20 Time March 2–9, 2020
Seeking ouT help for depreSSion iS
hard enough. It doesn’t make things any
easier that it can take weeks, months or
longer of trying different treatments to find
something that works. Anti depressants can
take at least four weeks to start working,
and research has shown that only about 30%
of patients respond well to the first drug
they’re prescribed. “Right now, treatment
selection is purely based on trial and error,”
says Dr. Madhukar Trivedi, a professor
at the University of Texas Southwestern
Medical Center.
But promising new research published in
February in Nature Biotechnology suggests
that a simple brain test, paired with artifi-
cial intelligence (AI), can help. Trivedi and a
team of researchers took data from a previous
study in which more than 200 people with
depression had an electroencephalogram
(EEG)—a non invasive test that records brain
waves—and were then given either sertraline
(a widely prescribed anti depressant mar-
keted as Zoloft) or a placebo for eight weeks.
They then created a machine- learning algo-
rithm to analyze the EEG data, which found
that 65% of study participants who shared a
particular brain-wave signature also showed
a strong response to sertraline. This, says
Dr. Amit Etkin, one of the paper’s authors and
a professor at Stanford University, is “far bet-
ter” than using clinical factors to try to guess
whether they will respond well to a drug.
The researchers also applied the AI algo-
rithm to data from a separate study in which
people had EEG testing before undergoing
transcranial magnetic stimulation (TMS), a
brain- stimulation technique to treat depres-
sion. They found that people who were not
expected to respond well to sertraline, based
on their brain waves, tended to have positive
responses to TMS.
Though this research is still preliminary,
“these are exciting results,” says Michele
Ferrante, the computational- psychiatry pro-
gram director at the National Institute of
Mental Health, which funded the research.
“This EEG lab test is quick”—it takes just a
few minutes—“cost-effective, and its out-
come is of high clinical impact.” The next
step is to conduct clinical trials in which AI
suggests a treatment based on the patient’s
EEG patterns “to see if these results hold
true.” Etkin believes that in five years, his
team’s prediction tool will be in clinical use.
As a personalized approach to depression
emerges, thanks to AI, Trivedi hopes people
will be more inclined to seek and stick with
treatment. “It gives patients a lot more con-
fidence in the treatments that they are being
provided,” he says. “That improves their abil-
ity to stay with that treatment until they get
better. We are not shooting in the dark.” □Your brain knows
the meds you need
By Mandy Oaklander
TheBrief Health
SLEEP
Don’t believe
everything
you’ve
heard about
blue light
Conventional wisdom
says exposure to blue
light—the type emitted
by electronic- device
screens—is bad
for sleep because
it messes with
circadian rhythms.
But in December,
researchers reported
in Current Biology that
yellow light actually
disturbed sleep more
than blue light in mice.
While animal studies
often do not translate
directly to human
behavior, the research
brought awareness
to an argument that
sleep experts have
been quietly making
for years.
“Blue light has
become the gluten of
the sleep world,” says
Dr. Cathy Goldstein, a
sleep specialist at Mich-
igan Medicine. That is, it
may be a potential trig-
ger for health issues,
but its impact has been
blown way out of propor-
tion. Spectrum of light
isn’t all that matters:
“You can’t have your
blue-light filter on, and
then have your phone or
your tablet at maximal
brightness,” and expect
to drift right off with
no problem, Goldstein
says. Blue-light-blocking
filters on electronics
may be helpful, but only
if you also turn down the
brightness and avoid
hours of aimless scroll-
ing, she adds.
—Jamie Ducharme