Latest / What's Your Problem? / The Quantum Shift in Biomedical Discovery from Smart Talks with IBM

Transcript

The Quantum Shift in Biomedical Discovery from Smart Talks with IBM · What's Your Problem?

• 0:02
  Speaker 1: I'm Malcolm Globwell and you're listening to Smart Talks with IBM.
• 0:07
  Speaker 1: When doctor Laura Jahi began treating epilepsy patients in the
• 0:11
  Speaker 1: early two thousands, she noticed something unsettling. Different surgeons could
• 0:16
  Speaker 1: look at the exact same case and recommend completely different treatments.
• 0:21
  Speaker 1: One surgeon might remove one part of the brain, another
• 0:24
  Speaker 1: a different part, and a third might not operate at all.
• 0:28
  Speaker 1: Doctor j Hi believed there had to be a better way,
• 0:31
  Speaker 1: one grounded in data. That conviction set her on a
• 0:35
  Speaker 1: path that would lead her to become Chief Research Information
• 0:38
  Speaker 1: Officer at Cleveland Clinic and the executive program lead for
• 0:42
  Speaker 1: the Discovery Accelerator. The Discovery Accelerator is a ten year
• 0:47
  Speaker 1: partnership between Cleveland Clinic and IBM where researchers are using
• 0:51
  Speaker 1: AI and quantum computing to make incredible discoveries in healthcare
• 0:56
  Speaker 1: and life sciences. I sat down with doctor j High
• 1:00
  Speaker 1: to explore what's happening now, what's possible with quantum computing,
• 1:04
  Speaker 1: and where this next era of biomedical discovery is headed.
• 1:10
  Speaker 1: Epilepsy was your kind of specialty within neurology?
• 1:13
  Speaker 2: Correct? Yes?
• 1:13
  Speaker 1: What led you to that?
• 1:15
  Speaker 3: I was always fascinated by the brain. You know, it's
• 1:19
  Speaker 3: the part of our body that leaves still to this day,
• 1:22
  Speaker 3: the most to be discovered. So I was always intrigued
• 1:27
  Speaker 3: by areas that leave more for discovery, and epilepsy was
• 1:33
  Speaker 3: my pragmatic side, wanting to choose a subspecialty where the
• 1:38
  Speaker 3: problem can be fixed. In epilepsy, there are many medications
• 1:43
  Speaker 3: that are very effective, and there's a brain surgery that
• 1:46
  Speaker 3: we can do to stop seizures when medicines don't work.
• 1:50
  Speaker 2: That attracted me.
• 1:51
  Speaker 3: You know, compared to other areas in neurology, like stroke,
• 1:55
  Speaker 3: for example, or dementia, where usually the damage is more.
• 2:01
  Speaker 2: I wanted to be able to tell my.
• 2:03
  Speaker 3: Patients that you have a big problem, but here's what
• 2:06
  Speaker 3: I can do to fix it, and epilepsy offered me that.
• 2:10
  Speaker 1: But what would there must have been interesting and intriguing
• 2:15
  Speaker 1: unsolved problems in neurology.
• 2:19
  Speaker 3: Oh my gosh, it's the whole brain, isn't it. Before
• 2:22
  Speaker 3: starting to deal with artificial intelligence and research. Right in
• 2:26
  Speaker 3: the neurology, I'm dealing with real intelligence, the human brain
• 2:30
  Speaker 3: and how it works and how we think and how
• 2:34
  Speaker 3: we make decisions, and how it can grow and evolve,
• 2:40
  Speaker 3: and so there is many untapped questions in neurology, and
• 2:47
  Speaker 3: that's part.
• 2:48
  Speaker 2: Of the fascination in it.
• 2:50
  Speaker 3: In epilepsy in particular, it's an electrical disease in the brain,
• 2:56
  Speaker 3: it's actually one of the conditions in neurology. That's a
• 3:01
  Speaker 3: perfect alignment of all of the scientific disciplines. It's biology
• 3:08
  Speaker 3: and physics and chemistry all working together to make us
• 3:15
  Speaker 3: who we truly are.
• 3:17
  Speaker 2: Right, So every.
• 3:19
  Speaker 3: Other discipline, if you think of computing, for example, it's
• 3:22
  Speaker 3: purely electricity. Or if we do drug development or drug discovery,
• 3:28
  Speaker 3: that's mostly chemistry. Experiments in the lab, that's mostly biology.
• 3:33
  Speaker 3: But the human brain is all of those put together.
• 3:39
  Speaker 3: The cells in our brain secret these chemical substances that
• 3:43
  Speaker 3: diffuse everywhere and hook up where they need to to
• 3:47
  Speaker 3: trigger certain circuits and then trigger some effects afterwards. So
• 3:53
  Speaker 3: it was just an elegant science that has big impacts.
• 4:00
  Speaker 1: We're shortly going to get there and talk about you've
• 4:03
  Speaker 1: taken on this kind of very technology focused roller Cleveland Clinic.
• 4:07
  Speaker 1: I'm curious about if we go back to when you
• 4:11
  Speaker 1: were just starting out at Cleveland Clinic. Yeah, how much
• 4:14
  Speaker 1: were you thinking about this sort of technology piece about
• 4:18
  Speaker 1: what technology could do for your specialty. About was that
• 4:21
  Speaker 1: on your mind or is this something you've come to
• 4:24
  Speaker 1: more recently.
• 4:26
  Speaker 3: Well, it's been a journey, right, And when I started
• 4:29
  Speaker 3: training as a clinician, my priority was just to learn
• 4:33
  Speaker 3: how to better care for my patients and how to
• 4:37
  Speaker 3: be a better physician. And then I realized that clinical
• 4:42
  Speaker 3: practice provides an immediate reward. I'm interacting with a human
• 4:48
  Speaker 3: being and helping them in the moment, so there is
• 4:51
  Speaker 3: that immediate reward that comes with that. But that wasn't enough.
• 4:55
  Speaker 3: I wanted something more. So then I learned biomedical research.
• 4:59
  Speaker 3: Pract this is and research offered me this path towards
• 5:04
  Speaker 3: a future. You know, the reward there is more long term.
• 5:09
  Speaker 3: I'm studying discovering things that could help many people in
• 5:13
  Speaker 3: the future, even though I will never get to see
• 5:16
  Speaker 3: them or meet them, or you know, have that immediate satisfaction.
• 5:20
  Speaker 3: So that shifted me from being a pure clinician to
• 5:23
  Speaker 3: being a clinician scientist. And as that journey progressed, it
• 5:28
  Speaker 3: became very clear, as medicine evolved over the past twenty years,
• 5:32
  Speaker 3: that we cannot do any good biomedical research without understanding
• 5:37
  Speaker 3: data and technology. You know, the balance is shifting from
• 5:42
  Speaker 3: most of the research is happening we call it, you know,
• 5:45
  Speaker 3: on the wet bench with actual experiments, physical experiments, to
• 5:50
  Speaker 3: a place where most of the work is happening through
• 5:55
  Speaker 3: compute and simulations and data. So I became much more
• 6:00
  Speaker 3: involved for my personal research in building big data models
• 6:05
  Speaker 3: and learning about AI and you know, learning about technology
• 6:09
  Speaker 3: in general. And then as that journey progressed, I was
• 6:15
  Speaker 3: fortunate enough to be an enroll for Cleveland Clinic, where
• 6:18
  Speaker 3: my job is to bring that technology and bridge it
• 6:22
  Speaker 3: to research for all researchers across our health care system.
• 6:28
  Speaker 1: When you were talking about how in your own research
• 6:30
  Speaker 1: you were moving in that direction, what was your own
• 6:33
  Speaker 1: research focused on. What were you looking at?
• 6:36
  Speaker 3: I was looking at brain surgery for epilepsy. It's an
• 6:43
  Speaker 3: intervention that's been around for decades actually, but when I
• 6:48
  Speaker 3: started practice, I was shocked by, you know, the practice
• 6:51
  Speaker 3: that we had were making decisions around surgery, like, you know,
• 6:56
  Speaker 3: what patients should get it versus not, how likely is
• 7:00
  Speaker 3: it to work, what part of the brain should we remove.
• 7:03
  Speaker 3: All of those decisions were at the time and the
• 7:07
  Speaker 3: early two thousands driven by clinical opinions, Right, you know,
• 7:12
  Speaker 3: you have an experienced surgeon, they decide to do this.
• 7:15
  Speaker 3: Somebody else might decide to do something completely different, and
• 7:19
  Speaker 3: I didn't feel that that was the right.
• 7:21
  Speaker 2: Way to practice medicine.
• 7:22
  Speaker 3: You know, that we needed to be more evidence based
• 7:25
  Speaker 3: and data driven. So I went in the business in
• 7:29
  Speaker 3: research of building models, predictive models that can ingest data
• 7:35
  Speaker 3: from all of the tests that we would do about
• 7:38
  Speaker 3: on these patients before to.
• 7:40
  Speaker 2: Figure out surgery.
• 7:42
  Speaker 3: So I learned how to analyze all types of data,
• 7:48
  Speaker 3: from genetic data and individuals to pictures to electrical recordings,
• 7:54
  Speaker 3: and then combine those into these prediction.
• 7:58
  Speaker 1: Models you're looking at. You're taking large numbers of surgeries
• 8:03
  Speaker 1: for epilepsy, and you're seeing what kind of connection there
• 8:06
  Speaker 1: is between the success of the surgical intervention and the
• 8:10
  Speaker 1: underlying presentation of.
• 8:11
  Speaker 2: The patient exactly.
• 8:13
  Speaker 3: So I would be telling the patient, what is your
• 8:17
  Speaker 3: specific chance of becoming seizure free with surgery instead of
• 8:22
  Speaker 3: giving them statistics about you know, like you know, in general,
• 8:26
  Speaker 3: how well is that going to be effective? So that
• 8:29
  Speaker 3: piece of individualizing medicine.
• 8:32
  Speaker 1: So Cleveland Clinic decides to create a post called Chief
• 8:35
  Speaker 1: Information Officers.
• 8:36
  Speaker 3: If research information we have research, yes, always chief information
• 8:40
  Speaker 3: officer runs it.
• 8:42
  Speaker 1: Oh, yes, chief research information.
• 8:44
  Speaker 2: Yeah, so it for research.
• 8:46
  Speaker 1: This is parenthetically a huge job. Yes, so you apply
• 8:51
  Speaker 1: for this, do you know that you're going to be
• 8:54
  Speaker 1: thinking and talking and dealing with quantum.
• 8:57
  Speaker 3: I started in January twenty twenty, and like every leader
• 9:03
  Speaker 3: who's put in a position, remember, everybody tells you should
• 9:06
  Speaker 3: read that the first ninety days great how to plan.
• 9:11
  Speaker 3: So I was reading that and doing my listening tours
• 9:15
  Speaker 3: to understand, and then COVID hits and I got a
• 9:20
  Speaker 3: call from our executive suite about all, there is this
• 9:25
  Speaker 3: thing called COVID that's coming. We will start testing people
• 9:28
  Speaker 3: in four days. People will want to do research with COVID.
• 9:33
  Speaker 2: Make it happen. So it was there's no chapter in
• 9:37
  Speaker 2: the book about that, you know.
• 9:39
  Speaker 3: So so I then it really it was like a
• 9:46
  Speaker 3: pressure cooker, you know, test with. Yeah, I have to
• 9:50
  Speaker 3: create this access to data, structured you know, resources, so
• 9:56
  Speaker 3: that we can learn from it as.
• 9:58
  Speaker 2: Quickly as possible.
• 10:00
  Speaker 3: And so that was a catalyst. So then comes twenty
• 10:04
  Speaker 3: twenty one. That was the year of our centennial one
• 10:07
  Speaker 3: hundred years for Cleveland Clinic. So everybody, not just me,
• 10:11
  Speaker 3: we were in a mindset where we were thinking long,
• 10:14
  Speaker 3: long term, you know, like what made us specialized? Now
• 10:18
  Speaker 3: how do we stay relevant? Where is the world going
• 10:21
  Speaker 3: to be ten years from now? And what should I
• 10:25
  Speaker 3: get going right this moment to shape that and be
• 10:29
  Speaker 3: ready for it. And that's when quantum came in my mind,
• 10:33
  Speaker 3: where unless we invest in it now twenty twenty one,
• 10:39
  Speaker 3: we will not be ready for this next computer revolution
• 10:43
  Speaker 3: that's coming after AI.
• 10:45
  Speaker 1: Everybody in the world right now is doing nothing but
• 10:47
  Speaker 1: talking about AI, and you are already thinking one step
• 10:52
  Speaker 1: beyond a quantum what's different about the opportunity that quantum
• 10:57
  Speaker 1: creates for a metic research than AI?
• 11:02
  Speaker 2: Biology?
• 11:03
  Speaker 3: The human body, by definition, is much closer to fundamentals
• 11:11
  Speaker 3: of quantum, you know, to quantum mechanics and quantum physics
• 11:15
  Speaker 3: than it is to AI. AI is a classical computing
• 11:20
  Speaker 3: approach that in essence, reduces every piece of data to
• 11:26
  Speaker 3: a black or white binary categorization of a one or
• 11:31
  Speaker 3: a zero. At its core nature around us, the human body,
• 11:38
  Speaker 3: there is nothing categorical about it. It's it's that whole
• 11:44
  Speaker 3: you know, continuum of colors of life. Quantum its principles
• 11:52
  Speaker 3: are that, you know, so there's all the scientific principles
• 11:56
  Speaker 3: about quantum physics and superb position and in tankerment, you know,
• 12:01
  Speaker 3: all of these complex things that people have a hard
• 12:04
  Speaker 3: time with, but for in essence, it.
• 12:08
  Speaker 2: Really is much more aligned.
• 12:11
  Speaker 3: Like if I want to draw a colored picture, I
• 12:15
  Speaker 3: will not go and pick up charcoal. You know, it's
• 12:18
  Speaker 3: much easier for me to draw it if I had
• 12:21
  Speaker 3: a colored palette with me, and quantum offers that. There
• 12:25
  Speaker 3: is plenty of situations in medicine that are just intractable,
• 12:31
  Speaker 3: you know, meaning it's not an issue just of it
• 12:34
  Speaker 3: being AI being slow, or it doesn't have enough data,
• 12:39
  Speaker 3: or if only we got more GPUs, you know, we
• 12:42
  Speaker 3: can answer those questions. There are some problems in medicine
• 12:47
  Speaker 3: that are fundamentally such that even if you give me
• 12:51
  Speaker 3: all the GPUs in the world, there is no way
• 12:55
  Speaker 3: that AI can model accurately how these mollyules in the
• 13:00
  Speaker 3: body are interacting among each other, or how compounds electrons
• 13:05
  Speaker 3: are moving within the mitochondria. These are the engines within
• 13:10
  Speaker 3: our cells. There's these fundamental things in biology that AI
• 13:16
  Speaker 3: and classical computers are just not built to be able
• 13:21
  Speaker 3: to stimulate.
• 13:22
  Speaker 1: So you must go to dinner parties, Doctor j. High.
• 13:26
  Speaker 1: People must ask you what is quantum computing? What do
• 13:29
  Speaker 1: you tell them?
• 13:31
  Speaker 3: Yes, Although I often, you know, we talk about other
• 13:34
  Speaker 3: things at dinner.
• 13:35
  Speaker 1: Parties, eventually it comes down to you. If I was
• 13:40
  Speaker 1: at that dinner party with you, I would ask you
• 13:42
  Speaker 1: what is quantum computer?
• 13:44
  Speaker 3: I would say, depends on how much time we have
• 13:46
  Speaker 3: at the party to explain it. The short answer would be,
• 13:51
  Speaker 3: it's a completely different way of working with computers than
• 13:56
  Speaker 3: what we're used to Right now, you can imagine that
• 14:00
  Speaker 3: AI as being like a car that you take to
• 14:03
  Speaker 3: go from one place to another. No matter how fast
• 14:07
  Speaker 3: that Ferrari can get and how much fewer you put
• 14:10
  Speaker 3: in it, it's never going to be a fighter jet.
• 14:14
  Speaker 2: It's never going to be a plane.
• 14:16
  Speaker 3: AI is the car, the plane is quant They are
• 14:20
  Speaker 3: ways to get from point A to point B, but
• 14:23
  Speaker 3: they work very differently, and we always use them in together.
• 14:30
  Speaker 3: If I'm flying from Shaker Heights to Yorktown Heights, I
• 14:35
  Speaker 3: drive to the airport, get on the plane, then take
• 14:38
  Speaker 3: an uber to get to Yorktown Heights. In research, we
• 14:41
  Speaker 3: will do the same. We do some piece of it
• 14:44
  Speaker 3: in AI, some piece of it in quantum, and then
• 14:47
  Speaker 3: go back and.
• 14:47
  Speaker 1: Forth back in twenty twenty one, Cleveland Clinic and IBM
• 14:51
  Speaker 1: announced that they were starting something called the Discovery Accelerator.
• 14:55
  Speaker 1: What is that.
• 14:56
  Speaker 3: It's an initiative, a program, a partnership really that is
• 15:02
  Speaker 3: designed to bridge advanced computational tools and technology through the
• 15:10
  Speaker 3: leader in that space, IBM, with biomedical science and research
• 15:17
  Speaker 3: and life sciences problems, and that is a Cleveland Clinic.
• 15:23
  Speaker 3: We called it a Discovery Accelerator because that was our goal.
• 15:27
  Speaker 3: We were both on both sides challenged with the fact
• 15:31
  Speaker 3: that discovery in medicine was just taking too long. The
• 15:34
  Speaker 3: classical example that really brought it to life to us
• 15:39
  Speaker 3: then was drug discovery that it took over a decade
• 15:43
  Speaker 3: and it still does actually over a decade. From the
• 15:47
  Speaker 3: moment that there is a compound that someone in a
• 15:51
  Speaker 3: lab biomedical lab thinks it would be effective to treat
• 15:56
  Speaker 3: a certain disease, it takes about ten to thirteen from
• 16:00
  Speaker 3: that moment to when that drug is on a shelf
• 16:03
  Speaker 3: for a patient to get to from a pharmacy. And
• 16:06
  Speaker 3: that was just too much of a gap to allow
• 16:10
  Speaker 3: when we have so many health conditions that we needed
• 16:13
  Speaker 3: to address, and a big part of that gap could
• 16:16
  Speaker 3: be computationally solved better simulation of compounds, designing drug trails
• 16:22
  Speaker 3: that are.
• 16:23
  Speaker 2: More efficient, you know, that would finish faster.
• 16:26
  Speaker 3: So that was the motivation to bring computational tools and
• 16:33
  Speaker 3: technology closer to biomedical researchers.
• 16:36
  Speaker 1: Cleveland Click and IBM team up. And I'm assuming the
• 16:40
  Speaker 1: IBM quantum guys and other people descend on Cleveland and
• 16:44
  Speaker 1: you have your first meeting with them. Are they telling
• 16:47
  Speaker 1: you things you would never thought of? Or I mean,
• 16:50
  Speaker 1: I'm just curious about what's the difference between what you
• 16:54
  Speaker 1: thought was the potential was and what you discovered the
• 16:58
  Speaker 1: potential was.
• 17:01
  Speaker 3: That is an excellent question. If I had to prioritize.
• 17:05
  Speaker 3: One lesson that I learned over the past few years
• 17:09
  Speaker 3: of doing this, it is that you can never know
• 17:14
  Speaker 3: what your you know where your brain is going to
• 17:17
  Speaker 3: go and discovery until you talk. You know, you have
• 17:23
  Speaker 3: to open it up and really listen to try to
• 17:27
  Speaker 3: learn what the other people are saying.
• 17:29
  Speaker 2: It's it went both ways.
• 17:31
  Speaker 1: Can you give me an example.
• 17:32
  Speaker 3: So, okay, we built a quantum right, so it took
• 17:35
  Speaker 3: it took like eight months to get this machine put together,
• 17:38
  Speaker 3: and we put it in our cafeteria.
• 17:41
  Speaker 2: That's the whole other.
• 17:42
  Speaker 1: Story where you put the quantum machine computer in your cafeteria. Yes, yes, yes,
• 17:50
  Speaker 1: can you see it when you're eating lunch?
• 17:52
  Speaker 3: Yeah? Yeah, we have people eating lunch around it all
• 17:54
  Speaker 3: the time. We wanted to have a machine that people
• 17:57
  Speaker 3: can see. Otherwise it it the program wouldn't launch properly,
• 18:02
  Speaker 3: so I needed to have it physically. So we had
• 18:06
  Speaker 3: to look at retro fitted in existing space, and the
• 18:09
  Speaker 3: cafeteria space worked out. It was far enough from the street,
• 18:13
  Speaker 3: you know, there was no vibration that it was a
• 18:17
  Speaker 3: double floor, you know, so the ceiling was high enough.
• 18:20
  Speaker 3: It just like technically fit all of those requirements. And
• 18:24
  Speaker 3: it was either there or we put it in our
• 18:29
  Speaker 3: data center, which is a building and like another city
• 18:33
  Speaker 3: close to Cleveland, and we picked the cafeteria.
• 18:37
  Speaker 1: Yeah. Now, I know this is sort of this is
• 18:39
  Speaker 1: kind of hilarious, but there's a serious point I I
• 18:42
  Speaker 1: want to touch on, which is why do you need
• 18:45
  Speaker 1: it on premises?
• 18:46
  Speaker 3: On the premises Cleveland kinnect research. We needed to change
• 18:51
  Speaker 3: how we think about research and shift the mindset of
• 18:57
  Speaker 3: all of our researchers. And all of our researchers, I'm
• 19:02
  Speaker 3: talking about three thousand individuals who are one hundred percent
• 19:06
  Speaker 3: doing biomedical research in Cleveland Clinic, two hundred and thirty
• 19:12
  Speaker 3: labs individual pis. So that's the scale that I'm talking
• 19:17
  Speaker 3: about that we had to create an impact on. So
• 19:21
  Speaker 3: having it, having it be there was as much for
• 19:28
  Speaker 3: inspiration and to trigger our motivation to change as it
• 19:34
  Speaker 3: was a you know, a practical solution, say, because we
• 19:37
  Speaker 3: had the space and the connections and all of.
• 19:41
  Speaker 1: That I saw in it IBM headquarters. They're beautiful, they're
• 19:44
  Speaker 1: works of art.
• 19:45
  Speaker 3: They are They're gorgeous, and the one that we have
• 19:49
  Speaker 3: is the most gorgeous.
• 19:53
  Speaker 2: One of all. This is not me, you know, the mom.
• 19:57
  Speaker 4: Bias talking about it.
• 20:00
  Speaker 3: You know, they got an award, the Red Dot Award
• 20:03
  Speaker 3: for Design went to IBM and Cleveland Clinic for our
• 20:08
  Speaker 3: quantum and the quantum that IBM built for RPI a
• 20:17
  Speaker 3: couple of years after hours. They modeled it after hours,
• 20:21
  Speaker 3: not after the you know the ones from before.
• 20:24
  Speaker 1: Just just so people know, we're talking about basically a
• 20:27
  Speaker 1: small garage eleven.
• 20:30
  Speaker 3: But size eleven foot by eleven eleven feet eleven feet,
• 20:34
  Speaker 3: you know the cube, So it's a it's a glass
• 20:38
  Speaker 3: cube and the glass comes all the way from Italy.
• 20:42
  Speaker 3: It's the same glass that protects the crown jewels and
• 20:48
  Speaker 3: you know the Mona Lisa and all that. So so
• 20:52
  Speaker 3: there's a glass all around, and then there is the
• 20:56
  Speaker 3: tube that you see, the stainless tube that's shiny, you know,
• 21:01
  Speaker 3: and clean. But the technologies are inside of it, you know,
• 21:04
  Speaker 3: the chandelier and then the processor and the bottom and
• 21:08
  Speaker 3: it's just a fascinating thing to watch and it hums.
• 21:14
  Speaker 3: It makes the sound so even it sounds alive.
• 21:19
  Speaker 1: You have a great deal of affection for your computer.
• 21:22
  Speaker 2: And we love our machine.
• 21:24
  Speaker 1: I want to go back to something you said before,
• 21:27
  Speaker 1: which is when you had your initial conversations with IBM,
• 21:31
  Speaker 1: both sides learned things that they hadn't previously thought of.
• 21:35
  Speaker 1: Give me an example of something that either side hadn't
• 21:39
  Speaker 1: realized could be done with this new technology.
• 21:42
  Speaker 3: Sure, I mean on the equivalent clinic side, we thought
• 21:46
  Speaker 3: that what quantum should be good for is that it
• 21:50
  Speaker 3: would be a faster computer, right, so that we have
• 21:54
  Speaker 3: these big data sets that are requiring much more compute
• 21:58
  Speaker 3: power and you know, GIP used than what we have
• 22:01
  Speaker 3: and we should just run them on the quantum. And
• 22:04
  Speaker 3: what we came to realize is that Quantum actually does
• 22:09
  Speaker 3: not do well with these large data sets. What it
• 22:12
  Speaker 3: does well with our smaller, better defined data sets, but
• 22:17
  Speaker 3: ones where simulation is more important. You know, we have
• 22:22
  Speaker 3: to run them through multiple models, multiple simulations of how
• 22:27
  Speaker 3: they interact. As an example, one of the very first
• 22:30
  Speaker 3: projects we threw at Quantum was wanting to predict complications
• 22:35
  Speaker 3: cardiac complications from general surgery using electronic.
• 22:39
  Speaker 2: Health record data.
• 22:41
  Speaker 3: So data from our electronic health records are by definition
• 22:45
  Speaker 3: these really big data sets. You have in them every
• 22:49
  Speaker 3: single thing that you know about the patient that you've collected,
• 22:54
  Speaker 3: and we thought that Quantum would help us build models,
• 22:58
  Speaker 3: better models with this data.
• 23:00
  Speaker 2: And it failed miserably. It wasn't good, you know, at
• 23:04
  Speaker 2: doing that thing.
• 23:05
  Speaker 1: And why didn't it like that problem because it's too
• 23:08
  Speaker 1: it's too bigger than wieldy.
• 23:10
  Speaker 3: Well, because the hardware isn't tready right, So the hardware
• 23:13
  Speaker 3: with Quantum, that issue was back then. You know, now
• 23:17
  Speaker 3: we've upgraded our processor, but still Quantum now is limited
• 23:22
  Speaker 3: by noise and by its ability to correct for errors
• 23:28
  Speaker 3: when it's doing computation. And the more data that you
• 23:34
  Speaker 3: throw at it that you require it, you know, to
• 23:36
  Speaker 3: put in its system you know, to model interactions, the
• 23:41
  Speaker 3: more errors it's likely to make, so then the harder
• 23:45
  Speaker 3: it is for it to get to an answer.
• 23:47
  Speaker 2: That you can trust.
• 23:49
  Speaker 3: Now, we made a lot of progress sense, which I'm
• 23:53
  Speaker 3: sure we'll get to I hope we'll get to with
• 23:56
  Speaker 3: some recent breakthroughs that we made in that space with
• 24:00
  Speaker 3: modeling large compounds and interactions.
• 24:04
  Speaker 2: But the way that got us.
• 24:06
  Speaker 3: To where we are now, where we could model large interactions,
• 24:09
  Speaker 3: it took us figuring out that we shouldn't be doing
• 24:13
  Speaker 3: everything on quantum.
• 24:15
  Speaker 1: So give me an example of a problem that quantum
• 24:19
  Speaker 1: is ideally suited for that the quantum really likes.
• 24:23
  Speaker 3: In drug discovery, for examine chemistry. It likes chemistry a
• 24:27
  Speaker 3: lot because in chemistry what it has to what we
• 24:31
  Speaker 3: wanted to model is how a drug that we put
• 24:36
  Speaker 3: in our body is going to interact with We say
• 24:39
  Speaker 3: the protein you know, the target, the ligand that it
• 24:43
  Speaker 3: needs to buy in too. Like you know, the drug
• 24:46
  Speaker 3: is a key and it needs to fit in a
• 24:47
  Speaker 3: lock in certain parts of the body to open it,
• 24:51
  Speaker 3: get in, do it stay. And there are many keys,
• 24:55
  Speaker 3: many potential compounds that we could test for many parts
• 25:01
  Speaker 3: of our body. We don't really know how they're going
• 25:03
  Speaker 3: to interact. Traditionally, what we do is we have to
• 25:05
  Speaker 3: build all the keys. We have to manufacture all these
• 25:08
  Speaker 3: compounds and then do actual trial clinical trials. Put them
• 25:12
  Speaker 3: in people, put them in animals, and see what happens.
• 25:14
  Speaker 1: See which one is best?
• 25:15
  Speaker 3: See yeah, which like two fit best together. So we
• 25:19
  Speaker 3: use AI to try to help us with that. But
• 25:22
  Speaker 3: AI can only model what it had learned.
• 25:25
  Speaker 2: Right, So for.
• 25:28
  Speaker 3: Rare diseases conditions that there isn't enough information out there
• 25:33
  Speaker 3: on what the you know, the locks look like, it's
• 25:37
  Speaker 3: really hard to then model it with AI and get
• 25:40
  Speaker 3: an accurate prediction of whether there's a fit or not.
• 25:44
  Speaker 3: Quantum does not rely on the previous data for its modeling.
• 25:50
  Speaker 3: Quantum does its modeling purely based on the physical characteristics
• 25:55
  Speaker 3: of the compound of the key you know that you're designing.
• 26:00
  Speaker 3: So that makes it ideal because it's then untethered with
• 26:05
  Speaker 3: It's not limited by do we have enough samples or
• 26:08
  Speaker 3: don't we have enough samples, or you know, what the
• 26:10
  Speaker 3: previous studies find or not. It's purely based on those
• 26:14
  Speaker 3: physical properties, those quantum properties. So we found ourselves in
• 26:19
  Speaker 3: situations where we were able to predict a fit between
• 26:26
  Speaker 3: certain targets and where in conditions like Alzheimer's disease. For example,
• 26:31
  Speaker 3: we published where the quantum based modeling of the compound
• 26:39
  Speaker 3: was much better than what we would have gotten with
• 26:44
  Speaker 3: what we got right, Like, we did it both ways,
• 26:46
  Speaker 3: and the quantum one was the better fit than the
• 26:49
  Speaker 3: AI generated one.
• 26:51
  Speaker 1: This is fair. Quantum is a little more of an
• 26:54
  Speaker 1: artist and a little less of a of a kind
• 26:57
  Speaker 1: of nerd us nerdy to me, what seems like creative
• 27:03
  Speaker 1: and artistic?
• 27:03
  Speaker 2: Creative?
• 27:04
  Speaker 1: Yes, creative, it's like people.
• 27:07
  Speaker 3: Yeah, it's it opens up path that you never knew existed.
• 27:14
  Speaker 3: That's why when I get asked about what do I
• 27:17
  Speaker 3: see is the best, you know, the the most important
• 27:20
  Speaker 3: breakthrough that quantum is going to allow us to do,
• 27:24
  Speaker 3: my answer is I really don't know, because we you know,
• 27:28
  Speaker 3: when other people invented these new technologies, I don't think
• 27:34
  Speaker 3: they really knew that they're you know.
• 27:36
  Speaker 2: Like think of laser.
• 27:38
  Speaker 3: I don't think the person who invented laser thought that
• 27:41
  Speaker 3: they will be used to scan groceries at the grocery store.
• 27:44
  Speaker 4: You know.
• 27:45
  Speaker 3: But so technology developing technology, the way I think of
• 27:50
  Speaker 3: it is like having a baby you know, you raise
• 27:52
  Speaker 3: it as best you can, but then they're going to
• 27:55
  Speaker 3: go off and do their thing, and you will be
• 27:59
  Speaker 3: tying them down if you restrict them to just what
• 28:02
  Speaker 3: you thought they should do.
• 28:03
  Speaker 2: You know. So it opens up that.
• 28:09
  Speaker 3: Space, that creative space for us to ask questions differently
• 28:15
  Speaker 3: than we used to. We should train our mind to
• 28:18
  Speaker 3: stop starting from classical and then trying to squeeze it
• 28:23
  Speaker 3: into quantum. We have to learn how to think quantum
• 28:27
  Speaker 3: up front, right from the beginning, which we haven't really
• 28:33
  Speaker 3: been doing as a scientific community since our inception. We
• 28:37
  Speaker 3: were trained, and how do you convert what you're thinking
• 28:40
  Speaker 3: into a formula that you can ask from a computer
• 28:46
  Speaker 3: which is a classical right computer with quantum because of
• 28:51
  Speaker 3: how it works, it can answer questions, It can look
• 28:54
  Speaker 3: at problems in a very different way. So we have
• 28:58
  Speaker 3: to think differently about the questions and how we ask them.
• 29:02
  Speaker 1: With IBM, you recently modeled protein with over twelve thousand atoms.
• 29:07
  Speaker 1: Talk to me about that and why it's so meaningful
• 29:10
  Speaker 1: for job discovery.
• 29:12
  Speaker 3: So in October of twenty twenty four, so just eighteen
• 29:17
  Speaker 3: months ago, the largest compound biological compound that could be
• 29:23
  Speaker 3: simulated with quantum was ten atoms big, and it was
• 29:30
  Speaker 3: unfathomable back then that we will get past the one
• 29:34
  Speaker 3: thousand or few thousand atom simulation in the foreseeable future.
• 29:41
  Speaker 3: And what our team with IBM and with Rieken and
• 29:45
  Speaker 3: Japan published last month April twenty twenty six is a
• 29:52
  Speaker 3: simulation of the electrical properties of an enzyme trips in
• 30:00
  Speaker 3: the body that is twelve thousand, six hundred atoms bit
• 30:05
  Speaker 3: for you know, orders of magnitude beyond what anybody thought
• 30:09
  Speaker 3: was possible in that span of time.
• 30:13
  Speaker 2: And the reason why.
• 30:15
  Speaker 3: That happened was because of a you know, innovations in
• 30:21
  Speaker 3: the technology itself where the teams stopped thinking of quantum
• 30:28
  Speaker 3: and AI as competitors and instead thought of them as
• 30:34
  Speaker 3: different members of.
• 30:35
  Speaker 2: The same team.
• 30:37
  Speaker 3: Right, you're we're now in basketball season in the US
• 30:41
  Speaker 3: the NPA, and you need the you need defense, but
• 30:44
  Speaker 3: you also need your center, somebody to shoot. You need
• 30:50
  Speaker 3: all of the pieces to work together. So with this,
• 30:55
  Speaker 3: it was figuring out where do I put you know,
• 30:58
  Speaker 3: when do I put AI on the field, When do
• 31:01
  Speaker 3: I put quantum on the field, and how do I
• 31:04
  Speaker 3: tell them.
• 31:04
  Speaker 2: To work together?
• 31:06
  Speaker 3: It's the scientific terms the quantum centric super computing. So
• 31:11
  Speaker 3: quantum is at the center, but we're using our supercomputing
• 31:15
  Speaker 3: tools AI classical to interact with it and split that
• 31:22
  Speaker 3: big problem of the twelve thousand, six hundred atoms into
• 31:26
  Speaker 3: pieces where some pieces are best served with quantum and
• 31:30
  Speaker 3: others are best served with classical.
• 31:33
  Speaker 1: This distinction that we now cling to AI and quantum
• 31:38
  Speaker 1: are these very different things develop by different people for
• 31:41
  Speaker 1: different purposes. What you're suggesting is that's probably going to
• 31:45
  Speaker 1: go away. Yeah, in the future, these things will work together.
• 31:49
  Speaker 1: It's going to become teamwork and not one on one
• 31:52
  Speaker 1: competition exactly.
• 31:54
  Speaker 2: And it is that now in Cleveland Clinic.
• 31:56
  Speaker 3: I mean the way we've evolved our priority is with IBM.
• 32:02
  Speaker 3: It's a realization that both organizations have come to where
• 32:06
  Speaker 3: really to for progress to happen, we should stop seeing
• 32:10
  Speaker 3: them as separate. We should put them together and work
• 32:17
  Speaker 3: to the best of what each piece of technology can provide.
• 32:21
  Speaker 1: One theme running through a lot of your your what
• 32:25
  Speaker 1: you've been talking about is that the arrival of this
• 32:29
  Speaker 1: new technology requires the researcher to behave differently and that's
• 32:39
  Speaker 1: one of the reasons why you want the quantum machine
• 32:42
  Speaker 1: and the on full display, and then you were talking
• 32:45
  Speaker 1: about how you have to ask different kinds of questions.
• 32:47
  Speaker 1: I'm curious, can you can you? Can you elaborate on
• 32:51
  Speaker 1: that a little bit? So take me back, for example,
• 32:54
  Speaker 1: to your earliest days. If I had given you all
• 32:57
  Speaker 1: these tools that people now, how would your research have
• 33:02
  Speaker 1: proceeded differently? What would you have done differently?
• 33:07
  Speaker 2: You know, I would have looked at the molecular.
• 33:17
  Speaker 3: Components of the human brain as they relate to outcomes
• 33:22
  Speaker 3: of brain surgery way earlier than I did. The first
• 33:25
  Speaker 3: ten years of my career doing research was all spent
• 33:30
  Speaker 3: building models that were purely based on brain.
• 33:34
  Speaker 2: Waves and pictures of the brain.
• 33:40
  Speaker 3: It wasn't until after I hit a wall with my
• 33:45
  Speaker 3: models aren't getting past that eighty percent accuracy threshold that
• 33:50
  Speaker 3: I started thinking, oh, you know, there must be something
• 33:54
  Speaker 3: genetic or you know, more biological that is influencing this.
• 33:59
  Speaker 3: Had I been exposed to quantum at least as a concept,
• 34:05
  Speaker 3: right to quantum computing and what quantum science is back then,
• 34:11
  Speaker 3: I think it would have opened up my mind to
• 34:15
  Speaker 3: realize that it's not just about what I see. You know,
• 34:19
  Speaker 3: there is hidden relationships that exist within the human body
• 34:26
  Speaker 3: and that's our genetic makeup and our chemical makeup that
• 34:31
  Speaker 3: influence what comes to the surface that urge to dig deeper.
• 34:38
  Speaker 3: The other thing it would have changed is it would
• 34:40
  Speaker 3: have made me reach out to engineers and physicists and
• 34:43
  Speaker 3: mathematicians much earlier in my career.
• 34:48
  Speaker 1: Yeah, yeah, yeah. And how would it have changed This
• 34:53
  Speaker 1: is a very kind of prosaic question, but just kind
• 34:56
  Speaker 1: of the day to day life of someone doing better research.
• 35:00
  Speaker 1: I mean, the oh wow, you walk into the office
• 35:03
  Speaker 1: in the morning. How does your day proceed differently when
• 35:06
  Speaker 1: you're when you have these kinds of tools at your fingertips.
• 35:12
  Speaker 3: That's the fundamental question in biomedical research right now, and
• 35:18
  Speaker 3: it's it's less to do with quantum, more to do
• 35:21
  Speaker 3: with agentic AI, right, these agents that we can work
• 35:26
  Speaker 3: with now to help us how to think more creatively
• 35:31
  Speaker 3: and how to do work that up until now was
• 35:36
  Speaker 3: more like Scott work that the researchers had to do,
• 35:41
  Speaker 3: whether it was you know, so the hypothesis generation has
• 35:45
  Speaker 3: always been the most creative part of aspect of scientific research.
• 35:51
  Speaker 3: But what comes after it with the data collection for example,
• 35:55
  Speaker 3: that was always such a repetitive, you know, exercise, and
• 36:01
  Speaker 3: then the analysis after that was something that was very
• 36:06
  Speaker 3: resource intensive and you had to try so many different
• 36:10
  Speaker 3: approaches before you get to an answer, and that was
• 36:15
  Speaker 3: fairly complex.
• 36:16
  Speaker 2: Now, with access to.
• 36:20
  Speaker 3: Urgantic AI and you know, some quantum, of course, we
• 36:26
  Speaker 3: can spend more of our energy on the creative thinking
• 36:31
  Speaker 3: part of the aspects of the work and less on
• 36:36
  Speaker 3: the you know, just that repetitive.
• 36:39
  Speaker 1: When you look around, I'm assuming you walk around Cleveland
• 36:42
  Speaker 1: Clinic and you have lots of conversations with some of
• 36:45
  Speaker 1: the most brilliant medical researchers in the world. Are you
• 36:50
  Speaker 1: satisfied with how quickly and aggressively they are adopting these
• 36:55
  Speaker 1: new technologies or do they still need encouragement from you
• 36:58
  Speaker 1: to do? You have to say, people, wait, I've got
• 37:02
  Speaker 1: this machine in the cafeteria. You should be using it
• 37:05
  Speaker 1: for this problem. How much are you doing that kind
• 37:08
  Speaker 1: of encouraging in cheerleading or is it unnecessary?
• 37:11
  Speaker 3: No, there's plenty of cheerleading that's necessary people. You know,
• 37:17
  Speaker 3: humans don't like to change. It's hardwired in us. So
• 37:23
  Speaker 3: there is plenty of cheerleading. But what happens is, I mean,
• 37:28
  Speaker 3: the way we built our program to where we are now,
• 37:32
  Speaker 3: so Cleveland clinic now is pretty much winning every global competition.
• 37:37
  Speaker 3: And Quantum for life sciences, whether that's the welcome trust,
• 37:42
  Speaker 3: you know, Quantum for biological applications, we our partner. There
• 37:47
  Speaker 3: was a startup in Finland Algorithm Make there brilliant. We
• 37:51
  Speaker 3: worked with them to develop a photodynamic drug therapy for cancer,
• 37:56
  Speaker 3: or whether it is the NIH with they had an
• 37:59
  Speaker 3: ex price challenge for Quantum or universities that we're collaborating with,
• 38:06
  Speaker 3: we have a program that's bringing startups to our ecosystem.
• 38:10
  Speaker 3: We give them access to the machine if they have
• 38:13
  Speaker 3: a question that is significant enough for life sciences, universities
• 38:18
  Speaker 3: that we're building a bachelor's, master's, PhD programs with on
• 38:24
  Speaker 3: quantum computing, we developed that whole ecosystem around it. If
• 38:31
  Speaker 3: that's not cheerleading, I don't know what else would qualify
• 38:34
  Speaker 3: for cheerleading. But then what happens is these early adopters,
• 38:39
  Speaker 3: the risk takers, become the cheerleaders themselves, right, and then
• 38:43
  Speaker 3: they work with it, they achieve success, and we're nothing
• 38:48
  Speaker 3: but competitive in medicine and science. Right, So then it
• 38:53
  Speaker 3: becomes okay, so and so I did this with this machine,
• 38:55
  Speaker 3: Let me learn it so I can do the same
• 38:58
  Speaker 3: and it becomes this verse virtuous cycle of then innovation
• 39:04
  Speaker 3: and growth and people wanting to work together.
• 39:08
  Speaker 2: It's just been fascinating to watch.
• 39:11
  Speaker 1: You said that people don't like change, but you clearly do.
• 39:15
  Speaker 2: I do. That's the mindset of researchers, right.
• 39:19
  Speaker 3: A researcher is someone who is not afraid to fail,
• 39:22
  Speaker 3: actually sees failure as a chance to learn something right,
• 39:26
  Speaker 3: to do better the next time. So we get rejected
• 39:30
  Speaker 3: all the time and we don't care, right, we keep
• 39:33
  Speaker 3: moving on with papers.
• 39:35
  Speaker 2: Grant applications.
• 39:37
  Speaker 3: So that mindset is what all of research is built around.
• 39:44
  Speaker 3: So it's a very forward looking mindset. And Cleveland Clinic
• 39:49
  Speaker 3: as the health system, we wouldn't have survived one hundred years.
• 39:52
  Speaker 3: We wouldn't have done all of the firsts that we had.
• 39:56
  Speaker 3: Serotonin the chemical that drives the whole all science of
• 40:01
  Speaker 3: psychiatry and neuroscience that was discovered in Cleveland Clinic. So
• 40:07
  Speaker 3: as an organization, we have enough of people who think
• 40:13
  Speaker 3: that way that they will be the early adopters who
• 40:17
  Speaker 3: will pull the others with them.
• 40:21
  Speaker 1: Yeah. One last question, look look ahead tenures. Pat me
• 40:28
  Speaker 1: a picture of what quantum and related technologies look like
• 40:32
  Speaker 1: for a place like Cleveland Clinic and tenures.
• 40:36
  Speaker 3: Well, what I hope is that ten years from now,
• 40:41
  Speaker 3: if I if I'm seeing a patient in clinic who
• 40:44
  Speaker 3: has bad epilepsy and for the love of you know,
• 40:47
  Speaker 3: I can't figure out what medicine do I need to
• 40:51
  Speaker 3: prescribe to them to make them seizure free, I will
• 40:55
  Speaker 3: be able to send them to get a blood test
• 40:58
  Speaker 3: that we can then run through some analytical platform that
• 41:05
  Speaker 3: leverages both quantum and AI that can model exactly for
• 41:11
  Speaker 3: that patient, what compound, either existing or not to be developed.
• 41:17
  Speaker 3: It's some new chemical that we haven't tested for that
• 41:21
  Speaker 3: indication yet is going to treat them, you know, make
• 41:27
  Speaker 3: them seizure free. It's and I think quantum is ideal
• 41:34
  Speaker 3: for a condition like mine epilepsy, because we are a
• 41:38
  Speaker 3: rare disease, and I think that benefit that it's going
• 41:42
  Speaker 3: to have will start with rare diseases, you know, as
• 41:44
  Speaker 3: I explained earlier, So take any other rare disease, we
• 41:48
  Speaker 3: should start there and then expand from that to more
• 41:52
  Speaker 3: complex things like cancer for example, and others. But those
• 41:57
  Speaker 3: rare conditions where we are left now completely scratching our
• 42:02
  Speaker 3: heads and going by intuition. It will make our care
• 42:08
  Speaker 3: truly precise, and it will make drug development a more
• 42:13
  Speaker 3: tailored exercise than the way it is now, where it's
• 42:20
  Speaker 3: like a hammer that's looking for nails?
• 42:22
  Speaker 1: Am I right in thinking that of all of the
• 42:24
  Speaker 1: over the one hundred year history or more now of
• 42:27
  Speaker 1: Cleveland clinic, this sounds like the absolute best time to
• 42:30
  Speaker 1: be a Cleveland clinic.
• 42:31
  Speaker 2: Yeah. I love it, No complaints, no complaints, And I
• 42:38
  Speaker 2: am hiring.
• 42:39
  Speaker 4: I need I need those quantum researchers, those people who
• 42:44
  Speaker 4: are wanting, you know, to apply quant genetic research, imaging research,
• 42:50
  Speaker 4: every single aspect of biomedical research.
• 42:54
  Speaker 3: We can't afford to just wait on the sideline and
• 42:59
  Speaker 3: until the technolog she's ready, and then you know, then
• 43:02
  Speaker 3: it was teach us it is ready now. That twelve
• 43:04
  Speaker 3: thousand atom simulation wouldn't have happened just a year and
• 43:09
  Speaker 3: a half ago at Quidin Yahn.
• 43:12
  Speaker 1: So the headline of this conversation is we're hiring, we hired.
• 43:15
  Speaker 2: Yes, Yeah, that's a good headline. We're growing, how about that.
• 43:24
  Speaker 1: Smart Talks with IBM is produced by Matt Ramano, Amy
• 43:27
  Speaker 1: Gains McQuaid, Trina Menino, and Jake Harper. Engineering by Nina
• 43:31
  Speaker 1: Bird Lawrence Mastering by Sarah Bruguerer, Music by Gramoscope, Strategy
• 43:36
  Speaker 1: by Cassidy Meyer, Sophia Derlon and Tatiana Lieberman. Special thanks
• 43:41
  Speaker 1: to doctor Laura Jahi, Alicia Real Cooney, and the Cleveland
• 43:45
  Speaker 1: Clinic team. Smart Talks with IBM is a production of
• 43:49
  Speaker 1: Pushkin Industries and Ruby Studio at iHeartMedia. To find more
• 43:53
  Speaker 1: Pushkin podcasts, listen on the iHeartRadio app, Apple Podcasts, or
• 43:58
  Speaker 1: wherever you listen to. I'm Malcolm Gladwell. This is a
• 44:02
  Speaker 1: paid advertisement from IBM. The conversations on this podcast don't
• 44:07
  Speaker 1: necessarily represent IBM's positions, strategies, or opinions.