The Washington Post - USA (2021-12-22)

A20 EZ RE THE WASHINGTON POST.WEDNESDAY, DECEMBER 22 , 2021

That choice is now bearing
fruit. Barzilay, 51, and a student
protege have built an AI that
seems able to predict with un-
precedented accuracy whether a
healthy person will get breast
cancer, in an innovation that
could seriously disrupt how we
think about the disease.
As she and her team laid out in
an article in the Journal of Clini-
cal Oncology last month and ex-
plore further in an upcoming
piece set to be published in Na-
ture Medicine, by analyzing a
mammogram’s set of byzantine
pixels and then cross-referencing
them with thousands of older
mammograms, the AI — known
as Mirai — can predict nearly half
of all incidences of breast cancer
up to five years before they hap-
pen.
It’s a marriage of tech and
health care that could alter mil-
lions of lives without a single drop
of medicine. “If the data is validat-
ed, I think this is very exciting,”
said Janine T. Katzen, a radiolo-
gist at Weill Cornell Medicine
who specializes in breast imag-
ing.
Assuming that validation hap-
pens — trials are about to begin —
Mirai could transform how mam-
mograms are used, open up a
whole new world of testing and
prevention, allow patients to
avoid aggressive treatments and
even save the lives of countless
people who get breast cancer.
(Men and nonbinary individuals
also are affected.) Mirai would
spit out risk scores for patients’
next five years, giving them a
chance to make health-care
choices that earlier generations
could only dream of.
The AI has an oracular quality:
The designers themselves don’t
understand how it works. They’re
just certain that it does.
That fact raises many broader
social and moral implications.
But there’s also a more practical
matter — whether the medical
establishment and insurance
companies will at all embrace
this.

Training Mirai

Any family that has been affect-
ed by breast cancer knows the
trajectory: A person is feeling
perfectly fine when a mammo-
gram or self-examination turns
up a troubling sign, jolting every-
thing to a stop. An MRI or biopsy
then confirms the suspicion.
Suddenly rushing in are fears
about the future, flurries of doc-
tor appointments assessing the
threat and many months of debil-
itating treatments and surgery.
Even in cases with a “successful”
outcome, physical and psycholog-
ical aftereffects — along with par-
alyzing fears of recurrence — can
last years.
Through it all, a question
gnaws: How could a body betray
us without offering up so much as
a warning message?
Barzilay asked another ques-
tion: What if it does and we just
haven’t built the tools to hear it?
The system most often trying
to listen has been Tyrer-Cuzick, a
statistical model into which doc-
tors input a list of basic variables
such as a person’s age and family
history. It usually predicts breast
cancer in just 20 to 25 percent of
people who go on to be diagnosed
with it.
MIT researchers took a differ-
ent tack. The team — Barzilay; the
student, Adam Yala; and Connie
Lehman, a Mass General doctor
Barzilay met through her oncolo-
gist — gathered more than
200,000 Mass General mammo-
grams of people who would and
would not go on to develop can-
cer. They fed them into Mirai to
train its algorithm. Mirai would
scan mammograms and make a
prediction, drawing from all it
had analyzed.
Then it would be told the actual
result and be “penalized” or “re-
warded” (via the mathematical
adjustment of the model) based
on the deviation from the reality.
It quickly learned what future
breast cancer did and did not look
like in the mammogram dots.
Once Mirai was trained, team
members embarked on a study.
They collected 129,000 mammo-
grams taken from 2008 to 2016,
spanning 62,000 patients in sev-
en hospitals in five places — Swe-
den, Israel, Ta iwan, Brazil and the
United States — and asked Mirai
to make its predictions. Anything
above a cumulative five-year risk
score of 2.5 percent was deemed
high, and the AI would then auto-
matically recommend further
testing such as a biopsy or MRI.
How well, the team wondered,
could Mirai predict which mam-
mogram belonged to a person
who developed cancer over a five-
year period?
The AI was correct in an aver-
age of about 76 out of 100 cases, an
improvement of 22 percent over
Tyrer-Cuzick, translating to mil-
lions of women in the real world.
Mirai’s “sensitivity”— the rate
at which it correctly foretold can-
cer in all those who would go o n to
be diagnosed with it — was about
44 percent, nearly double Tyrer-
Cuzick’s 20 to 25 percent. (The

MAMMOGRAM FROM A

study did not distinguish be-

tween more and less aggressive

forms of cancer.)

“This is the next, very positive

step forward,” Dorraya El-Ashry,

chief scientific officer for the

Breast Cancer Research Founda-

tion, said in an interview. “There

is a lot of work to do. But it is very

encouraging.”

The foundation provided fund-

ing for Barzilay’s research, as did

MIT’s Jameel Clinic and the Brit-

ish nonprofit Wellcome Trust.

Barzilay and Yala early on decided

to make the technology open-

source so any hospital could use

it; there are no patents on Mirai.

“It was never a question,” Bar-

zilay said. “This should be for

everyone to build on.”

A different tack

The mammogram is a little bit

like Winston Churchill’s democ-

racy: It’s the worst screening

method, except for all the others.

The approach — which uses low-

grade radiation to examine breast

tissue from multiple viewing an-

gles — has become the gold stan-

dard over the past several dec-

ades, and many medical profes-

sionals swear by it as an uncom-

fortable but important safeguard.

It also has drawn its share of

critics in the oncology and wom-

en’s health communities who say

it has led to unnecessary radia-

tion exposure, overtesting, false

positives and all the stress that

comes with them.

Barzilay and her team say that

the problem lies not in the mam-

mogram but in how it is being

used. Right now, human radiolo-

gists — able to see only so much —

focus on factors such as breast

density, a notoriously unreliable

marker because dense breasts are

common in many healthy wom-

en, too.

The researchers say the ma-

chine can see a lot more. “The

mammogram is such a rich

source of information. I just don’t

believe it’s been mined for all its

potential,” Yala said, noting it

could get even better with the

advent of the burgeoning “3-D

mammogram,” a process known

as tomosynthesis.

Lehman says it is not the tool

but the approach that has been

the issue. “We don’t need to do

age-based screenings — we can do

risk-based screenings,” she said.

The overall number of mammo-

grams probably would be the

same, but instead of all women

ing center and head of that cen-

ter’s artificial-intelligence divi-

sion, s aid s he i s bullish about how

it can transform preventive care.

But she also noted many tricky

issues that have yet to be worked

out. “Here’s t he scenario I’m inter-

ested in,” she said. “If Tyrer-Cuz-

ick says a person is high-risk and

Mirai says they’re not, who should

they listen to?” After all, if the AI

is wrong, it could create the optics

that a machine hurt a human.

Much like self-driving cars,

Barzilay and Lehman say, the ma-

chine does not have to eliminate

error in every single case. It sim-

ply has to be marginally better

than humans in the total number

of cases.

There is also the black-box

question. Many scientific enter-

prises at least allow researchers

to know, eventually, how it rough-

ly works. But Mirai presents the

possibility that millions of wom-

en will be told what to do about

their health for reasons no one

understands.

“We don’t really know exactly

how aspirin works, yet we use it

all the time,” Yala said. He noted

that amorphous recommenda-

tion engines are in wide use for

everything from shopping to

streaming. “But when it comes to

medicine, where we need it most,

we insist on humans.”

Advocacy groups say they are

unconcerned about the black-box

issue. “Knowledge is power, wher-

ever the knowledge is coming

from,” said Elana Silber, executive

director of Sharsheret, a group

focusing on Jewish women affect-

ed by breast cancer. “If people can

understand their risk better, they

can take measures to protect their

health and save lives.”

The research has also earned

the cautious endorsement of

large-scale medical groups. Rob-

ert Smith, senior vice president

for cancer screening at t he Ameri-

can Cancer Society, said that he

sees Mirai as a “very good thing”

and that it “does appear to offer

advantages,” though he said that

“we need to move forward care-

fully.”

Many radiologists in the field

are enthusiastic too. Katerina

Dodelzon, Katzen’s colleague at

Weill Cornell, noted the technol-

ogy’s ability to take radiology

“from diagnostic to prognostic”

functions.

The same optimism may not

yet have taken hold with breast

cancer surgeons or oncologists,

who most directly advise patients

on breast cancer risk. Requests

for comment to such doctors at

four high-level hospitals were de-

clined, and one hospital staffer

described an ambivalence among

that group. Mathematical models

are common in cancer treatments

such as chemotherapy dosages,

but that is more familiar to physi-

cians than outsourcing a progno-

sis to a computer.

Even some radiologists are

conflicted, fearing automation

could take their jobs. Some more-

traditional detection-related

technologies — machines meant

to identify cancers already pre-

sent — are in various stages of

research or deployment by

Google, the Dutch start-up

ScreenPoint and the British com-

pany Kheiron Medical. Those ef-

forts have caused some conster-

nation in the radiology communi-

ty.

While emphasizing that these

technologies are meant merely as

a tool for the human reader, Tobi-

as Rijken, chief technological offi-

cer and co-founder of Kheiron

Medical, also pointed to a ma-

chine’s comparative advantage in

the life-or-death effort of breast

cancer imaging. “A n AI works

24/7, it doesn’t get tired, and it

doesn’t have personal problems

at home,” he said.

Real-world rollout

Among the sites for the

planned Mirai trials are the Mexi-

can hospital network Grupo An-

geles and Novant Health, the

sprawling southeastern U.S.

health-care system. Novant aims

to roll out the trials in the coming

months at its flagship hospital in

Winston-Salem, N.C., where as

many as 150,000 patients who

come in for mammograms will be

given risk scores produced by

Mirai.

The hurdles will arrive with

them.

In most cases, insurance com-

panies pay for mammograms

only for people over 40, and there

has even been a push by some U.S.

companies in recent years to raise

the age to 45 or even 50. Upending

the system to pay for mammo-

grams for women in their 30s will

not be easy. Many a lso will not pay

for a breast MRI recommended

by an AI.

“It’s the biggest challenge we

have: Will insurance pay?” said

Bipin Karunakaran, vice presi-

dent of clinical insights and ana-

lytics at Novant. Grant money

might help subsidize costs in the

trial, but that isn’t a long-term

solution.

Barzilay and Yala said that add-

ing mammograms for some

younger higher-risk people will

actually lower costs for insurers

by helping avert expensive treat-

ments down the road. But they

acknowledged that persuading

them of this will take time.

Patient adoption is also an

open question. Some see a gener-

ational split, with younger people

embracing an algorithm while

older ones resist. “One of the big

questions we get from patients

over a certain age, and I certainly

understand it, is whether a ma-

chine can care about them in the

same way,” Lehman said.

Of course, thanks precisely to a

history of age-based guidelines,

younger people tend to get fewer

mammograms in the first place.

“I don’t want to be pessimistic

about this, because the idea that

we can more accurately predict

five years of risk is really promis-

ing, even revolutionary,” said

Kate Lampen-Sachar, a radiolo-

gist at the Miami Cancer Insti-

tute’s Baptist Health Breast Cen-

ter and an adviser to the Young

Survival Coalition, an advocacy

group for women diagnosed with

breast cancer under age 40 — a

group that has seen rates rise in

recent years.

“But I think it remains to be

seen how easily this could be

implemented,” she said. “Because

in the end, it still requires a mam-

mogram be performed. And that

isn’t simple for people under 40.”

There are also regulatory chal-

lenges. The Food and Drug Ad-

ministration requires that any

new tool in a hospital that has not

been approved go t hrough a strict

internal review process, which

means many upcoming on-the-

ground battles for Mirai to prove

it can do more good than harm.

Barzilay said she has no choice

but to press on.

“Not long after I turned 40 —

about three years before I was

diagnosed — I went for my first

mammogram,” she said. “They

told me everything was fine and

there was nothing to worry about.

Would Mirai have noticed what-

ever was happening inside me?

Would it have sent me for more

screening and told me to watch

more closely? Would it have al-

lowed me to catch the cancer

much sooner and avoid all that

treatment? There are women who

will be diagnosed with breast can-

cer in three years. I feel a respon-

sibility to give them Mirai now.”

Just out of a sense of dark

curiosity, she recently fed that

initial mammogram into Mirai. It

told her she was high-risk.

[email protected]

over 40 getting them annually,

some women under 40 who are at

higher risk would get them, while

low-risk people over 40 would get

them less often.

The Mirai team also hopes the

AI will better represent women of

color.

“When you start seeing the

data about racial bias in tradi-

tional risk models, it’s chilling,”

Lehman said. “A nd the reason is

because they mainly take into

account European Caucasian

women and not Hispanic, Asian

and Black women. I’ve seen with

my own eyes how racially biased

traditional risk scores are.”

Many w orry that AI might inte-

grate similar biases, because,

well, it’s being programmed by

the same people who design the

math models. But Yala said the

results of the study did not show

bias; the rates of cancer it found

among its many subjects in Asia,

South America and the Middle

East, and in hospitals with a sig-

nificant number of Black patients

in the United States, were consis-

tent with actual real-world rates.

Breast cancer affects some eth-

nic and racial groups dispropor-

tionately. Black women are

40 percent more likely to die of

breast cancer than White women.

Ashkenazi Jewish women are 10

times as likely as other groups to

have gene mutations associated

with breast cancer.

The breast cancer statistics are

alarming across the board. One in

8 American women will be strick-

en with the disease at some point

during their lifetimes. While

many cancers, such as lung can-

cer, have been declining in the

United States, breast cancer rates

have been going up — an annual

average of half a percentage point

between 2008 and 2017, accord-

ing to the American Cancer Soci-

ety.

When Barzilay was first start-

ing her research, most hospitals

turned her away, saying breast

cancer had been treated for years

without AI.

“I felt like I had something

really important to give,” said

Barzilay, who has what might be

described as an affable indomita-

bility, a boundary-pushing re-

searcher crossed with Gal Gadot.

“A nd they acted like I was trying

to sell snow to an Eskimo.” So she

enlisted Yala, at the time still an

undergrad, who set out on the

laborious door-to-door task of

wheedling for access to anony-

mous mammograms.

A small breakthrough came

when Barzilay was introduced to

Lehman, allowing them to get

hold of Mass General’s files. The

two women soon became a well-

known brand in cutting-edge

breast cancer circles — “Regina

and Connie,” a kind of single

phrase indicating a complemen-

tary duo.

Barzilay and Yala are both from

places far removed from Massa-

chusetts’s medical community,

which may be key to their disrup-

tive mind-set. Barzilay was raised

in Moldova and immigrated to

Israel at 20 after the fall of the

Iron Curtain — she was picking

almonds on a kibbutz when most

Americans her age were on spring

break — before coming to the

United States nearly a decade

later. Even her first name — pro-

nounced with a hard “g,” as in

“regulate” — has a kind of edgy

contrarianism.

Yala, meanwhile, was born in

Algeria and arrived as a 10-year-

old in the suburbs of Chicago

after his parents fled political

instability at home.

“I guess coming from some-

where far away made me not

accept the status quo way of doing

things,” the 26-year-old said. “A nd

it definitely helped me go around

the world begging hospitals for

mammograms.”

Trust issues

The ethical implications for

Mirai are significant.

Sarah Eskreis-Winkler, a radi-

ologist at Memorial Sloan Ketter-

ing Cancer Center’s breast imag-

A mammogram

breakthrough, but

obstacles abound

SOPHIE PARK FOR THE WASHINGTON POST

Artificial-intelligence researcher Regina Barzilay and her student Adam Yala last week at MIT in Cambridge, Mass. They have

built an AI program that seems able to predict with unprecedented accuracy whether a healthy person will get breast cancer.