobody wants to get told they’ve got inoperable lung cancer. I cried because I knew what this meant for her.”

Now Stumbo, whose mother died the following year, in 1997, is among a group of Kentucky clinicians and researchers determined to rewrite the script for other families by promoting training and boosting awareness about early detection in the state with the highest lung cancer death rate. For the past decade, Kentucky researchers have promoted lung cancer screening, first recommended by the U.S. Preventive Services Task Force in 2013. These days the Bluegrass State screens more residents who are at high risk of developing lung cancer than any state except Massachusetts — 10.6% of eligible residents in 2022, more than double the national rate of 4.5% — according to the most recent American Lung Association analysis.

The effort has been driven by a research initiative called the Kentucky LEADS (Lung Cancer Education, Awareness, Detection, and Survivorship) Collaborative, which in 2014 launched to improve screening and prevention, to identify more tumors earlier, when survival odds are far better. The group has worked with clinicians and hospital administrators statewide to boost screening rates both in urban areas and regions far removed from academic medical centers, such as rural Appalachia. But, a decade into the program, the researchers face an ongoing challenge as they encourage more people to get tested, namely the fear and stigma that swirl around smoking and lung cancer.

Lung cancer kills more Americans than any other malignancy, and the death rates are worst in a swath of states including Kentucky and its neighbors Tennessee and West Virginia, and stretching south to Mississippi and Louisiana, according to data from the Centers for Disease Control and Prevention.

It’s a bit early to see the impact on lung cancer deaths because people may still live for years with a malignancy, LEADS researchers said. Plus, treatment improvements and other factors may also help reduce death rates along with increased screening. Still, data already shows that more cancers in Kentucky are being detected before they become advanced, and thus more difficult to treat, they said. Of total lung cancer cases statewide, the percentage of advanced cases — defined as cancers that had spread to the lymph nodes or beyond — hovered near 81% between 2000 and 2014, according to Kentucky Cancer Registry data. By 2020, that number had declined to 72%, according to the most recent data available.

“We are changing the story of families. And there is hope where there has not been hope before,” said Jennifer Knight, a LEADS principal investigator.

Older adults in their 60s and 70s can hold a particularly bleak view of their mortality odds, given what their loved ones experienced before screening became available, said Ashley Shemwell, a nurse navigator for the lung cancer screening program at Owensboro Health, a nonprofit health system that serves Kentucky and Indiana.

“A lot of them will say, ‘It doesn’t matter if I get lung cancer or not because it’s going to kill me. So I don’t want to know,’” said Shemwell. “With that generation, they saw a lot of lung cancers and a lot of deaths. And it was terrible deaths because they were stage 4 lung cancers.” But she reminds them that lung cancer is much more treatable if caught before it spreads.

The collaborative works with several partners, including the University of Kentucky, the University of Louisville, and GO2 for Lung Cancer, and has received grant funding from the Bristol Myers Squibb Foundation. Leaders have provided training and other support to 10 hospital-based screening programs, including a stipend to pay for resources such as educational materials or a nurse navigator, Knight said. In 2022, state lawmakers established a statewide lung cancer screening program based in part on the group’s work.

Jacob Sands, a lung cancer physician at Boston’s Dana-Farber Cancer Institute, credits the LEADS collaborative with encouraging patients to return for annual screening and follow-up testing for any suspicious nodules. “What the Kentucky LEADS program is doing is fantastic, and that is how you really move the needle in implementing lung screening on a larger scale,” said Sands, who isn’t affiliated with the Kentucky program and serves as a volunteer spokesperson for the American Lung Association.

In 2014, Kentucky expanded Medicaid, increasing the number of lower-income people who qualified for lung cancer screening and any related treatment. Adults 50 to 80 years old are advised to get a CT scan every year if they have accumulated at least 20 pack years and still smoke or have quit within the past 15 years, according to the latest task force recommendation, which widened the pool of eligible adults. (To calculate pack years, multiply the packs of cigarettes smoked daily by years of smoking.) The lung association offers an online quiz, called “Saved By The Scan,” to figure out likely eligibility for insurance coverage.

Half of U.S. patients aren’t diagnosed until their cancer has spread beyond the lungs and lymph nodes to elsewhere in the body. By then, the five-year survival rate is 8.2%.

But regular screening boosts those odds. When a CT scan detects lung cancer early, patients have an 81% chance of living at least 20 years, according to data published in November in the journal Radiology.

Some adults, like Lisa Ayers, didn’t realize lung cancer screening was an option. Her family doctor recommended a CT scan last year after she reported breathing difficulties. Ayers, who lives in Ohio near the Kentucky border, got screened at UK King’s Daughters, a hospital in far eastern Kentucky. The scan didn’t take much time, and she didn’t have to undress, the 57-year-old said. “It took me longer to park,” she quipped.

She was diagnosed with a lung carcinoid tumor, a type of neuroendocrine cancer that can grow in various parts of the body. Her cancer was considered too risky for surgery, Ayers said. A biopsy showed the cancer was slow-growing, and her doctors said they would monitor it closely.

Ayers, a lifelong smoker, recalled her doctor said that her type of cancer isn’t typically linked to smoking. But she quit anyway, feeling like she’d been given a second chance to avoid developing a smoking-related cancer. “It was a big wake-up call for me.”

Adults with a smoking history often report being treated poorly by medical professionals, said Jamie Studts, a health psychologist and a LEADS principal investigator, who has been involved with the research from the start. The goal is to avoid stigmatizing people and instead to build rapport, meeting them where they are that day, he said.

“If someone tells us that they’re not ready to quit smoking but they want to have lung cancer screening, awesome; we’d love to help,” Studts said. “You know what? You actually develop a relationship with an individual by accepting, ‘No.’”

Nationally, screening rates vary widely. Massachusetts reaches 11.9% of eligible residents, while California ranks last, screening just 0.7%, according to the lung association analysis.

That data likely doesn’t capture all California screenings, as it may not include CT scans done through large managed care organizations, said Raquel Arias, a Los Angeles-based associate director of state partnerships at the American Cancer Society. She cited other 2022 data for California, looking at lung cancer screening for eligible Medicare fee-for-service patients, which found a screening rate of 1%-2% in that population.

But, Arias said, the state’s effort is “nowhere near what it needs to be.”

The low smoking rate in California, along with its image as a healthy state, “seems to have come with the unintended consequence of further stigmatizing people who smoke,” said Arias, citing one of the findings from a 2022 report looking at lung cancer screening barriers. For instance, eligible patients may be reluctant to share prior smoking habits with their health provider, she said.

Meanwhile, Kentucky screening efforts progress, scan by scan.

At Appalachian Regional Healthcare, 3,071 patients were screened in 2023, compared with 372 in 2017. “We’re just scratching the surface of the potential lives that we can have an effect on,” said Stumbo, a lung cancer screening champion at the health system, which includes 14 hospitals, most located in eastern Kentucky.

The doctor hasn’t shed his own grief about what his family missed after his mother died at age 51, long before annual screening was recommended. “Knowing that my children were born, and never knowing their grandmother,” he said, “just how sad is that?”

KFF Health News is a national newsroom that produces in-depth journalism about health issues and is one of the core operating programs at KFF—an independent source of health policy research, polling, and journalism. Learn more about KFF.

Subscribe to KFF Health News’ free Morning Briefing.