April 9, 2025 • 22 mins
Psychiatrist Dr. Rachna Saralka joins Cardiologist Dr. Michael Koren to explore the emerging field of artificial intelligence in psychology. They discuss the promise and shortfalls of using AI in this field, and the need for hard data and validated results through clinical trials. They get into empathy, the placebo effect, and potential use of AI to train psychologists and other doctors just like chess bots can help teach people to play chess.
Be a part of advancing science by participating in clinical research.
Have a question for Dr. Koren? Email him at askDrKoren@MedEvidence.com
Listen on Spotify
Listen on Apple Podcasts
Watch on YouTube
Share with a friend. Rate, Review, and Subscribe to the MedEvidence! podcast to be notified when new episodes are released.
Follow us on Social Media:
Facebook
Instagram
X (Formerly Twitter)
LinkedIn
Want to learn more? Checkout our entire library of podcasts, videos, articles and presentations at www.MedEvidence.com
Music: Storyblocks - Corporate Inspired
Thank you for listening!
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Announcer (00:00):
Welcome to MedEvidence!, where we help you
navigate the truth behindmedical research with unbiased,
evidence-proven facts.
Hosted by cardiologist and topmedical researcher, Dr Michael
Koren.
Dr. Michael Koren (00:11):
Hello, I'm Dr .
Michael Koren, the executiveeditor of MedEvidence! And if
you ever wondered what AI andpsychiatry and clinical research
had in common, you may findthis podcast to be fascinating.
Now, quite frankly, I don'tthink anybody has thought about
those three things in the samesentence, but I have Dr.
(00:32):
Rachna Saralkar here and sheand I are going to talk about
that the intersection ofartificial intelligence,
psychiatry and clinical research.
So, Rachna, welcome toMedEvidence! Thank you for
joining me, and I'm reallyexcited about this conversation.
I think it's going to take offin many different directions, so
we'll have some fun with thisand hopefully do a little
(00:53):
education along the way.
Dr. Rachna Saralkar (00:54):
That sounds great.
Thanks, Michael, I'm glad to behere.
Dr. Michael Koren (00:58):
So just to start us off, let our
MedEvidence audience know aboutyour background, how you got to
become a principal investigatorand your journey.
That covered all those areasthat I just spoke about.
Dr. Rachna Saralkar (01:10):
Yeah, absolutely.
So I'd say.
My journey started off inmedical school at Thomas
Jefferson University, then Iwent on to do my psychiatric
residency at Johns Hopkins Aftergraduating from residency-
Dr. Michael Koren (01:23):
We have a little rivalry there.
As a Harvard guy, sometimes youdon't always get along.
Dr. Rachna Saralkar (01:27):
Oh, no, yes .
Dr. Michael Koren (01:29):
But I like you, so I'll make an exception.
Dr. Rachna Saralkar (01:32):
I appreciate you letting me be on
the show, no, so after that Imoved out to the Bay Area for
almost 10 years and while I wasout there I wanted to really
focus on patient care.
I wanted to make sure that Iwas going to be a really good
doctor.
You know I was.
I wanted to make sure inpsychiatry we see patients in
all sorts of different areas.
So in psychiatric emergencyrooms I worked in inpatient
(01:56):
units, I was a consult liaisonpsychiatrist in the hospital and
I also held an outpatientpractice for 10 years.
So, yeah, I wanted to make sureI was good at delivering care
and have real experience in that.
(02:19):
And then about three years ago Iwas really frustrated by the
amount of variability I saw inthe quality of care patients got
before they came to see me,depending on the different types
of clinicians that they hadseen, the types of treatments
they had received.
And the second thing thatreally bothered me were how poor
the outcomes were, how poorlypatients were really doing,
(02:40):
especially the ones who feltlike they had tried everything
and spent years trying meds andtreatments before they finally
found one thing that worked.
And in medicine we call thiskind of "stratification and we
wish in psychiatry that we hadbetter stratification to pick
the right treatment for theright person first, and I was
really disheartened by the lackof that and I said I want to go
(03:02):
back to school and figure outhow I can be part of finding
some solutions to these problems.
Dr. Michael Koren (03:07):
Very, very cool Very cool and so
Dr. Rachna Saralkar (03:09):
Yeah, go ahead.
Dr. Michael Koren (03:11):
Yeah, so most recently you're a principal
investigator now with a nationalcompany that runs clinical
trials, so talk a little bitabout that connection.
Dr. Rachna Saralkar (03:18):
Yeah, so I I ended up being here at
Flourish Research as aninvestigator, but the way I
landed here, the way I gotinterested in research, was
after I was at a startup for thelast couple of years working on
using AI to measure depressionlevels and anxiety levels using
(03:42):
audiovisual features.
So the way somebody's facemoves, the way their voice
changes when they're talking,and during the process of being
in that world of working withthe FDA, attending conferences,
seeing other companies roll outAI therapists and lots and lots
of different tools, I was reallyfrustrated by the quality of
(04:05):
evidence that backed a lot ofthese tools and I said I want to
be an expert in clinicalresearch and I want to know how
to properly validate treatmentsand tools in an ethical manner,
because I want my patientsgetting well-validated care at
the end of the day, and sothat's why I entered clinical
(04:26):
research.
Dr. Michael Koren (04:27):
Interesting.
So just educate me.
This is not an area that Ireally track.
How far is AI in treating apatient with depression?
Is an AI bot as good or betterthan a therapist at this
juncture?
Dr. Rachna Saralkar (04:42):
At this juncture, it is definitely not
even close to being better thana therapist, I'd say.
You know, I think there's a lotof really interesting studies
and a lot of really great toolsthat are coming out, and some of
them show really promising datathat you know.
AI tools and AI therapistsprobably can truly emote empathy
(05:04):
and they probably really cancreate patient alliance between
the AI bot and the patient, andso there are studies showing
that this can really happen andI'd say, when patients know who
they're talking to and they'reokay with the fact that they're
talking to an AI agent, an AIbot, then it can work really
(05:26):
well.
There's a lot of dangersassociated with it.
Still, I'd say there are a lotof problems that have not been
ironed out a lot of safetyissues, privacy issues and I'm
happy to get into the otherthings that I think are of
concern there but we're reallygetting closer and closer to
having AI at least be part ofthe therapeutic process, right?
(05:48):
So I think there's a differencebetween an AI bot being a
therapist themselves versus AIbeing part of the process and
trying to improve the treatments.
Dr. Michael Koren (05:57):
Interesting.
Yeah, I've heard that statedbefore about AI bots having
empathy, and I have to say thatI find that a statement that I'm
going to push back on, for thesimple reason that empathy is
(06:17):
intrinsically human is.
A computer can't have empathy.
They can fake empathy, they canmake the recipient think
there's empathy, but empathyreally, sort of by definition of
the word, requires two humanbeings.
Yeah.
So yeah.
Dr. Rachna Saralkar (06:36):
I totally agree with you.
I think this comes into theproblem of, I think of language,
in my opinion.
So we have this word, empathy,and it's the word that we've had
for a long time.
So that's how we are trying todescribe this relationship
between doctor and patient, andwe're trying to, and there are
scientists who are studying whatthe factors that go into
(06:57):
empathy and trying to measurewell, how well do AI bots do
that?
When?
To your point, I completelyagree with you.
If I met an alien and a humanbeing on a new planet for the
first time, I don't care howwell the alien talks to me, I
know that the human beingunderstands me and feels the
same feelings that I feel andhas the ability at least to feel
(07:17):
those things, and thatimmediately creates a connection
that an alien or a robot or anAI agent could never do.
I cannot form that connectionwith them, but I do think I can
feel something with that alien.
I do think I could feelsomething with that bot.
I just don't think we have aterm for it yet.
Dr. Michael Koren (07:35):
Right, right, yeah, it's interesting.
Obviously, as humans, we needto know that other people care
about us.
We need to know that oursuffering is not unique to us.
I think those are importantthings, but how to get that
message across is really whatsounds like.
Your research is involved, andI had an interesting
(07:58):
conversation recently.
I think it was meant as aninsult to me, but I was talking
to a patient and she mentionedto me that she got a lot of
solace from her dog, that herdog paid attention to her, and
she never questioned whether ornot somebody that she was
talking to was paying attentionto her when it was with her dog,
(08:20):
like the feelings that she hadwith human beings.
And then she was talking to meabout it.
I didn't know if she wasaccusing me of this or not, but
especially in the modern erawhere we're looking back and
forth from our EMR and thepeople are wondering are you
really paying attention to me?
Dr. Rachna Saralkar (08:32):
Yeah, absolutely.
Dr. Michael Koren (08:33):
And she made a specific point that when she
was interfacing with thehealthcare system she wasn't
getting that, but when sheinterfaced with her puppy she
got that.
So you know, interesting.
And then the other thing I'llthrow out just to be a little
provocative about quote computerprogramming and human
intelligence, is how long ittook computers to beat humans in
(08:56):
chess.
I don't know if you've studiedthat or not, but it sounds like
you probably have.
But just for the listeners, IBMstarted looking at this problem
back in the very early 1960sand they were doing this on
mainframe computers that werestill very, very powerful and
they were having the hardesttime, despite having dozens of
(09:16):
computer scientists working onthis problem of beating a
grandmaster in chess, becausethe human brain is really good
at pattern recognition andbasically they would see a
pattern and the humans wouldknow how to manipulate that
pattern.
The computers were alwayscatching up, and so for a long,
long time it was actually over30 years computers could not
beat the best humans in chess.
(09:37):
And then all of a sudden theychanged the programming to make
the computers more human, whichwas to start bluffing.
So the computer started tolearn how to just make a crazy
move that made no sense that wassomething that a grandmaster
hadn't seen before, and at thatpoint the grandmasters would
panic a little bit.
They wouldn't know exactly howto deal with it.
(09:57):
And then there was an openingfor the computers to win, and
nowadays computers canabsolutely destroy humans in
chess.
So there's no grandmaster thatcan consistently beat a computer
.
It's really flipped.
But it took so many years to dothat, and in psychiatry that
gets even more complex thanchess.
Dr. Rachna Saralkar (10:16):
Oh, it's so much more complex, but I mean,
I think what's for me, what wasreally kind of uplifting and
exciting about the entirehistory of AI and chess was that
at the end of those 30 yearsnow the grandmaster you know.
Before it used to take, youknow, many, many years for
somebody who was like anapprentice in chess to become a
(10:39):
grandmaster.
That time, I think, has beencut in half because now they're
training with AI, they'repracticing against AI, and how
good they get is so much fasterand that's what I'm hoping is
happening in healthcare right.
Dr. Michael Koren (10:54):
I love that point.
That's a brilliant point.
Thank you for bringing that up.
That's exactly right.
So sometimes you have to thinkabout things from the other way
around and I absolutely lovethat.
There's so many places wherethe tail wags the dog and we
always have to think let's getthe dog to wag the tail.
Dr. Rachna Saralkar (11:11):
Yeah, yeah, no, and I definitely think
that's where the most importantapplications will be in
healthcare.
You know it doesn't sound assexy or as fun, but education
using AI and helping doctorsbecome better doctors,
therapists become bettertherapists using AI is out there
and that's really exciting.
Dr. Michael Koren (11:33):
Yeah, that's very cool, yeah.
So switching gears a little bit, tell me about some of the
areas that you're working on nowin terms of clinical research.
What are you doing, what areasare you looking to do in the
future, and a little bit aboutthe patient value proposition.
I think one of the things thatI really focus on as a
cardiologist that does a lot ofclinical trials is how do I
(11:55):
bring value to my patients?
So maybe you can comment onthat in your realm.
Dr. Rachna Saralkar (11:59):
Sure.
So our site in Philadelphia.
We have a lot of Alzheimer'strials right now and we're
growing out our depressiontrials at the moment and I think
that both of these sets oftrials are so I think are so
important.
You know, we have a lot ofconnections within our community
to groups of foundations andgroup homes and places where we
(12:27):
know, you know, a geriatricdemographic lives and we do our
best to go out to those placesand form connections in those
communities so we can educateeveryone.
You know, even if we only getone or two people who end up
being interested in a clinicaltrial, I think it's so important
for people to know that we'reat the precipice of being able
(12:47):
to treat things that maybe youonly know exist in your family
history and you aren't evenhaving symptoms of yet, like
Alzheimer's disease, right.
In the depression realm,I think there are so many, you
know, cutting edge treatmentsthat are, you know, one trying
to cut down on some of thehorrible side effects of the
existing treatments that we haveand two, trying to treat
(13:10):
treatment resistant depressionin a way we've never been able
to do before, and I think thoseare really exciting areas that
both of those things I thinkaren't really out in the market
yet.
And when patients come here, Ilove my job because I get to
spend as much time as they needgoing through and educating them
(13:32):
about not just what trials wehave but what the history of the
disease processes that run intheir family are and what
potential treatments we couldoffer or even they could get
from their outside doctor.
Dr. Michael Koren (13:45):
Yeah, it's fascinating, so let's dig into
that a little bit more.
I think those are both superinteresting areas.
We'll start with depression,and again, I'm a cardiologist,
but our site here in Florida hasbeen involved in depression
studies in the past.
In fact, one of the studiesthat I was personally involved
with was called the SAD HeartStudy, which looked at
Sertraline back in the day as away of treating post-myocardial
(14:10):
infarction depression,post-heart attack of depression.
Dr. Rachna Saralkar (14:13):
Wow fascinating.
Dr. Michael Koren (14:14):
Yeah, it turned out to be a very
successful and safe treatment,most importantly safe post-MI,
and probably is life-saving inmany cases.
But the problem with thosestudies is that there is a very
strong placebo effect.
So when you do aplacebo-controlled study in
depression, just the interactionwith the team and the staff and
(14:37):
the physicians seems to helppeople.
Again, this empathy concept thatwe're talking about when we
started so talk to us a littlebit about that and ways of
dealing with that, knowing it'snot necessarily a bad thing At
the end of the day if the studyitself helps people that's great
.
Dr. Rachna Saralkar (14:54):
Yeah, yeah.
No, I think it's important forpatients to understand that when
you walk into someplace that'sdoing clinical trials and you're
there for depression, it'sdifferent from walking in to see
your psychiatrist or yourtherapist, because when there is
a trial in depression to yourpoint, the placebo effect means
(15:15):
that people could getimprovement from not from just
the interaction and help fromtalking to people in the
community, talking to people atthe site.
And so what we do here is we doour very best to treat
everybody exactly the same,which is not what we do really
in personalized one-on-onetherapy care.
(15:37):
Right, we would dig into eachof your problems each day and
dive into what's bothering youand what's not.
We won't do that at a clinicaltrial site, because we want to
treat everybody the same withkindness, with empathy, and we
always will, and we can provideeducation, but we try not to.
We don't go as deep into kindof emotional issues.
For that reason.
Dr. Michael Koren (15:58):
Right, right, but at the end of the day you
know part of us it plays ascientific role and we want to
see if the investigationalproduct makes a difference.
Dr. Rachna Saralkar (16:09):
Yeah, yeah.
Dr. Michael Koren (16:10):
But part of us, as good clinical
investigators, are clinicians.
We're physicians that want tosee our patients get better,
regardless of their assignmentin a research protocol, and so
from that standpoint we want toencourage people A to get into
clinical research, because evenpeople that get placebo seem to
benefit from the interaction,and that's okay.
(16:31):
It makes it harderscientifically in some places,
but again, as a clinician toclinician, we're okay with that
concept.
Dr. Rachna Saralkar (16:38):
It's what my field relies on completely.
You know, I am more than okaywith the placebo effect and I
think as long as we're, you know, and most patients are too, you
know.
so I agree
Dr. Michael Koren (16:50):
Yeah, and that's also true not only in
psych studies but other thingsthat you would.
You would think would be moreobjective, but they actually are
driven by stress, anxiety andpsychological issues.
The number one that I've beeninvolved with is blood pressure.
Is that when you do a placebocontrolled blood pressure study,
people's blood pressure goesdown on placebo just because
(17:12):
they have the confidence ofdeveloping this rapport with the
team and probably complyingbetter with their baseline diet
and exercise and everything else, and things all move in the
right direction.
And I can tell some storiesabout really promising
technologies that were verydifficult to prove because of
the placebo effect of peoplebeing in a blood pressure study.
Dr. Rachna Saralkar (17:32):
That's amazing.
I didn't know that.
Dr. Michael Koren (17:34):
Yeah, so interesting stuff how that
translates to different areas inclinical research.
So let's shift gears a littlebit to Alzheimer's or memory
issues, and you brought up areally, really interesting point
is we don't know exactly whento intervene for this disease,
and I think it's fair to saythat most of the interventions
that have been put out there todate have looked at the end
(17:57):
stages of disease rather thantreating earlier.
So maybe comment a little biton that and help us understand
that balance and trade off alittle bit more.
Dr. Rachna Saralkar (18:07):
Yeah, sure.
So a lot of the earlier studiesto your point we're looking at.
You know, if somebody alreadyhas Alzheimer's disease, what
can we do?
And so there are, you know, afew FDA approved medicines that
help pull one of those proteinsthat can lead to Alzheimer's
called amyloid, out of the brain.
What they found was that, youknow, when you do that so late
stage to somebody who's alreadyhaving significant symptoms one,
(18:30):
it only seems to reduce thesymptoms about maybe 20 to 30%
at best.
And second, there's more sideeffects from the medication
versus when we start treatingearlier, when there's less of
that amyloid and tau proteinthat can lead to the disease,
but there is still some.
There seem to be fewer sideeffects and we can get people
(18:50):
significantly better outcomesbecause we stop cell death, we
stop your neurons from dyingearly on.
So I think this research is soimportant and it's going to save
millions of lives.
Dr. Michael Koren (19:06):
Yeah, yeah, obviously Alzheimer's disease is
a huge problem, especially asthe population ages and is less
likely to die of a heart attackor stroke.
You're more likely to sufferfrom these other problems, so
we're seeing thatepidemiologically.
But getting back to yourinterest in AI, is there an AI
bot that will make Alzheimer'sgo away?
Or if you do enough puzzles,you don't get the Alzheimer's in
(19:28):
the first place?
Is this being studiedcritically and properly?
Dr. Rachna Saralkar (19:32):
I don't know, I have no idea.
I don't know if there's any.
I'm sure somebody somewhere isdoing something with AI.
I mean the most I know thereare a lot of companies that are
building things out for, yes,for cognitive learning and
cognitive testing using AI, andI do think those tests are great
but probably need to be wellvalidated, which was kind of,
(19:55):
again, one of the big reasonswhy I came into clinical
research, because I think allthose things need to be better
validated.
Dr. Michael Koren (20:01):
Yeah, maybe you and I should write an
investigator-initiated studylooking at an intervention of
doing puzzles using an AI bot ormaybe chess or checkers we were
talking about that and thenrandomizing people at risk and
seeing how "smart they are quote, unquote two years down the
(20:22):
road and whether or not theyhave any, how well they do on
validated testing of memory.
That might be an interestinglittle project.
That might be very interesting.
Well, we'll put that on ourlist of to-dos.
Dr. Rachna Saralkar (20:35):
Sounds good .
Dr. Michael Koren (20:37):
And yeah, Rachna, this has been a fabulous
conversation.
I don't know if there'sanything else you want to
present to the audience in termsof some of the challenges or
things that you see for thefuture with regard to clinical
research in your new role.
Dr. Rachna Saralkar (20:51):
You know, I think the only thing I would
add and it's probably a largerconversation, something that I
am starting to see when I'mgoing through these protocols
with patients is that when thereare requests for data, requests
for scans and images that acompany is asking for, I think
(21:15):
we're working on making doing abetter and better job of making
sure that patients understandthe risks that are involved with
that, not just today, but couldbe down the line with the data,
because I think that's a fearthat a lot of people who kind of
sign away data rights have thatyou know, what are people going
to be able to do with my data?
(21:35):
We're moving into a world wherewe're videotaping audiotaping
in clinical trials sometimes andwe want to, and it's really
important to me that patientsunderstand and that we're being
careful about the protocols wechoose, that patients aren't
ever being limited by thetesting that we're doing.
Dr. Michael Koren (21:58):
Yeah, I love that point.
It's a fabulous point andcertainly very, very important.
Well, Rachna, this has been adelightful conversation.
Thank you for being part ofMedEvidence! and I look forward
to working with you in thefuture.
Dr. Rachna Saralkar (22:10):
Same Thanks so much.
Announcer (22:11):
Thanks for joining the MedEvidence! podcast.
To learn more, head over toMedEvidence.
com or subscribe to our podcaston your favorite podcast
platform.
Welcome to MedEvidence!, where we help you
navigate the truth behindmedical research with unbiased,
evidence-proven facts.
Hosted by cardiologist and topmedical researcher, Dr Michael
Koren.
Dr. Michael Koren (00:11):
Hello, I'm Dr .
Michael Koren, the executiveeditor of MedEvidence! And if
you ever wondered what AI andpsychiatry and clinical research
had in common, you may findthis podcast to be fascinating.
Now, quite frankly, I don'tthink anybody has thought about
those three things in the samesentence, but I have Dr.
(00:32):
Rachna Saralkar here and sheand I are going to talk about
that the intersection ofartificial intelligence,
psychiatry and clinical research.
So, Rachna, welcome toMedEvidence! Thank you for
joining me, and I'm reallyexcited about this conversation.
I think it's going to take offin many different directions, so
we'll have some fun with thisand hopefully do a little
(00:53):
education along the way.
Dr. Rachna Saralkar (00:54):
That sounds great.
Thanks, Michael, I'm glad to behere.
Dr. Michael Koren (00:58):
So just to start us off, let our
MedEvidence audience know aboutyour background, how you got to
become a principal investigatorand your journey.
That covered all those areasthat I just spoke about.
Dr. Rachna Saralkar (01:10):
Yeah, absolutely.
So I'd say.
My journey started off inmedical school at Thomas
Jefferson University, then Iwent on to do my psychiatric
residency at Johns Hopkins Aftergraduating from residency-
Dr. Michael Koren (01:23):
We have a little rivalry there.
As a Harvard guy, sometimes youdon't always get along.
Dr. Rachna Saralkar (01:27):
Oh, no, yes .
Dr. Michael Koren (01:29):
But I like you, so I'll make an exception.
Dr. Rachna Saralkar (01:32):
I appreciate you letting me be on
the show, no, so after that Imoved out to the Bay Area for
almost 10 years and while I wasout there I wanted to really
focus on patient care.
I wanted to make sure that Iwas going to be a really good
doctor.
You know I was.
I wanted to make sure inpsychiatry we see patients in
all sorts of different areas.
So in psychiatric emergencyrooms I worked in inpatient
(01:56):
units, I was a consult liaisonpsychiatrist in the hospital and
I also held an outpatientpractice for 10 years.
So, yeah, I wanted to make sureI was good at delivering care
and have real experience in that.
(02:19):
And then about three years ago Iwas really frustrated by the
amount of variability I saw inthe quality of care patients got
before they came to see me,depending on the different types
of clinicians that they hadseen, the types of treatments
they had received.
And the second thing thatreally bothered me were how poor
the outcomes were, how poorlypatients were really doing,
(02:40):
especially the ones who feltlike they had tried everything
and spent years trying meds andtreatments before they finally
found one thing that worked.
And in medicine we call thiskind of "stratification and we
wish in psychiatry that we hadbetter stratification to pick
the right treatment for theright person first, and I was
really disheartened by the lackof that and I said I want to go
(03:02):
back to school and figure outhow I can be part of finding
some solutions to these problems.
Dr. Michael Koren (03:07):
Very, very cool Very cool and so
Dr. Rachna Saralkar (03:09):
Yeah, go ahead.
Dr. Michael Koren (03:11):
Yeah, so most recently you're a principal
investigator now with a nationalcompany that runs clinical
trials, so talk a little bitabout that connection.
Dr. Rachna Saralkar (03:18):
Yeah, so I I ended up being here at
Flourish Research as aninvestigator, but the way I
landed here, the way I gotinterested in research, was
after I was at a startup for thelast couple of years working on
using AI to measure depressionlevels and anxiety levels using
(03:42):
audiovisual features.
So the way somebody's facemoves, the way their voice
changes when they're talking,and during the process of being
in that world of working withthe FDA, attending conferences,
seeing other companies roll outAI therapists and lots and lots
of different tools, I was reallyfrustrated by the quality of
(04:05):
evidence that backed a lot ofthese tools and I said I want to
be an expert in clinicalresearch and I want to know how
to properly validate treatmentsand tools in an ethical manner,
because I want my patientsgetting well-validated care at
the end of the day, and sothat's why I entered clinical
(04:26):
research.
Dr. Michael Koren (04:27):
Interesting.
So just educate me.
This is not an area that Ireally track.
How far is AI in treating apatient with depression?
Is an AI bot as good or betterthan a therapist at this
juncture?
Dr. Rachna Saralkar (04:42):
At this juncture, it is definitely not
even close to being better thana therapist, I'd say.
You know, I think there's a lotof really interesting studies
and a lot of really great toolsthat are coming out, and some of
them show really promising datathat you know.
AI tools and AI therapistsprobably can truly emote empathy
(05:04):
and they probably really cancreate patient alliance between
the AI bot and the patient, andso there are studies showing
that this can really happen andI'd say, when patients know who
they're talking to and they'reokay with the fact that they're
talking to an AI agent, an AIbot, then it can work really
(05:26):
well.
There's a lot of dangersassociated with it.
Still, I'd say there are a lotof problems that have not been
ironed out a lot of safetyissues, privacy issues and I'm
happy to get into the otherthings that I think are of
concern there but we're reallygetting closer and closer to
having AI at least be part ofthe therapeutic process, right?
(05:48):
So I think there's a differencebetween an AI bot being a
therapist themselves versus AIbeing part of the process and
trying to improve the treatments.
Dr. Michael Koren (05:57):
Interesting.
Yeah, I've heard that statedbefore about AI bots having
empathy, and I have to say thatI find that a statement that I'm
going to push back on, for thesimple reason that empathy is
(06:17):
intrinsically human is.
A computer can't have empathy.
They can fake empathy, they canmake the recipient think
there's empathy, but empathyreally, sort of by definition of
the word, requires two humanbeings.
Yeah.
So yeah.
Dr. Rachna Saralkar (06:36):
I totally agree with you.
I think this comes into theproblem of, I think of language,
in my opinion.
So we have this word, empathy,and it's the word that we've had
for a long time.
So that's how we are trying todescribe this relationship
between doctor and patient, andwe're trying to, and there are
scientists who are studying whatthe factors that go into
(06:57):
empathy and trying to measurewell, how well do AI bots do
that?
When?
To your point, I completelyagree with you.
If I met an alien and a humanbeing on a new planet for the
first time, I don't care howwell the alien talks to me, I
know that the human beingunderstands me and feels the
same feelings that I feel andhas the ability at least to feel
(07:17):
those things, and thatimmediately creates a connection
that an alien or a robot or anAI agent could never do.
I cannot form that connectionwith them, but I do think I can
feel something with that alien.
I do think I could feelsomething with that bot.
I just don't think we have aterm for it yet.
Dr. Michael Koren (07:35):
Right, right, yeah, it's interesting.
Obviously, as humans, we needto know that other people care
about us.
We need to know that oursuffering is not unique to us.
I think those are importantthings, but how to get that
message across is really whatsounds like.
Your research is involved, andI had an interesting
(07:58):
conversation recently.
I think it was meant as aninsult to me, but I was talking
to a patient and she mentionedto me that she got a lot of
solace from her dog, that herdog paid attention to her, and
she never questioned whether ornot somebody that she was
talking to was paying attentionto her when it was with her dog,
(08:20):
like the feelings that she hadwith human beings.
And then she was talking to meabout it.
I didn't know if she wasaccusing me of this or not, but
especially in the modern erawhere we're looking back and
forth from our EMR and thepeople are wondering are you
really paying attention to me?
Dr. Rachna Saralkar (08:32):
Yeah, absolutely.
Dr. Michael Koren (08:33):
And she made a specific point that when she
was interfacing with thehealthcare system she wasn't
getting that, but when sheinterfaced with her puppy she
got that.
So you know, interesting.
And then the other thing I'llthrow out just to be a little
provocative about quote computerprogramming and human
intelligence, is how long ittook computers to beat humans in
(08:56):
chess.
I don't know if you've studiedthat or not, but it sounds like
you probably have.
But just for the listeners, IBMstarted looking at this problem
back in the very early 1960sand they were doing this on
mainframe computers that werestill very, very powerful and
they were having the hardesttime, despite having dozens of
(09:16):
computer scientists working onthis problem of beating a
grandmaster in chess, becausethe human brain is really good
at pattern recognition andbasically they would see a
pattern and the humans wouldknow how to manipulate that
pattern.
The computers were alwayscatching up, and so for a long,
long time it was actually over30 years computers could not
beat the best humans in chess.
(09:37):
And then all of a sudden theychanged the programming to make
the computers more human, whichwas to start bluffing.
So the computer started tolearn how to just make a crazy
move that made no sense that wassomething that a grandmaster
hadn't seen before, and at thatpoint the grandmasters would
panic a little bit.
They wouldn't know exactly howto deal with it.
(09:57):
And then there was an openingfor the computers to win, and
nowadays computers canabsolutely destroy humans in
chess.
So there's no grandmaster thatcan consistently beat a computer
.
It's really flipped.
But it took so many years to dothat, and in psychiatry that
gets even more complex thanchess.
Dr. Rachna Saralkar (10:16):
Oh, it's so much more complex, but I mean,
I think what's for me, what wasreally kind of uplifting and
exciting about the entirehistory of AI and chess was that
at the end of those 30 yearsnow the grandmaster you know.
Before it used to take, youknow, many, many years for
somebody who was like anapprentice in chess to become a
(10:39):
grandmaster.
That time, I think, has beencut in half because now they're
training with AI, they'repracticing against AI, and how
good they get is so much fasterand that's what I'm hoping is
happening in healthcare right.
Dr. Michael Koren (10:54):
I love that point.
That's a brilliant point.
Thank you for bringing that up.
That's exactly right.
So sometimes you have to thinkabout things from the other way
around and I absolutely lovethat.
There's so many places wherethe tail wags the dog and we
always have to think let's getthe dog to wag the tail.
Dr. Rachna Saralkar (11:11):
Yeah, yeah, no, and I definitely think
that's where the most importantapplications will be in
healthcare.
You know it doesn't sound assexy or as fun, but education
using AI and helping doctorsbecome better doctors,
therapists become bettertherapists using AI is out there
and that's really exciting.
Dr. Michael Koren (11:33):
Yeah, that's very cool, yeah.
So switching gears a little bit, tell me about some of the
areas that you're working on nowin terms of clinical research.
What are you doing, what areasare you looking to do in the
future, and a little bit aboutthe patient value proposition.
I think one of the things thatI really focus on as a
cardiologist that does a lot ofclinical trials is how do I
(11:55):
bring value to my patients?
So maybe you can comment onthat in your realm.
Dr. Rachna Saralkar (11:59):
Sure.
So our site in Philadelphia.
We have a lot of Alzheimer'strials right now and we're
growing out our depressiontrials at the moment and I think
that both of these sets oftrials are so I think are so
important.
You know, we have a lot ofconnections within our community
to groups of foundations andgroup homes and places where we
(12:27):
know, you know, a geriatricdemographic lives and we do our
best to go out to those placesand form connections in those
communities so we can educateeveryone.
You know, even if we only getone or two people who end up
being interested in a clinicaltrial, I think it's so important
for people to know that we'reat the precipice of being able
(12:47):
to treat things that maybe youonly know exist in your family
history and you aren't evenhaving symptoms of yet, like
Alzheimer's disease, right.
In the depression realm,I think there are so many, you
know, cutting edge treatmentsthat are, you know, one trying
to cut down on some of thehorrible side effects of the
existing treatments that we haveand two, trying to treat
(13:10):
treatment resistant depressionin a way we've never been able
to do before, and I think thoseare really exciting areas that
both of those things I thinkaren't really out in the market
yet.
And when patients come here, Ilove my job because I get to
spend as much time as they needgoing through and educating them
(13:32):
about not just what trials wehave but what the history of the
disease processes that run intheir family are and what
potential treatments we couldoffer or even they could get
from their outside doctor.
Dr. Michael Koren (13:45):
Yeah, it's fascinating, so let's dig into
that a little bit more.
I think those are both superinteresting areas.
We'll start with depression,and again, I'm a cardiologist,
but our site here in Florida hasbeen involved in depression
studies in the past.
In fact, one of the studiesthat I was personally involved
with was called the SAD HeartStudy, which looked at
Sertraline back in the day as away of treating post-myocardial
(14:10):
infarction depression,post-heart attack of depression.
Dr. Rachna Saralkar (14:13):
Wow fascinating.
Dr. Michael Koren (14:14):
Yeah, it turned out to be a very
successful and safe treatment,most importantly safe post-MI,
and probably is life-saving inmany cases.
But the problem with thosestudies is that there is a very
strong placebo effect.
So when you do aplacebo-controlled study in
depression, just the interactionwith the team and the staff and
(14:37):
the physicians seems to helppeople.
Again, this empathy concept thatwe're talking about when we
started so talk to us a littlebit about that and ways of
dealing with that, knowing it'snot necessarily a bad thing At
the end of the day if the studyitself helps people that's great
.
Dr. Rachna Saralkar (14:54):
Yeah, yeah.
No, I think it's important forpatients to understand that when
you walk into someplace that'sdoing clinical trials and you're
there for depression, it'sdifferent from walking in to see
your psychiatrist or yourtherapist, because when there is
a trial in depression to yourpoint, the placebo effect means
(15:15):
that people could getimprovement from not from just
the interaction and help fromtalking to people in the
community, talking to people atthe site.
And so what we do here is we doour very best to treat
everybody exactly the same,which is not what we do really
in personalized one-on-onetherapy care.
(15:37):
Right, we would dig into eachof your problems each day and
dive into what's bothering youand what's not.
We won't do that at a clinicaltrial site, because we want to
treat everybody the same withkindness, with empathy, and we
always will, and we can provideeducation, but we try not to.
We don't go as deep into kindof emotional issues.
For that reason.
Dr. Michael Koren (15:58):
Right, right, but at the end of the day you
know part of us it plays ascientific role and we want to
see if the investigationalproduct makes a difference.
Dr. Rachna Saralkar (16:09):
Yeah, yeah.
Dr. Michael Koren (16:10):
But part of us, as good clinical
investigators, are clinicians.
We're physicians that want tosee our patients get better,
regardless of their assignmentin a research protocol, and so
from that standpoint we want toencourage people A to get into
clinical research, because evenpeople that get placebo seem to
benefit from the interaction,and that's okay.
(16:31):
It makes it harderscientifically in some places,
but again, as a clinician toclinician, we're okay with that
concept.
Dr. Rachna Saralkar (16:38):
It's what my field relies on completely.
You know, I am more than okaywith the placebo effect and I
think as long as we're, you know, and most patients are too, you
know.
so I agree
Dr. Michael Koren (16:50):
Yeah, and that's also true not only in
psych studies but other thingsthat you would.
You would think would be moreobjective, but they actually are
driven by stress, anxiety andpsychological issues.
The number one that I've beeninvolved with is blood pressure.
Is that when you do a placebocontrolled blood pressure study,
people's blood pressure goesdown on placebo just because
(17:12):
they have the confidence ofdeveloping this rapport with the
team and probably complyingbetter with their baseline diet
and exercise and everything else, and things all move in the
right direction.
And I can tell some storiesabout really promising
technologies that were verydifficult to prove because of
the placebo effect of peoplebeing in a blood pressure study.
Dr. Rachna Saralkar (17:32):
That's amazing.
I didn't know that.
Dr. Michael Koren (17:34):
Yeah, so interesting stuff how that
translates to different areas inclinical research.
So let's shift gears a littlebit to Alzheimer's or memory
issues, and you brought up areally, really interesting point
is we don't know exactly whento intervene for this disease,
and I think it's fair to saythat most of the interventions
that have been put out there todate have looked at the end
(17:57):
stages of disease rather thantreating earlier.
So maybe comment a little biton that and help us understand
that balance and trade off alittle bit more.
Dr. Rachna Saralkar (18:07):
Yeah, sure.
So a lot of the earlier studiesto your point we're looking at.
You know, if somebody alreadyhas Alzheimer's disease, what
can we do?
And so there are, you know, afew FDA approved medicines that
help pull one of those proteinsthat can lead to Alzheimer's
called amyloid, out of the brain.
What they found was that, youknow, when you do that so late
stage to somebody who's alreadyhaving significant symptoms one,
(18:30):
it only seems to reduce thesymptoms about maybe 20 to 30%
at best.
And second, there's more sideeffects from the medication
versus when we start treatingearlier, when there's less of
that amyloid and tau proteinthat can lead to the disease,
but there is still some.
There seem to be fewer sideeffects and we can get people
(18:50):
significantly better outcomesbecause we stop cell death, we
stop your neurons from dyingearly on.
So I think this research is soimportant and it's going to save
millions of lives.
Dr. Michael Koren (19:06):
Yeah, yeah, obviously Alzheimer's disease is
a huge problem, especially asthe population ages and is less
likely to die of a heart attackor stroke.
You're more likely to sufferfrom these other problems, so
we're seeing thatepidemiologically.
But getting back to yourinterest in AI, is there an AI
bot that will make Alzheimer'sgo away?
Or if you do enough puzzles,you don't get the Alzheimer's in
(19:28):
the first place?
Is this being studiedcritically and properly?
Dr. Rachna Saralkar (19:32):
I don't know, I have no idea.
I don't know if there's any.
I'm sure somebody somewhere isdoing something with AI.
I mean the most I know thereare a lot of companies that are
building things out for, yes,for cognitive learning and
cognitive testing using AI, andI do think those tests are great
but probably need to be wellvalidated, which was kind of,
(19:55):
again, one of the big reasonswhy I came into clinical
research, because I think allthose things need to be better
validated.
Dr. Michael Koren (20:01):
Yeah, maybe you and I should write an
investigator-initiated studylooking at an intervention of
doing puzzles using an AI bot ormaybe chess or checkers we were
talking about that and thenrandomizing people at risk and
seeing how "smart they are quote, unquote two years down the
(20:22):
road and whether or not theyhave any, how well they do on
validated testing of memory.
That might be an interestinglittle project.
That might be very interesting.
Well, we'll put that on ourlist of to-dos.
Dr. Rachna Saralkar (20:35):
Sounds good .
Dr. Michael Koren (20:37):
And yeah, Rachna, this has been a fabulous
conversation.
I don't know if there'sanything else you want to
present to the audience in termsof some of the challenges or
things that you see for thefuture with regard to clinical
research in your new role.
Dr. Rachna Saralkar (20:51):
You know, I think the only thing I would
add and it's probably a largerconversation, something that I
am starting to see when I'mgoing through these protocols
with patients is that when thereare requests for data, requests
for scans and images that acompany is asking for, I think
(21:15):
we're working on making doing abetter and better job of making
sure that patients understandthe risks that are involved with
that, not just today, but couldbe down the line with the data,
because I think that's a fearthat a lot of people who kind of
sign away data rights have thatyou know, what are people going
to be able to do with my data?
(21:35):
We're moving into a world wherewe're videotaping audiotaping
in clinical trials sometimes andwe want to, and it's really
important to me that patientsunderstand and that we're being
careful about the protocols wechoose, that patients aren't
ever being limited by thetesting that we're doing.
Dr. Michael Koren (21:58):
Yeah, I love that point.
It's a fabulous point andcertainly very, very important.
Well, Rachna, this has been adelightful conversation.
Thank you for being part ofMedEvidence! and I look forward
to working with you in thefuture.
Dr. Rachna Saralkar (22:10):
Same Thanks so much.
Announcer (22:11):
Thanks for joining the MedEvidence! podcast.
To learn more, head over toMedEvidence.
com or subscribe to our podcaston your favorite podcast
platform.
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!