WEBVTT

00:00:01.560 --> 00:00:04.416
We live in a medication nation.

00:00:04.440 --> 00:00:09.496
Four point five billion drug prescriptions
will be prescribed by doctors like me

00:00:09.520 --> 00:00:11.336
this year, in the United States alone.

00:00:11.360 --> 00:00:13.776
That's 15 for every man, woman and child.

00:00:13.800 --> 00:00:15.016
And for most of us,

00:00:15.040 --> 00:00:18.576
our experience with this medication
is often confusing number of pills,

00:00:18.600 --> 00:00:22.216
instructions, side effects,
one-size-fits-all dosing,

00:00:22.240 --> 00:00:24.696
which all too often
we aren't taking as prescribed.

00:00:24.720 --> 00:00:26.736
And this comes at tremendous expense,

00:00:26.760 --> 00:00:29.656
costing us our time,
our money and our health.

00:00:29.680 --> 00:00:32.576
And in our now exponential,
connected, data-driven age,

NOTE Paragraph

00:00:32.600 --> 00:00:35.080
I think we can and we must do better.

00:00:35.880 --> 00:00:39.016
So let's take a dive
at some of the challenges we have

00:00:39.040 --> 00:00:42.096
and some potential solutions.

00:00:42.120 --> 00:00:43.376
Let's start with the fact

00:00:43.400 --> 00:00:46.656
that many drugs don't work
for those who are prescribed to them.

00:00:46.680 --> 00:00:51.296
The top 10 grossing drugs
in the United States this year,

00:00:51.320 --> 00:00:54.936
they only benefit one in four
to one in 23 of who take them.

00:00:54.960 --> 00:00:58.976
That's great if you're number one,
but what about everybody else?

00:00:59.000 --> 00:01:02.056
And what's worse, drugs,
when they sometimes don't work,

00:01:02.080 --> 00:01:03.496
can still cause side effects.

NOTE Paragraph

00:01:03.520 --> 00:01:05.416
Take aspirin -- about one in four of us

00:01:05.440 --> 00:01:08.376
who take aspirin to reduce
our risk of cardiovascular disease,

00:01:08.400 --> 00:01:10.376
are unknowingly aspirin-resistant.

00:01:10.400 --> 00:01:13.376
And still have the same risks
of gastrointestinal bleeds

00:01:13.400 --> 00:01:15.160
that kill thousands every year.

00:01:16.040 --> 00:01:19.016
It's adverse drug reactions like these

00:01:19.040 --> 00:01:22.216
that are, by some estimates,
the number four leading cause of death

00:01:22.240 --> 00:01:23.456
in the United States.

00:01:23.480 --> 00:01:24.936
My own grandfather passed away

00:01:24.960 --> 00:01:27.976
after a single dose of antibiotic
caused his kidneys to fail.

00:01:28.000 --> 00:01:30.976
Now, adverse drug reactions
and side effects

00:01:31.000 --> 00:01:34.016
are often tied to challenges in dosing.

NOTE Paragraph

00:01:34.040 --> 00:01:37.776
I trained in pediatrics -- little people,
internal medicine -- big people,

00:01:37.800 --> 00:01:40.216
so one night I might have been
on call in the NICU,

00:01:40.240 --> 00:01:42.496
carefully dosing
to the fraction of a milligram,

00:01:42.520 --> 00:01:43.936
a medication for a NICU baby.

00:01:43.960 --> 00:01:46.216
The next night --
on call in the emergency room,

00:01:46.240 --> 00:01:49.776
treating a 400-pound lineman
or a frail nursing-home patient,

00:01:49.800 --> 00:01:53.696
who, by most accounts, usually
would get the same dose of medications

00:01:53.720 --> 00:01:55.016
from the formulary.

00:01:55.040 --> 00:01:58.376
Which would mean, most of the time
I would be underdosing the lineman,

00:01:58.400 --> 00:02:01.416
and overdosing the nursing-home patient.

00:02:01.440 --> 00:02:02.816
And beyond age and weight,

00:02:02.840 --> 00:02:05.800
we tend to ignore differences
in sex and race in dosing.

NOTE Paragraph

00:02:06.680 --> 00:02:10.856
Now, beyond this, we know
we have a massive challenge

00:02:10.880 --> 00:02:13.096
with noncompliance or low adherence.

00:02:13.120 --> 00:02:15.216
Many of us who need
to take our medications

00:02:15.240 --> 00:02:18.056
aren't taking them
or are taking them incorrectly.

00:02:18.080 --> 00:02:20.776
You know, 40 percent
of adults in the US over 65

00:02:20.800 --> 00:02:23.256
are on five or more
prescription medications.

00:02:23.280 --> 00:02:24.616
Sometimes 15 or more.

00:02:24.640 --> 00:02:30.120
And even small improvements in adherence
can dramatically save dollars and lives.

NOTE Paragraph

00:02:31.440 --> 00:02:34.496
So, as we think into the future,

00:02:34.520 --> 00:02:36.296
you think that where we are today,

00:02:36.320 --> 00:02:40.296
as we often hear about smart,
personalized, targeted drugs,

00:02:40.320 --> 00:02:42.216
Internet of Things, gene therapy, AI,

00:02:42.240 --> 00:02:45.056
that we'd already arrived
in this era of precision medicine.

00:02:45.080 --> 00:02:46.776
In reality, we still live in an age

00:02:46.800 --> 00:02:49.776
of empiric, trial-and-error
imprecision medicine.

00:02:49.800 --> 00:02:51.096
I think we can do better.

00:02:51.120 --> 00:02:55.496
What if we could reimagine ways
to help make your medicine-taking easier?

00:02:55.520 --> 00:02:59.136
To get the right doses
and combinations to match you?

00:02:59.160 --> 00:03:01.856
What if we could move beyond
today's literal cutting edge

00:03:01.880 --> 00:03:04.656
of pill cutters and fax machines,

00:03:04.680 --> 00:03:07.496
to an era where we could have
better outcomes, lower costs,

00:03:07.520 --> 00:03:10.520
saving lives and space
in your medicine cabinet?

NOTE Paragraph

00:03:11.440 --> 00:03:14.256
Well, I think part of the solution
is all the emerging ways

00:03:14.280 --> 00:03:17.776
that we can measure and connect
our health care information.

00:03:17.800 --> 00:03:20.856
Today, we pretty much live
in a reactive, sick-care world,

00:03:20.880 --> 00:03:23.136
siloed information that doesn't flow.

00:03:23.160 --> 00:03:26.136
We have the potential to move
into more continuous, real-time

00:03:26.160 --> 00:03:28.416
proactive world of true health care.

00:03:28.440 --> 00:03:31.616
And part of that starts with
the emerging world of quantified self,

00:03:31.640 --> 00:03:34.896
we can measure so much
of our physiology and behaviors today,

00:03:34.920 --> 00:03:37.136
and often it's siloed
on our phones and scales,

00:03:37.160 --> 00:03:40.136
but it's starting to connect
to our clinicians, our caregivers,

00:03:40.160 --> 00:03:43.360
so they can better optimize prevention,
diagnostics and therapy.

00:03:44.840 --> 00:03:47.736
And when we can do that,
we can do some interesting things.

NOTE Paragraph

00:03:47.760 --> 00:03:49.816
Take, for example, hypertension.

00:03:49.840 --> 00:03:53.656
It's the number one risk factor
for early death and morbidity worldwide.

00:03:53.680 --> 00:03:56.976
Half of adult Americans,
on approximation, have hypertension,

00:03:57.000 --> 00:03:59.016
less than half have it well-controlled.

00:03:59.040 --> 00:04:02.517
It's often because it takes two
or three different classes of medications,

00:04:02.541 --> 00:04:05.856
it's tough to do adherence and adjust
your blood pressure medications.

00:04:05.880 --> 00:04:08.856
We have 500 preventable deaths
from noncontrolled hypertension

00:04:08.880 --> 00:04:10.896
in the US, every day.

00:04:10.920 --> 00:04:13.778
But now we're in the era
of connected blood pressure cuffs --

00:04:13.802 --> 00:04:15.856
the FDA just approved
a blood pressure cuff

00:04:15.880 --> 00:04:17.536
that can go into your watch.

00:04:17.560 --> 00:04:21.055
There are now prototypes of cuffless
radar-based blood pressure devices

00:04:21.079 --> 00:04:23.736
that can continuously stream
your blood pressure.

00:04:23.760 --> 00:04:25.216
So, in the future, I could --

00:04:25.240 --> 00:04:27.907
instead of spot-checking
my blood pressure in the clinic,

00:04:27.931 --> 00:04:30.507
my doctor could see
my real-time numbers and my trends,

00:04:30.531 --> 00:04:32.696
and adjust them as necessary,

00:04:32.720 --> 00:04:35.136
with the help of a blood pressure
dosing algorithm,

00:04:35.160 --> 00:04:37.496
or using the Internet of Things.

NOTE Paragraph

00:04:37.520 --> 00:04:40.896
Now, technology today can do even more.

00:04:40.920 --> 00:04:43.296
My smartwatch, already today,
has an EKG built in,

00:04:43.320 --> 00:04:46.656
that can be read
by artificial intelligence.

00:04:46.680 --> 00:04:49.616
I'm wearing a small, Band-Aid-sized patch,

00:04:49.640 --> 00:04:51.896
that is live-streaming
my vital signs right now.

00:04:51.920 --> 00:04:53.136
Let's take a look.

00:04:53.160 --> 00:04:55.576
They're actually a little
concerning at the moment.

NOTE Paragraph

00:04:55.600 --> 00:04:57.896
(Laughter)

NOTE Paragraph

00:04:57.920 --> 00:05:00.336
Now, it's not just my real-time vitals

00:05:00.360 --> 00:05:02.536
that can be seen
by my medical team or myself,

00:05:02.560 --> 00:05:04.256
it could be my retrospective data,

00:05:04.280 --> 00:05:08.256
and again, that'd be used to modify
dosing and medication going forward.

00:05:08.280 --> 00:05:10.696
Even my weight can be super-quantified.

00:05:10.720 --> 00:05:15.616
My weight, now my shape,
how much body mass, fat,

00:05:15.640 --> 00:05:16.896
muscle mass I might have,

00:05:16.920 --> 00:05:19.880
and use that to optimize
my prevention or therapy.

00:05:20.800 --> 00:05:22.616
And it's not just for the tech-savvy.

00:05:22.640 --> 00:05:25.776
Now, MIT engineers have modified wi-fi

00:05:25.800 --> 00:05:29.256
so we can seamlessly
connect and collect our vital signs,

00:05:29.280 --> 00:05:31.536
from our connected rings
and smart mattresses,

00:05:31.560 --> 00:05:34.256
we can start to share
this digital exhaust, our digitome,

00:05:34.280 --> 00:05:37.496
and even potentially crowdsource it,
sharing our health information,

00:05:37.520 --> 00:05:39.976
just like we share
with our Google Maps and driving,

00:05:40.000 --> 00:05:43.720
to improve our -- not our driving,
but our health experience globally.

NOTE Paragraph

00:05:44.880 --> 00:05:46.296
So, that's great.

00:05:46.320 --> 00:05:48.616
We can potentially now
collect this information.

00:05:48.640 --> 00:05:52.416
What if your labs
can go from the central lab

00:05:52.440 --> 00:05:54.976
to your home, to your phone,
to even inside our bodies

00:05:55.000 --> 00:05:58.016
to measure drug levels or other varieties?

00:05:58.040 --> 00:06:00.136
And of course,
we're in the age of genomics.

00:06:00.160 --> 00:06:03.056
I've been sequenced,
it's just less than 1,000 dollars today.

00:06:03.080 --> 00:06:05.536
And I can start to understand
my pharmacogenomics --

00:06:05.560 --> 00:06:08.176
how my genes impact
whether I need high dose, low dose,

00:06:08.200 --> 00:06:10.256
or maybe a different
medication altogether.

00:06:10.280 --> 00:06:13.056
Let's imagine if your physician
or your pharmacist,

00:06:13.080 --> 00:06:15.736
had this information
integrated into their workflow,

00:06:15.760 --> 00:06:19.616
augmented with artificial intelligence,
AI, or as I like to refer to it, IA --

00:06:19.640 --> 00:06:21.216
intelligence augmentation,

00:06:21.240 --> 00:06:22.656
to leverage that information,

00:06:22.680 --> 00:06:25.256
to understand of the 18,000
or more approved drugs,

00:06:25.280 --> 00:06:28.616
which would be the right dose
and combination for you.

NOTE Paragraph

00:06:28.640 --> 00:06:31.656
So great, now maybe we can
optimize your drugs and your doses,

00:06:31.680 --> 00:06:34.823
but the problem today is,
we're still using this amazing technology

00:06:34.847 --> 00:06:36.736
to keep track of our drugs.

00:06:36.760 --> 00:06:39.336
And of course, these technologies evolve,

00:06:39.360 --> 00:06:42.496
there's connected dispensers,
reminder apps,

00:06:42.520 --> 00:06:45.536
smart pill bottle caps that can text
or tweet you or your mother

00:06:45.560 --> 00:06:47.416
if you haven't taken your medications.

00:06:47.440 --> 00:06:49.256
PillPack was just acquired by Amazon,

00:06:49.280 --> 00:06:53.776
so soon we may have same-day delivery
of our drugs, delivered by drone.

00:06:53.800 --> 00:06:55.976
So, all these things are possible today,

00:06:56.000 --> 00:06:57.896
but we're still taking multiple pills.

00:06:57.920 --> 00:06:59.416
What if we can make it simpler?

NOTE Paragraph

00:06:59.440 --> 00:07:02.616
I think one of the solutions
is to make better use of the polypill.

00:07:02.640 --> 00:07:06.096
A polypill is the integration of multiple
medications into a single pill.

00:07:06.120 --> 00:07:09.616
And we have these today in common,
over-the-counter cold and flu remedies.

00:07:09.640 --> 00:07:12.136
And there have been
prevention polypill studies done,

00:07:12.160 --> 00:07:14.816
giving combinations
of statins, blood pressure, aspirin,

00:07:14.840 --> 00:07:16.896
which in randomized studies
have been shown

00:07:16.920 --> 00:07:19.256
to dramatically reduce risk,
compared to placebo.

00:07:19.280 --> 00:07:23.216
But these polypills weren't personalized,
they weren't optimized to the individual.

00:07:23.240 --> 00:07:25.736
What if we could optimize
your personalized polypill?

00:07:25.760 --> 00:07:29.096
So it would be built for you,
based on you, it could adapt to you,

00:07:29.120 --> 00:07:30.896
even every single day.

00:07:30.920 --> 00:07:34.856
Well, we're now in the era of 3D printing,
you can print personalized braces,

00:07:34.880 --> 00:07:36.496
hearing aids, orthopedic devices,

00:07:36.520 --> 00:07:39.976
even I've been scanned
and had my jeans tailored to fit to me.

NOTE Paragraph

00:07:40.000 --> 00:07:41.296
So this got me thinking,

00:07:41.320 --> 00:07:44.816
what if we could 3D print
your personalized polypill?

00:07:44.840 --> 00:07:47.216
So instead of taking
six medications, for example,

00:07:47.240 --> 00:07:48.936
I could integrate them into one.

00:07:48.960 --> 00:07:51.296
So it would be easier to take,
improve adherence

00:07:51.320 --> 00:07:53.940
and potentially, it could even
integrate in supplements,

00:07:53.964 --> 00:07:57.136
like vitamin D or CoQ10.

00:07:57.160 --> 00:08:00.136
So with some help --
I call these "IntelliMeds" --

00:08:00.160 --> 00:08:02.856
and with the help of my
IntelliMedicine engineering team,

00:08:02.880 --> 00:08:05.896
we built the first
IntelliMedicine prototype printer.

NOTE Paragraph

00:08:05.920 --> 00:08:07.136
And here's how it works:

00:08:07.160 --> 00:08:09.536
instead of full tablets,
we have small micromeds,

00:08:09.560 --> 00:08:11.016
one or two milligrams each,

00:08:11.040 --> 00:08:14.056
which are sorted and selected
based on the dose and combination

00:08:14.080 --> 00:08:15.696
needed for an individual.

00:08:15.720 --> 00:08:18.176
And of course, these would be
doses and combinations

00:08:18.200 --> 00:08:20.656
you could already take together,
FDA-approved drugs.

00:08:20.680 --> 00:08:22.496
We could change the pharmacokinetics

00:08:22.520 --> 00:08:26.480
by professionally layering on different
elements to the individual micromeds.

00:08:27.560 --> 00:08:29.216
And when we hit print,

00:08:29.240 --> 00:08:32.496
you print your combination of medications
that might be needed by you

00:08:32.520 --> 00:08:34.256
on any individual day.

00:08:34.280 --> 00:08:38.176
And we'd start with, again, generic drugs
for the most common problems.

00:08:38.200 --> 00:08:41.856
About 90 percent of prescribed drugs today
are low-cost generics.

00:08:41.880 --> 00:08:45.216
And once we've printed the pill,
we can do some fun bells and whistles.

00:08:45.240 --> 00:08:47.496
We could print the name of the patient,

00:08:47.520 --> 00:08:50.056
the date, the day of the week, a QR code.

00:08:50.080 --> 00:08:54.096
We could print different meds for tapering
for a patient on a steroid taper,

00:08:54.120 --> 00:08:56.936
or tapering from pain medications.

NOTE Paragraph

00:08:56.960 --> 00:09:01.936
So, this is actually a look at our
prototype IntelliMedicine printer.

00:09:01.960 --> 00:09:03.936
See, unveil it here.

00:09:03.960 --> 00:09:06.896
It has about 16 different silos,

00:09:06.920 --> 00:09:09.520
each containing individual micromeds.

00:09:10.680 --> 00:09:14.896
And I can now adjust on the software
individual dosings.

00:09:14.920 --> 00:09:18.376
And when I do that,
the robotic arm will adjust

00:09:18.400 --> 00:09:21.496
the height of these spansules
and the micromeds will release.

00:09:21.520 --> 00:09:23.056
I can now --

00:09:23.080 --> 00:09:25.576
The automated process
would rotate and cycle through,

00:09:25.600 --> 00:09:27.456
to make sure the micromeds are loaded.

00:09:27.480 --> 00:09:29.256
And when I hit print,

00:09:29.280 --> 00:09:31.696
these will all fall through the device,

00:09:31.720 --> 00:09:35.336
I now pull out my
personalized printed polypill,

00:09:35.360 --> 00:09:39.336
with the doses
and medications meant for me.

00:09:39.360 --> 00:09:41.976
And we can take a look,
if you look back to the slides,

00:09:42.000 --> 00:09:45.976
you can see the whole process,
we can see the drug silos being selected,

00:09:46.000 --> 00:09:47.976
the pills doing down the different silos,

00:09:48.000 --> 00:09:50.816
and being collected
in the individual capsule.

NOTE Paragraph

00:09:50.840 --> 00:09:52.536
Now, this is great,

00:09:52.560 --> 00:09:54.616
I can potentially
print my meds based on me,

00:09:54.640 --> 00:09:56.016
instead of taking six pills.

00:09:56.040 --> 00:09:59.176
I can now be looking
at my individual dosing,

00:09:59.200 --> 00:10:01.376
my smartwatch is looking
at my blood pressure,

00:10:01.400 --> 00:10:03.976
I needed an adjustment
in my blood pressure medicines,

00:10:04.000 --> 00:10:06.696
my coumadin level, my blood is too thin,

00:10:06.720 --> 00:10:10.296
so I lower my micromed
dose of coumadin, a blood thinner.

00:10:10.320 --> 00:10:12.496
So, this could be
smartly adapted, day to day,

00:10:12.520 --> 00:10:15.176
programmed by my physician
or cardiologist.

00:10:15.200 --> 00:10:18.776
And you can imagine that larger printers,
fast printers like this,

00:10:18.800 --> 00:10:21.536
could be in your corner pharmacy,

00:10:21.560 --> 00:10:23.776
in your doctor's office,
in a rural clinic.

00:10:23.800 --> 00:10:27.736
But it could eventually merge and shrink
to small ones, that could be in your home,

00:10:27.760 --> 00:10:31.136
with integrated cartridges like this,
that are delivered by drone.

00:10:31.160 --> 00:10:33.216
Could print your personalized polypill,

00:10:33.240 --> 00:10:36.536
each morning on your kitchen
or your bathroom cabinet.

00:10:36.560 --> 00:10:38.376
And this could evolve, I think,

00:10:38.400 --> 00:10:42.216
into an incredible way to improve
adherence in medications across the globe.

NOTE Paragraph

00:10:42.240 --> 00:10:46.256
So, I hope we can reimagine
the future of medicine in new ways,

00:10:46.280 --> 00:10:47.816
moving from polypharmacy,

00:10:47.840 --> 00:10:51.296
one-size-fits-all,
low adherence, complications

00:10:51.320 --> 00:10:55.376
to an era of personalized,
precise, on-demand medications,

00:10:55.400 --> 00:10:58.776
that can take us
and individualize our own health

00:10:58.800 --> 00:11:01.496
and health and medicine around the planet.

NOTE Paragraph

00:11:01.520 --> 00:11:02.776
Thank you very much.

NOTE Paragraph

00:11:02.800 --> 00:11:08.320
(Applause)

NOTE Paragraph

00:11:09.880 --> 00:11:11.936
Host: Daniel, that's kind of awesome.

00:11:11.960 --> 00:11:13.176
Really cool.

00:11:13.200 --> 00:11:14.576
Question for you, though.

00:11:14.600 --> 00:11:18.136
How long is it until, say, that
nursing-home patient that you mentioned

00:11:18.160 --> 00:11:20.736
is able to print
their pills in their home?

NOTE Paragraph

00:11:20.760 --> 00:11:23.536
Daniel Kraft: Well, again,
this is just a prototype.

00:11:23.560 --> 00:11:26.696
We think that the regulatory route
be automated compounding,

00:11:26.720 --> 00:11:29.990
and especially in nursing homes,
folks are taking multiple medications,

00:11:29.990 --> 00:11:31.370
and they're often mixed up,

00:11:31.370 --> 00:11:34.370
so it would be a perfect place
to start with these technologies.

00:11:34.370 --> 00:11:38.030
These aren't going to evolve and start
with printers on your bathroom counter.

00:11:38.030 --> 00:11:41.380
We need to be intelligent and smart
about how we roll these things out,

00:11:41.380 --> 00:11:45.090
but realizing there's so many challenges
with dosing, adherence and precision,

00:11:45.090 --> 00:11:47.680
and now that we have
all these amazing new technologies

00:11:47.680 --> 00:11:49.700
that can integrate and be leveraged,
I think we need approaches like this
to really catalyze and foster

00:11:49.700 --> 00:11:52.180
I think we need approaches like this
to really catalyze and foster

00:11:52.180 --> 00:11:54.020
a true future of health and medicine.

NOTE Paragraph

00:11:54.020 --> 00:11:56.336
Host: Great, thank you.
DK: Thanks.

NOTE Paragraph

00:11:56.360 --> 00:11:58.840
(Applause)