Fortune - USA (2020-04)

24 FORTUNE APRIL 2020

search keyword data to the

location of people clicking

on Wikipedia pages.

Much of the data comes

from the world’s larg-

est Internet companies,

including Google, which

supplies search keyword

and location data to some

pandemic- detection start-

ups. Meanwhile, Facebook

has shared aggregated data

about users’ movements

as well as posts mention-

ing the coronavirus from

Facebook Groups and

Instagram. Anon ymized

data from Twitter, China’s

Tencent, and others also

fuels the algorithms, which

typically run not on the

monitoring firms’ own

computers but on serv-

ers managed by Amazon,

Microsoft, and Google

that use chips specifically

designed for A.I.

To be sure, pumping

huge amounts of informa-

tion into A.I. and machine-

learning systems is no

guarantee of success. For

example, Google shuttered

a project that forecast the

severity of seasonal flu

outbreaks after it wildly

overestimated the 2013

cycle. One problem was

that Google’s own efforts

to help people search for

health care information

fooled the system into fore-

casting that more people

were getting sick.

The challenge for

companies developing

pandemic-detection sys-

tems is to ensure that they

focus only on relevant bits

of information, without

getting misled by hysteria

that’s unrelated to actual

illnesses. That’s why all of

the systems still rely on

importation risk on Jan. 14

were actually the first four

that ended up receiving

cases,” he says.

Another approach is to

eschew all the online chat-

ter and news reports and

instead use actual medi-

cal data. San Francisco

startup Kinsa sells smart

thermometers that work

with an app to help people

decide when to see a doc-

tor. With about 1 million

households and more than

1,000 schools using Kinsa

gear, those thermometers

provide clues about the

spread of the seasonal flu

in the U.S. The eight-year-

old company claims to

have exceeded the accuracy

of the Centers for Disease

Control’s flu forecast for

some years and hopes

to develop a system that

could predict flu outbreaks

in local areas up to three

months in advance.

“The difference is the

quality of the data,” Kinsa

CEO Inder Singh explains.

Of course, the Kinsa

method works only where

people use its devices. In

the U.S., that means most

cities but not so much

in rural areas. And the

company has yet to expand

to other countries, where

even a $20 smart ther-

mometer may be too pricey

for most people.

Ultimately, though,

more medical devices

reporting directly to A.I.

systems could make for the

quickest and most accurate

early-warning system,

says Metabiota’s Gallivan:

“For earlier detection, it’s

about creating a much

smarter public health and

medical system.”

humans to look deeper

into each case and why

they frequently adjust the

sources of information that

their technology relies on.

“You have to recognize that

data is constantly chang-

ing based on what people

are doing online and

always have to retune your

algorithms for that,” says

John Brownstein, chief in-

novation officer at Boston

Children’s Hospital and

cocreator of another A.I.

alert system, HealthMap,

which warned about the

coronavirus a day before

BlueDot.

HealthMap’s A.I.-gen-

erated warning about the

coronavirus was backed up

by intel from local physi-

cians in Wuhan who were

sharing their concerns in

an online forum called

ProMed. Such posts are

the “early canaries in a coal

mine that can provide data

pointing to do a deeper

dive,” Brownstein says.

Using fresh data is also

important. Initial simula-

tions of how the corona-

virus may spread relied on

past air travel itineraries.

But once the outbreak

became known and

governments began ban-

ning movement in certain

regions of China, travel

patterns changed, notes

Mark Gallivan, director of

data science at Metabiota,

another startup using A.I.

to detect pandemics. As

a result, the San Fran-

cisco company updated its

library of historical passen-

ger information with real-

time location data from

millions of mobile phones.

“The first four countries

that showed the highest

THE BRIEF — DIGITAL HEALTH

T H E DATA

FUELING A.I.

PA N D E M I C

PREDICTIONS

Smart, connected

medical devices

Millions of patients

are treated with ther-

mometers and other

devices that send

data to an app. The

aggregate informa-

tion can provide early

warning of a cluster

of patients with fever,

for example.

Search keywords and

locations

The questions people

want answered at a

particular time and

place can signal an

outbreak. But the

data must be filtered

carefully, as search

queries can reflect

hysteria as much as

a real epidemic.

Local news articles

Reporters on the

ground often write

stories about unusual

medical problems

or virus outbreaks.

The articles can be

translated and ana-

lyzed using natural-

language processing.

Air travel patterns

Airlines generate

about 4 billion travel

itineraries annually.

That historical data

can be used to predict

how an outbreak may

spread to other cities

based on the most

popular destinations

from the source city.

DIG.W.0420.XMIT.indd 24 FINAL 3/9/2020 2:54:24 PM