1 00:00:00,160 --> 00:00:02,960 Speaker 1: Hey everyone, it's Robert and Joe here. Today we've got 2 00:00:02,960 --> 00:00:05,240 Speaker 1: something a little bit different to share with you. It's 3 00:00:05,280 --> 00:00:09,400 Speaker 1: a new season of the Smart Talks with IBM podcast series. 4 00:00:09,720 --> 00:00:13,520 Speaker 2: This season on Smart Talks with IBM, Malcolm Gladwell is back, 5 00:00:13,520 --> 00:00:15,760 Speaker 2: and this time he's taking the show on the road. 6 00:00:15,880 --> 00:00:19,160 Speaker 2: Malcolm is stepping outside the studio to explore how IBM 7 00:00:19,239 --> 00:00:22,880 Speaker 2: clients are using artificial intelligence to solve real world challenges 8 00:00:23,079 --> 00:00:25,520 Speaker 2: and transform the way they do business. 9 00:00:25,480 --> 00:00:29,560 Speaker 1: From accelerating scientific breakthroughs to reimagining education. It's a fresh 10 00:00:29,600 --> 00:00:33,040 Speaker 1: look at innovation in action, where big ideas meet cutting 11 00:00:33,120 --> 00:00:33,960 Speaker 1: edge solutions. 12 00:00:34,320 --> 00:00:37,160 Speaker 2: You'll hear from industry leaders, creative thinkers, and of course 13 00:00:37,280 --> 00:00:40,920 Speaker 2: Malcolm Gladwell himself as he guides you through each story. 14 00:00:41,440 --> 00:00:44,680 Speaker 1: New episodes of Smart Talks with IBM drop every month 15 00:00:44,680 --> 00:00:48,279 Speaker 1: on the iHeartRadio app, Apple Podcasts, or wherever you get 16 00:00:48,320 --> 00:00:52,240 Speaker 1: your podcasts. Learn more at IBM dot com slash smart Talks. 17 00:00:52,880 --> 00:00:55,400 Speaker 1: This is a paid advertisement from IBM. 18 00:00:57,200 --> 00:01:02,600 Speaker 3: H'm Malcolm Gladwell and you're listening to Smart Talk with IBM. 19 00:01:02,960 --> 00:01:06,319 Speaker 3: When doctor Laura Jahi began treating epilepsy patients in the 20 00:01:06,360 --> 00:01:11,520 Speaker 3: early two thousands, she noticed something unsettling. Different surgeons could 21 00:01:11,520 --> 00:01:16,319 Speaker 3: look at the exact same case and recommend completely different treatments. 22 00:01:16,680 --> 00:01:19,480 Speaker 3: One surgeon might remove one part of the brain, another 23 00:01:19,680 --> 00:01:23,039 Speaker 3: a different part, and a third might not operate at all. 24 00:01:23,800 --> 00:01:26,320 Speaker 3: Doctor j Hi believed there had to be a better way, 25 00:01:26,760 --> 00:01:30,840 Speaker 3: one grounded in data. That conviction set her on a 26 00:01:30,840 --> 00:01:34,040 Speaker 3: path that would lead her to become Chief Research Information 27 00:01:34,120 --> 00:01:38,000 Speaker 3: Officer at Cleveland Clinic and the executive program lead for 28 00:01:38,080 --> 00:01:42,360 Speaker 3: the Discovery Accelerator. The Discovery Accelerator is a ten year 29 00:01:42,440 --> 00:01:46,960 Speaker 3: partnership between Cleveland Clinic and IBM where researchers are using 30 00:01:47,000 --> 00:01:51,640 Speaker 3: AI and quantum computing to make incredible discoveries in healthcare 31 00:01:52,000 --> 00:01:55,080 Speaker 3: and life sciences. I sat down with doctor j Hi 32 00:01:55,400 --> 00:01:59,440 Speaker 3: to explore what's happening now, what's possible with quantum computing, 33 00:02:00,040 --> 00:02:03,840 Speaker 3: and where this next era of biomedical discovery is headed. 34 00:02:05,520 --> 00:02:09,120 Speaker 3: Epilepsy was your kind of specialty within neurology, correct? Yes, 35 00:02:09,200 --> 00:02:10,080 Speaker 3: what led you to that? 36 00:02:10,840 --> 00:02:14,240 Speaker 4: I was always fascinated by the brain. You know, it's 37 00:02:14,800 --> 00:02:17,760 Speaker 4: the part of our body that lives still to this 38 00:02:17,840 --> 00:02:21,680 Speaker 4: day the most to be discovered. So I was always 39 00:02:21,840 --> 00:02:28,920 Speaker 4: intrigued by areas that leave more for discovery. And epilepsy 40 00:02:29,080 --> 00:02:33,080 Speaker 4: was my pragmatic side, wanting to choose a subspecialty where 41 00:02:33,639 --> 00:02:37,880 Speaker 4: the problem can be fixed. In epilepsy, there are many 42 00:02:37,919 --> 00:02:41,399 Speaker 4: medications that are very effective, and there's a brain surgery 43 00:02:41,520 --> 00:02:44,640 Speaker 4: that we can do to stop seizures when medicines don't work. 44 00:02:45,760 --> 00:02:46,960 Speaker 5: That attracted me. 45 00:02:47,120 --> 00:02:51,000 Speaker 4: You know, compared to other areas in neurology, like stroke, 46 00:02:51,080 --> 00:02:55,560 Speaker 4: for example, or dementia, where usually the damage is more definite. 47 00:02:56,200 --> 00:02:59,359 Speaker 4: I wanted to be able to tell my patients that 48 00:03:00,080 --> 00:03:02,280 Speaker 4: you have a big problem, but here's what I can. 49 00:03:02,160 --> 00:03:05,280 Speaker 5: Do to fix it, and epilepsy offered me that. 50 00:03:06,200 --> 00:03:09,959 Speaker 3: But what would There must have been interesting and intriguing 51 00:03:10,400 --> 00:03:14,200 Speaker 3: unsolved problems in neurology. 52 00:03:14,919 --> 00:03:17,480 Speaker 4: Oh my gosh, it's the whole brain, isn't it. Before 53 00:03:17,639 --> 00:03:21,799 Speaker 4: starting to deal with artificial intelligence and research. Right in 54 00:03:21,840 --> 00:03:25,959 Speaker 4: the neurology, I'm dealing with real intelligence, the human brain 55 00:03:26,120 --> 00:03:29,400 Speaker 4: and how it works and how we think and how 56 00:03:29,440 --> 00:03:34,000 Speaker 4: we make decisions, and how it. 57 00:03:34,000 --> 00:03:35,800 Speaker 5: Can grow and evolve. 58 00:03:36,040 --> 00:03:42,440 Speaker 4: And so there is many untaped questions in neurology. 59 00:03:41,880 --> 00:03:45,680 Speaker 5: And that's part of the fascination in it. 60 00:03:45,960 --> 00:03:51,400 Speaker 4: In epilepsy in particular, it's an electrical disease in the brain. 61 00:03:51,680 --> 00:03:56,760 Speaker 4: It's actually one of the conditions in a neurology that's 62 00:03:56,800 --> 00:04:02,960 Speaker 4: a perfect alignment of all of the scientific disciplines. It's 63 00:04:03,120 --> 00:04:09,560 Speaker 4: biology and physics and chemistry all working together to make 64 00:04:09,760 --> 00:04:15,920 Speaker 4: us who we truly are. Right, So every other discipline, 65 00:04:15,920 --> 00:04:19,240 Speaker 4: if you think of computing, for example, it's purely electricity. 66 00:04:19,520 --> 00:04:23,560 Speaker 4: Or if we do drug development or drug discovery, that's 67 00:04:23,560 --> 00:04:29,240 Speaker 4: mostly chemistry experiments in the lab, that's mostly biology. But 68 00:04:29,680 --> 00:04:35,279 Speaker 4: the human brain is all of those put together. The 69 00:04:35,400 --> 00:04:39,360 Speaker 4: cells in our brain secret these chemical substances that diffuse 70 00:04:39,520 --> 00:04:43,120 Speaker 4: everywhere and hook up where they need to to trigger 71 00:04:43,200 --> 00:04:48,719 Speaker 4: certain circuits and then trigger some effects afterwards. So it 72 00:04:48,960 --> 00:04:55,200 Speaker 4: was just an elegant science that has big impacts. 73 00:04:55,839 --> 00:04:58,680 Speaker 3: We're shortly going to get there and talk about you've 74 00:04:58,720 --> 00:05:01,880 Speaker 3: taken on this kind of very techn aology focused roller 75 00:05:01,920 --> 00:05:06,440 Speaker 3: Cleveland Clinic. I'm curious about if we go back to 76 00:05:06,520 --> 00:05:09,400 Speaker 3: when you were just starting out at Cleveland Clinic. Yeah, 77 00:05:09,440 --> 00:05:12,560 Speaker 3: how much were you thinking about this sort of technology piece, 78 00:05:13,240 --> 00:05:17,000 Speaker 3: about what technology could do for your specialty? About was 79 00:05:17,000 --> 00:05:19,000 Speaker 3: that on your mind or is this something you've come 80 00:05:19,080 --> 00:05:19,880 Speaker 3: to more recently. 81 00:05:21,560 --> 00:05:24,680 Speaker 4: Well, it's been a journey, right, and when I started 82 00:05:24,720 --> 00:05:28,760 Speaker 4: training as a clinician, my priority was just to learn 83 00:05:28,839 --> 00:05:32,320 Speaker 4: how to better care for my patients and how to 84 00:05:32,360 --> 00:05:34,080 Speaker 4: be a better physician. 85 00:05:34,360 --> 00:05:36,080 Speaker 5: Right, And then I. 86 00:05:36,120 --> 00:05:42,400 Speaker 4: Realized that clinical practice provides an immediate reward. I'm interacting 87 00:05:42,440 --> 00:05:45,080 Speaker 4: with a human being and helping them in the moment, 88 00:05:45,400 --> 00:05:48,719 Speaker 4: so there is that immediate reward that comes with that. 89 00:05:48,839 --> 00:05:51,880 Speaker 5: But that wasn't enough. I wanted something more. 90 00:05:51,960 --> 00:05:58,279 Speaker 4: So then I learned biomedical research practices, and research offered 91 00:05:58,320 --> 00:06:01,400 Speaker 4: me this path towards a future. You know, the reward 92 00:06:01,480 --> 00:06:06,440 Speaker 4: there is more long term. I'm studying discovering things that 93 00:06:06,560 --> 00:06:10,760 Speaker 4: could help many people in the future, even though I 94 00:06:10,800 --> 00:06:13,280 Speaker 4: will never get to see them or meet them, or 95 00:06:13,320 --> 00:06:17,080 Speaker 4: you know, have that immediate satisfaction. So that shifted me 96 00:06:17,200 --> 00:06:20,520 Speaker 4: from being a pure clinician to being a clinician scientist. 97 00:06:21,200 --> 00:06:25,280 Speaker 4: And as that journey progressed, it became very clear, as 98 00:06:25,360 --> 00:06:28,400 Speaker 4: medicine evolved over the past twenty years, that we cannot 99 00:06:28,440 --> 00:06:34,760 Speaker 4: do any good biomedical research without understanding data and technology. 100 00:06:34,920 --> 00:06:38,120 Speaker 4: You know, the balance is shifting from most of the 101 00:06:38,200 --> 00:06:41,159 Speaker 4: research is happening we call it, you know, on the 102 00:06:41,160 --> 00:06:46,640 Speaker 4: wet bench, with actual experiments, physical experiments, to a place 103 00:06:46,760 --> 00:06:51,600 Speaker 4: where most of the work is happening through compute and 104 00:06:51,680 --> 00:06:56,359 Speaker 4: simulations and data. So I became much more involved for 105 00:06:56,480 --> 00:07:01,799 Speaker 4: my personal research in building big data models and learning 106 00:07:01,839 --> 00:07:05,560 Speaker 4: about AI and you know, learning about technology in general. 107 00:07:06,520 --> 00:07:11,400 Speaker 4: And then as that journey progressed, I was fortunate enough 108 00:07:11,440 --> 00:07:14,320 Speaker 4: to be a role for Cleveland Clinic where my job 109 00:07:14,480 --> 00:07:18,160 Speaker 4: is to bring that technology and bridge it to research 110 00:07:18,720 --> 00:07:22,320 Speaker 4: for all researchers across our healthcare system. 111 00:07:23,280 --> 00:07:25,920 Speaker 3: When you were talking about how in your own research 112 00:07:25,960 --> 00:07:28,360 Speaker 3: you were moving in that direction, what was your own 113 00:07:28,400 --> 00:07:30,240 Speaker 3: research focused on. What were you looking at? 114 00:07:31,920 --> 00:07:38,680 Speaker 4: I was looking at brain surgery for epilepsy. It's an 115 00:07:38,720 --> 00:07:43,240 Speaker 4: intervention that's been around for decades actually, but when I 116 00:07:43,320 --> 00:07:47,160 Speaker 4: started practice, I was shocked by, you know, the practice 117 00:07:47,200 --> 00:07:51,520 Speaker 4: that we had were making decisions around surgery, like, you know, 118 00:07:51,600 --> 00:07:55,920 Speaker 4: what patients should get it versus not, how likely is 119 00:07:55,960 --> 00:07:58,600 Speaker 4: it to work? What part of the brain should we remove. 120 00:07:59,120 --> 00:08:02,880 Speaker 4: All of those visions were at the time and the 121 00:08:03,000 --> 00:08:07,800 Speaker 4: early two thousands driven by clinical opinions. Right, you know, 122 00:08:07,840 --> 00:08:10,160 Speaker 4: you have an experienced surgeon, they decide to do this. 123 00:08:10,320 --> 00:08:13,800 Speaker 4: Somebody else might decide to do something completely different. And 124 00:08:14,680 --> 00:08:16,920 Speaker 4: I didn't feel that that was the right way to 125 00:08:17,000 --> 00:08:17,880 Speaker 4: practice medicine. 126 00:08:17,920 --> 00:08:18,480 Speaker 5: You know that we. 127 00:08:18,520 --> 00:08:22,360 Speaker 4: Needed to be more evidence based and data driven. So 128 00:08:22,720 --> 00:08:26,440 Speaker 4: I went in the business in research of building models, 129 00:08:26,800 --> 00:08:31,960 Speaker 4: predictive models that can ingest data from all of the 130 00:08:32,040 --> 00:08:35,719 Speaker 4: tests that we would do about on these patients before to. 131 00:08:35,720 --> 00:08:36,840 Speaker 5: Figure out surgery. 132 00:08:37,320 --> 00:08:43,360 Speaker 4: So I learned how to analyze all types of data 133 00:08:43,440 --> 00:08:48,840 Speaker 4: from genetic data and individuals to pictures to electrical recordings 134 00:08:49,280 --> 00:08:54,280 Speaker 4: and then combine those into these prediction models. 135 00:08:54,840 --> 00:08:57,840 Speaker 3: So basically you're looking at you're taking large numbers of 136 00:08:58,480 --> 00:09:01,559 Speaker 3: surgeries for epilepsy, and you're seeing what kind of connection 137 00:09:01,640 --> 00:09:05,440 Speaker 3: there is between the success of the surgical intervention and 138 00:09:05,520 --> 00:09:07,240 Speaker 3: the underlying presentation of. 139 00:09:07,200 --> 00:09:08,679 Speaker 5: The patient exactly. 140 00:09:08,800 --> 00:09:12,480 Speaker 4: So I would be telling the patient what is your 141 00:09:12,679 --> 00:09:17,400 Speaker 4: specific chance of becoming seizure free with surgery instead of 142 00:09:17,480 --> 00:09:21,200 Speaker 4: giving them statistics about you know, like you know, in general, 143 00:09:21,440 --> 00:09:24,240 Speaker 4: how well is that going to be effective? So that 144 00:09:24,400 --> 00:09:27,400 Speaker 4: piece of individualizing medicine. 145 00:09:27,520 --> 00:09:30,800 Speaker 3: So Cleveland Clinic decides to create a post called Chief 146 00:09:30,800 --> 00:09:31,840 Speaker 3: Information Officers. 147 00:09:31,880 --> 00:09:35,760 Speaker 4: If research information we have research, yes, always, chief information 148 00:09:35,880 --> 00:09:37,000 Speaker 4: officer runs it. 149 00:09:37,800 --> 00:09:40,080 Speaker 3: Oh yes, chief research information. 150 00:09:39,880 --> 00:09:41,440 Speaker 5: Yeah, so it for research. 151 00:09:41,640 --> 00:09:47,040 Speaker 3: This is parenthetically a huge job. Yes, So you apply 152 00:09:47,160 --> 00:09:49,560 Speaker 3: for this, do you know that you're going to be 153 00:09:49,640 --> 00:09:52,559 Speaker 3: thinking and talking and dealing with quantum. 154 00:09:52,880 --> 00:09:58,760 Speaker 4: I started in January twenty twenty, and like every leader 155 00:09:58,760 --> 00:10:01,640 Speaker 4: who's put in a position, remember everybody tells you should 156 00:10:01,679 --> 00:10:05,920 Speaker 4: read that the first ninety days, Oh great, how to plan. 157 00:10:06,480 --> 00:10:10,040 Speaker 4: So I was reading that and doing my listening tours 158 00:10:10,360 --> 00:10:15,199 Speaker 4: to understand, and then COVID hits and I had a 159 00:10:15,240 --> 00:10:20,559 Speaker 4: call from our executive suite about all, there is this 160 00:10:20,640 --> 00:10:24,000 Speaker 4: thing called COVID that's coming. We will start testing people 161 00:10:24,080 --> 00:10:28,160 Speaker 4: in four days. People will want to do research with COVID. 162 00:10:28,600 --> 00:10:29,360 Speaker 5: Make it happen. 163 00:10:29,800 --> 00:10:33,839 Speaker 4: So it was there's no chapter in the book about that, 164 00:10:33,960 --> 00:10:40,320 Speaker 4: you know, So so I then it really it was 165 00:10:40,400 --> 00:10:42,760 Speaker 4: like a pressure cooker, you know. 166 00:10:42,920 --> 00:10:46,079 Speaker 5: Test with Yeah, I have to create. 167 00:10:45,840 --> 00:10:51,400 Speaker 4: This access to data, structured you know, resources so that 168 00:10:51,440 --> 00:10:55,720 Speaker 4: we can learn from it as quickly as possible. And 169 00:10:56,240 --> 00:10:59,840 Speaker 4: so that was a catalyst. So then comes twenty twenty one. 170 00:11:00,200 --> 00:11:03,360 Speaker 4: That was the year of our centennial one hundred years 171 00:11:03,360 --> 00:11:06,520 Speaker 4: for Cleveland Clinic. So everybody, not just me, we were 172 00:11:06,559 --> 00:11:10,880 Speaker 4: in a mindset where we were thinking long, long term, 173 00:11:10,960 --> 00:11:14,160 Speaker 4: you know, like what made us specialized till now? How 174 00:11:14,200 --> 00:11:17,320 Speaker 4: do we stay relevant? Where is the world going to 175 00:11:17,320 --> 00:11:21,160 Speaker 4: be ten years from now? And what should I get 176 00:11:21,240 --> 00:11:25,360 Speaker 4: going right this moment to shape that and be ready 177 00:11:25,440 --> 00:11:27,959 Speaker 4: for it. And that's when quantum came in my mind, 178 00:11:28,800 --> 00:11:34,000 Speaker 4: where unless we invest in it now twenty twenty one, 179 00:11:34,640 --> 00:11:38,199 Speaker 4: we will not be ready for this next computer revolution 180 00:11:38,360 --> 00:11:39,840 Speaker 4: that's coming after AI. 181 00:11:40,440 --> 00:11:42,920 Speaker 3: Everybody in the world right now is doing nothing but 182 00:11:43,040 --> 00:11:47,600 Speaker 3: talking about AI, and you are already thinking one step 183 00:11:47,640 --> 00:11:52,080 Speaker 3: beyond the quantum? What's different about the opportunity that quantum 184 00:11:52,640 --> 00:11:56,439 Speaker 3: creates for American research than AI. 185 00:11:57,720 --> 00:11:58,400 Speaker 5: Biology? 186 00:11:58,880 --> 00:12:07,000 Speaker 4: The human body, by definition, is much closer to fundamentals 187 00:12:07,000 --> 00:12:11,040 Speaker 4: of quantum, you know, to quantum mechanics and quantum physics 188 00:12:11,080 --> 00:12:16,040 Speaker 4: than it is to AI. AI is a classical computing 189 00:12:16,160 --> 00:12:21,440 Speaker 4: approach that in essence reduces every piece of data to 190 00:12:21,600 --> 00:12:26,199 Speaker 4: a black or white binary categorization of a. 191 00:12:26,200 --> 00:12:27,160 Speaker 5: One or a zero. 192 00:12:28,280 --> 00:12:33,480 Speaker 4: At its core nature around us, the human body, there 193 00:12:33,559 --> 00:12:39,560 Speaker 4: is nothing categorical about it. It's that whole, you know, 194 00:12:39,679 --> 00:12:48,680 Speaker 4: continuum of colors of life. Quantum its principles are that, 195 00:12:49,120 --> 00:12:53,440 Speaker 4: you know, so there's all the scientific principles about quantum 196 00:12:53,640 --> 00:12:58,200 Speaker 4: physics and superposition and in tanker, all of these complex 197 00:12:58,240 --> 00:13:00,760 Speaker 4: things that people have a hard time with. But for 198 00:13:01,600 --> 00:13:07,080 Speaker 4: in essence, it really is much more aligned, Like if 199 00:13:07,160 --> 00:13:10,640 Speaker 4: I want to draw a colored picture, I will not 200 00:13:10,760 --> 00:13:14,199 Speaker 4: go and pick up charcoal. You know, It's much easier 201 00:13:14,240 --> 00:13:17,880 Speaker 4: for me to draw it if I had a colored 202 00:13:17,920 --> 00:13:18,640 Speaker 4: palette with me. 203 00:13:18,800 --> 00:13:20,760 Speaker 5: And quantum offers that. 204 00:13:20,840 --> 00:13:26,240 Speaker 4: There is plenty of situations in medicine that are just intractable, 205 00:13:26,679 --> 00:13:29,960 Speaker 4: you know, meaning it's not an issue just of it 206 00:13:30,000 --> 00:13:34,000 Speaker 4: being AI being slow, or it doesn't have enough data, 207 00:13:34,480 --> 00:13:37,400 Speaker 4: or if only we got more GPUs, you know, we 208 00:13:37,440 --> 00:13:42,479 Speaker 4: can answer those questions. There are some problems in medicine 209 00:13:42,760 --> 00:13:46,600 Speaker 4: that are fundamentally such that even if you give me 210 00:13:46,679 --> 00:13:49,680 Speaker 4: all the GPUs in the world, there is no way 211 00:13:50,400 --> 00:13:55,800 Speaker 4: that AI can model accurately how these molecules in the 212 00:13:55,880 --> 00:14:01,120 Speaker 4: body are interacting among each other, or how comp electrons 213 00:14:01,160 --> 00:14:05,880 Speaker 4: are moving within the mitochondria. These are the engines within 214 00:14:06,040 --> 00:14:11,920 Speaker 4: our cells. There's these fundamental things in biology that AI 215 00:14:12,120 --> 00:14:16,320 Speaker 4: and classical computers are just not built to be able 216 00:14:16,360 --> 00:14:17,040 Speaker 4: to simulate. 217 00:14:17,720 --> 00:14:21,240 Speaker 3: So you must go to dinner parties, doctor j. High. 218 00:14:21,600 --> 00:14:25,000 Speaker 3: People must ask you what is quantum computing? What do 219 00:14:25,040 --> 00:14:25,760 Speaker 3: you tell them? 220 00:14:26,280 --> 00:14:29,520 Speaker 4: Yes, although I often, you know, we talk about other 221 00:14:29,560 --> 00:14:30,760 Speaker 4: things at dinner parties. 222 00:14:32,760 --> 00:14:35,480 Speaker 3: Eventually it comes down to you. If I was at 223 00:14:35,480 --> 00:14:38,160 Speaker 3: that dinner party with you, I would ask you what 224 00:14:38,280 --> 00:14:39,040 Speaker 3: is quantic computer? 225 00:14:39,440 --> 00:14:41,840 Speaker 6: I would say, depends on how much time we have 226 00:14:42,000 --> 00:14:46,000 Speaker 6: at the party to explain it. The short answer would be, 227 00:14:46,280 --> 00:14:51,640 Speaker 6: it's a completely different way of working with computers than 228 00:14:51,680 --> 00:14:55,360 Speaker 6: what we're used to right now. You can imagine that 229 00:14:55,520 --> 00:14:58,360 Speaker 6: AI as being like a car that you take to 230 00:14:58,400 --> 00:15:02,200 Speaker 6: go from one place to another. No matter how fast 231 00:15:02,480 --> 00:15:06,120 Speaker 6: that Ferrari can get and how much fewre you put 232 00:15:06,160 --> 00:15:09,120 Speaker 6: in it, it's never going to be a fighter jet. 233 00:15:09,440 --> 00:15:10,920 Speaker 5: It's never going to be a plane. 234 00:15:11,840 --> 00:15:15,240 Speaker 4: AI is the car, the plane is quant They are 235 00:15:15,680 --> 00:15:18,640 Speaker 4: ways to get from point A to point B, but 236 00:15:18,880 --> 00:15:24,920 Speaker 4: they work very differently, and we always use them in together. 237 00:15:25,400 --> 00:15:30,200 Speaker 4: If I'm flying from Shaker Heights to Yorktown Heights, I 238 00:15:30,480 --> 00:15:33,240 Speaker 4: drive to the airport, get on the plane, then take 239 00:15:33,280 --> 00:15:37,120 Speaker 4: an uber to get to Yorktown Heights. In research, we 240 00:15:37,160 --> 00:15:39,640 Speaker 4: will do the same. We do some piece of it 241 00:15:39,720 --> 00:15:42,200 Speaker 4: in AI, some piece of it in Quantum, and then 242 00:15:42,240 --> 00:15:43,120 Speaker 4: go back and forth. 243 00:15:43,600 --> 00:15:47,200 Speaker 3: Back in twenty twenty one, Cleveland Clinic and IBM announced 244 00:15:47,200 --> 00:15:50,800 Speaker 3: it they were starting something called the Discovery Accelerator. What 245 00:15:50,920 --> 00:15:51,280 Speaker 3: is that? 246 00:15:52,160 --> 00:15:56,600 Speaker 4: It's an initiative, a program, a partnership really that is 247 00:15:57,320 --> 00:16:03,600 Speaker 4: designed to a bridge at advanced computational tools and technology 248 00:16:04,800 --> 00:16:11,160 Speaker 4: through the leader in that space, IBM with biomedical science 249 00:16:11,240 --> 00:16:17,120 Speaker 4: and research and life sciences problems, and that is a 250 00:16:17,160 --> 00:16:21,240 Speaker 4: Cleveland clinic. We called it a discovery accelerator because that 251 00:16:21,400 --> 00:16:24,120 Speaker 4: was our goal. You know, we were both on both 252 00:16:24,160 --> 00:16:28,120 Speaker 4: sides challenged to the fact that discovery in medicine was 253 00:16:28,160 --> 00:16:32,800 Speaker 4: just taking too long. The classical example that really brought 254 00:16:32,800 --> 00:16:37,040 Speaker 4: it to life to us then was drug discovery that 255 00:16:37,120 --> 00:16:40,160 Speaker 4: it took over a decade and it still does actually 256 00:16:40,640 --> 00:16:44,360 Speaker 4: over a decade. From the moment that there is a 257 00:16:44,480 --> 00:16:50,320 Speaker 4: compound that someone in a lab biomedical lab thinks it 258 00:16:50,360 --> 00:16:53,880 Speaker 4: would be effective to treat a certain disease, it takes 259 00:16:53,920 --> 00:16:57,240 Speaker 4: about ten to thirteen years from that moment to when 260 00:16:57,280 --> 00:16:59,760 Speaker 4: that drug is on a shelf for a patient to 261 00:16:59,760 --> 00:17:02,680 Speaker 4: get tool from a pharmacy. And that was just too 262 00:17:02,720 --> 00:17:06,960 Speaker 4: much of a gap to allow when we have so 263 00:17:07,119 --> 00:17:10,359 Speaker 4: many health conditions that we needed to address, and a 264 00:17:10,400 --> 00:17:14,720 Speaker 4: big part of that gap could be computationally solved. Better 265 00:17:14,800 --> 00:17:19,280 Speaker 4: simulation of compounds, designing drug trails that are more efficient, 266 00:17:19,520 --> 00:17:23,679 Speaker 4: you know, that would finish faster. So that was the 267 00:17:23,920 --> 00:17:31,800 Speaker 4: motivation to bring computational tools and technology closer to biomedical researchers. 268 00:17:32,000 --> 00:17:35,639 Speaker 3: Cleveland Click and IBM team up, and I'm assuming the 269 00:17:35,680 --> 00:17:39,520 Speaker 3: IBM Quantum guys and other people descend on Cleveland and 270 00:17:39,560 --> 00:17:42,680 Speaker 3: you have your first meeting with them. Are they telling 271 00:17:42,720 --> 00:17:45,920 Speaker 3: you things you would never thought of? Or I mean, 272 00:17:46,080 --> 00:17:48,399 Speaker 3: I'm just curious about what's the difference between what you 273 00:17:50,160 --> 00:17:54,159 Speaker 3: thought was the potential was and what you discovered the 274 00:17:54,160 --> 00:17:54,919 Speaker 3: potential was. 275 00:17:56,240 --> 00:18:00,000 Speaker 4: That is an excellent question if I had to prioritize. 276 00:18:00,200 --> 00:18:03,840 Speaker 4: Is one lesson that I learned over the past few 277 00:18:03,920 --> 00:18:08,000 Speaker 4: years of doing this. It is that you can never 278 00:18:08,280 --> 00:18:12,560 Speaker 4: know what your you know where your brain is going 279 00:18:12,640 --> 00:18:19,000 Speaker 4: to go and discovery until you talk. You know, you 280 00:18:19,040 --> 00:18:22,200 Speaker 4: have to open it up and really listen to try 281 00:18:22,240 --> 00:18:23,879 Speaker 4: to learn what the other people are saying. 282 00:18:24,320 --> 00:18:26,520 Speaker 5: It's it went both ways. 283 00:18:26,680 --> 00:18:27,720 Speaker 3: Can you give you an example. 284 00:18:27,880 --> 00:18:30,320 Speaker 4: So, okay, we built the quantum right, so it took 285 00:18:30,680 --> 00:18:34,200 Speaker 4: it took like eight months to get this machine put together, and. 286 00:18:34,119 --> 00:18:38,720 Speaker 5: We put it in our cafeteria. That's the whole other story. 287 00:18:38,440 --> 00:18:43,480 Speaker 3: Where you put the quantum machine computer in your cafeteria? Yes, yes, yes, 288 00:18:45,320 --> 00:18:46,919 Speaker 3: Can you see it when you're eating lunch? 289 00:18:47,359 --> 00:18:47,639 Speaker 1: Yeah? 290 00:18:47,720 --> 00:18:50,520 Speaker 4: Yeah, we have people eating lunch around it all the time. 291 00:18:51,000 --> 00:18:53,680 Speaker 4: We wanted to have a machine that people can see. 292 00:18:53,920 --> 00:18:57,520 Speaker 4: Otherwise it the program wouldn't launch properly. 293 00:18:57,600 --> 00:18:59,960 Speaker 5: So I needed to have it physics. 294 00:19:00,720 --> 00:19:04,240 Speaker 4: So we had to look at retrofitted in existing space, 295 00:19:04,280 --> 00:19:06,560 Speaker 4: and the cafeteria space worked out. 296 00:19:06,720 --> 00:19:09,439 Speaker 5: It was far enough from the street, you know, there was. 297 00:19:09,320 --> 00:19:13,720 Speaker 4: No vibration that it was a double floor, you know, 298 00:19:13,760 --> 00:19:17,240 Speaker 4: so the ceiling was high enough. It just like technically 299 00:19:17,320 --> 00:19:22,040 Speaker 4: fit all of those requirements. And it was either there 300 00:19:22,200 --> 00:19:26,080 Speaker 4: or we put it in our data center, which is 301 00:19:26,119 --> 00:19:30,800 Speaker 4: a building and like another city close to Cleveland, and 302 00:19:30,920 --> 00:19:32,160 Speaker 4: we picked the cafeteria. 303 00:19:32,440 --> 00:19:34,840 Speaker 3: Yeah, now why I know this is sort of this 304 00:19:34,880 --> 00:19:37,119 Speaker 3: is kind of hilarious, but there's a serious point I 305 00:19:37,119 --> 00:19:40,679 Speaker 3: I want to touch on, which is why do you 306 00:19:40,760 --> 00:19:41,879 Speaker 3: need it on premises? 307 00:19:42,000 --> 00:19:45,640 Speaker 4: On the premises Cleveland Clinic research, We needed to change 308 00:19:46,240 --> 00:19:51,800 Speaker 4: how we think about research and shift the mindset of 309 00:19:52,480 --> 00:19:56,159 Speaker 4: all of our researchers and all. 310 00:19:56,040 --> 00:19:57,000 Speaker 5: Of our researchers. 311 00:19:57,119 --> 00:20:01,320 Speaker 4: I'm talking about three thousand individuals who are one hundred 312 00:20:01,359 --> 00:20:05,919 Speaker 4: percent doing biomedical research and Cleveland Clinic two one hundred 313 00:20:05,920 --> 00:20:11,960 Speaker 4: and thirty labs individual pis. So that's the scale that 314 00:20:12,440 --> 00:20:15,600 Speaker 4: I'm talking about that we had to create an impact 315 00:20:15,760 --> 00:20:17,080 Speaker 4: on so. 316 00:20:17,200 --> 00:20:22,040 Speaker 5: Having it having it be there was. 317 00:20:22,400 --> 00:20:27,159 Speaker 4: As much for inspiration and to trigger our motivation to 318 00:20:27,320 --> 00:20:31,800 Speaker 4: change as it was a you know, a practical solution, say, 319 00:20:31,800 --> 00:20:36,359 Speaker 4: because we had the space and the connections and all of. 320 00:20:36,280 --> 00:20:39,960 Speaker 3: That I saw in it. IBM headquarters. They're beautiful. 321 00:20:39,960 --> 00:20:43,320 Speaker 4: Their works of art they are They're gorgeous, and the 322 00:20:43,320 --> 00:20:49,080 Speaker 4: one that we have is the most gorgeous one of all. 323 00:20:49,240 --> 00:20:53,560 Speaker 5: This is not me, you know, the mom bias talking 324 00:20:53,600 --> 00:20:54,600 Speaker 5: about it. 325 00:20:54,600 --> 00:20:57,920 Speaker 4: It is you know, they got an award, the Red 326 00:20:57,960 --> 00:21:03,159 Speaker 4: Dot Award for Design went to IBM and Cleveland Clinic 327 00:21:03,280 --> 00:21:10,800 Speaker 4: for our quantum and the quantum that IBM built for 328 00:21:11,080 --> 00:21:15,439 Speaker 4: RPI a couple of years after hours. They modeled it 329 00:21:15,560 --> 00:21:19,040 Speaker 4: after hours, not after the you know the ones from before. 330 00:21:19,280 --> 00:21:22,800 Speaker 3: Just just so people know, we're talking about basically a 331 00:21:22,840 --> 00:21:26,320 Speaker 3: small garage. 332 00:21:26,280 --> 00:21:29,879 Speaker 4: Size eleven foot by eleven eleven feet eleven feet. 333 00:21:29,720 --> 00:21:31,040 Speaker 3: You know, the cube small. 334 00:21:31,720 --> 00:21:35,760 Speaker 4: So it's a it's a glass cube, and the glass 335 00:21:35,800 --> 00:21:40,080 Speaker 4: comes all the way from Italy. It's the same glass 336 00:21:40,560 --> 00:21:44,720 Speaker 4: that protects the Crown jewels and you know the Mona 337 00:21:44,760 --> 00:21:49,080 Speaker 4: Lisa and all that. So so there's a glass all 338 00:21:49,160 --> 00:21:52,920 Speaker 4: around and then there is the tube that you see, 339 00:21:53,080 --> 00:21:56,919 Speaker 4: the stainless tube that's shiny, you know, and clean, but 340 00:21:57,400 --> 00:22:00,159 Speaker 4: the technologies all inside of it, you know, the the 341 00:22:00,240 --> 00:22:02,960 Speaker 4: leer and then the processor and the bottom. 342 00:22:02,560 --> 00:22:09,320 Speaker 5: And it's just a fascinating thing to watch. And it hums. 343 00:22:09,400 --> 00:22:12,679 Speaker 5: It makes the sound so even it sounds alive. 344 00:22:15,000 --> 00:22:17,679 Speaker 3: You have a great deal of affection for your computer, 345 00:22:17,800 --> 00:22:18,000 Speaker 3: and we. 346 00:22:18,080 --> 00:22:19,560 Speaker 5: Love our machine. 347 00:22:20,200 --> 00:22:22,440 Speaker 3: I want to go back to something you said before, 348 00:22:22,520 --> 00:22:26,080 Speaker 3: which is when you had your initial conversations with IBM, 349 00:22:26,600 --> 00:22:30,520 Speaker 3: both sides learned things that they hadn't previously thought of. 350 00:22:30,760 --> 00:22:34,800 Speaker 3: Give me an example of something that either side hadn't 351 00:22:34,840 --> 00:22:37,160 Speaker 3: realized could be done with this new technology. 352 00:22:37,280 --> 00:22:41,480 Speaker 4: Sure, I mean on the equivalent clinic side, we thought 353 00:22:41,840 --> 00:22:45,960 Speaker 4: that what quantum should be good for is that it 354 00:22:46,000 --> 00:22:49,040 Speaker 4: would be a faster computer, right, so that we have 355 00:22:49,200 --> 00:22:54,160 Speaker 4: these big data sets that are requiring much more compute 356 00:22:54,200 --> 00:22:56,399 Speaker 4: power and you know GPUs than what we have and 357 00:22:56,440 --> 00:22:57,160 Speaker 4: we should. 358 00:22:56,880 --> 00:22:58,959 Speaker 5: Just run them on the quantum. 359 00:22:59,560 --> 00:23:04,280 Speaker 4: And what we came to realize is that quantum actually 360 00:23:04,280 --> 00:23:07,320 Speaker 4: does not do well with these large data sets. What 361 00:23:07,400 --> 00:23:11,960 Speaker 4: it does well with our smaller, better defined data sets, 362 00:23:12,000 --> 00:23:16,960 Speaker 4: but ones where simulation is more important, you know, we 363 00:23:17,040 --> 00:23:22,280 Speaker 4: have to run them through multiple models, you multiple simulations 364 00:23:22,280 --> 00:23:25,560 Speaker 4: of how they interact. As an example, one of the 365 00:23:25,680 --> 00:23:29,560 Speaker 4: very first projects we threw at Quantum was wanting to 366 00:23:29,640 --> 00:23:35,320 Speaker 4: predict complications cardiac complications from general surgery using electronic health 367 00:23:35,359 --> 00:23:40,080 Speaker 4: record data. So data from our electronic health records are 368 00:23:40,240 --> 00:23:43,639 Speaker 4: by definition these really big data sets. You have in 369 00:23:43,680 --> 00:23:47,320 Speaker 4: them every single thing that you know about the patient 370 00:23:47,520 --> 00:23:51,480 Speaker 4: that you've collected. And we thought that Quantum would help 371 00:23:51,560 --> 00:23:56,600 Speaker 4: us build models, better models with this data. And it 372 00:23:56,760 --> 00:24:00,720 Speaker 4: failed miserably. It wasn't good, you know, at doing that thing. 373 00:24:00,800 --> 00:24:03,119 Speaker 3: And why didn't it? Like that problem because it's too 374 00:24:03,480 --> 00:24:04,640 Speaker 3: it's too bigger than wieldy. 375 00:24:05,240 --> 00:24:08,720 Speaker 4: Well, because the hardware isn't tready right, So the hardware 376 00:24:08,880 --> 00:24:13,000 Speaker 4: with Quantum, that issue was back then. You know, now 377 00:24:13,040 --> 00:24:17,400 Speaker 4: we've upgraded our processor. But still Quantum now is limited 378 00:24:17,440 --> 00:24:23,360 Speaker 4: by noise and by its ability to correct for errors 379 00:24:23,440 --> 00:24:29,159 Speaker 4: when it's doing computation. And the more data that you 380 00:24:29,359 --> 00:24:31,840 Speaker 4: throw at it that you require it, you know, to 381 00:24:32,040 --> 00:24:36,440 Speaker 4: put in its system, you know, to model interactions, the 382 00:24:36,480 --> 00:24:39,320 Speaker 4: more errors it's likely to make. So then the harder 383 00:24:40,320 --> 00:24:42,960 Speaker 4: it is for it to get to an answer. 384 00:24:42,640 --> 00:24:44,040 Speaker 5: That you can trust. 385 00:24:44,600 --> 00:24:48,520 Speaker 4: Now, we made a lot of progress sense, which I'm 386 00:24:48,560 --> 00:24:50,240 Speaker 4: sure we'll get to. 387 00:24:50,440 --> 00:24:51,320 Speaker 5: I hope we'll get. 388 00:24:51,200 --> 00:24:54,359 Speaker 4: To with some recent breakthroughs that we made in that 389 00:24:54,440 --> 00:25:00,560 Speaker 4: space with modeling large compounds and interactions. But the way 390 00:25:00,720 --> 00:25:02,800 Speaker 4: that got us to where we are now where we 391 00:25:02,800 --> 00:25:06,600 Speaker 4: could model large interactions, it took us figuring out that 392 00:25:06,720 --> 00:25:10,360 Speaker 4: we shouldn't be doing everything on quantum. 393 00:25:10,720 --> 00:25:14,120 Speaker 3: So give me an example of a problem that quantum 394 00:25:14,320 --> 00:25:18,080 Speaker 3: is ideally suited for that the quantum really. 395 00:25:17,960 --> 00:25:22,560 Speaker 4: Likes in drug discovery, for examine chemistry, it likes chemistry 396 00:25:22,640 --> 00:25:26,680 Speaker 4: a lot because in chemistry what it has to What 397 00:25:26,760 --> 00:25:30,840 Speaker 4: we wanted to model is how a drug that we 398 00:25:31,080 --> 00:25:34,320 Speaker 4: put in our body is going to interact with We 399 00:25:34,359 --> 00:25:38,560 Speaker 4: say the protein you know, the target, the ligand that 400 00:25:38,640 --> 00:25:41,240 Speaker 4: it needs to bind too, like you know, the drug 401 00:25:41,320 --> 00:25:43,080 Speaker 4: is the key and it needs to fit in a 402 00:25:43,160 --> 00:25:46,120 Speaker 4: lock in certain parts of the body to open it, 403 00:25:46,520 --> 00:25:51,040 Speaker 4: get in, do it stay. And there are many keys, 404 00:25:51,200 --> 00:25:56,560 Speaker 4: many potential compounds that we could test for many parts 405 00:25:56,560 --> 00:25:58,880 Speaker 4: of our body. We don't really know how they're going 406 00:25:58,920 --> 00:26:01,080 Speaker 4: to interact. Tradition, what we do is we have to 407 00:26:01,160 --> 00:26:03,480 Speaker 4: build all the keys. We have to manufacture all these 408 00:26:03,520 --> 00:26:07,440 Speaker 4: compounds and then do actual trial clinical trials, put them 409 00:26:07,440 --> 00:26:09,760 Speaker 4: in people, put them in animals and see what happens. 410 00:26:10,040 --> 00:26:11,080 Speaker 3: See which one is best? 411 00:26:11,160 --> 00:26:14,879 Speaker 4: See yeah, which like two fit best together. So we 412 00:26:15,000 --> 00:26:17,760 Speaker 4: use AI to try to help us with that. But 413 00:26:18,000 --> 00:26:21,480 Speaker 4: AI can only model what it had learned, right, So 414 00:26:21,640 --> 00:26:28,359 Speaker 4: for rare diseases conditions that there isn't enough information out 415 00:26:28,359 --> 00:26:31,639 Speaker 4: there on what the you know, the locks look like, 416 00:26:32,240 --> 00:26:35,239 Speaker 4: it's really hard to then model it with AI and 417 00:26:35,320 --> 00:26:38,439 Speaker 4: get an accurate prediction of whether there's a fit or not. 418 00:26:40,000 --> 00:26:45,120 Speaker 4: Quantum does not rely on the previous data for its modeling. 419 00:26:45,280 --> 00:26:46,560 Speaker 5: Quantum does. 420 00:26:46,680 --> 00:26:51,360 Speaker 4: It's modeling purely based on the physical characteristics of the 421 00:26:51,520 --> 00:26:55,720 Speaker 4: compound of the key you know that you're designing. So 422 00:26:56,160 --> 00:27:00,880 Speaker 4: that makes it ideal because it's then untethered with It's 423 00:27:00,920 --> 00:27:03,560 Speaker 4: not limited by do we have enough samples or don't 424 00:27:03,600 --> 00:27:06,080 Speaker 4: we have enough samples, or you know, what the previous 425 00:27:06,119 --> 00:27:11,400 Speaker 4: studies find or not. It's purely based on those physical properties, 426 00:27:11,480 --> 00:27:15,879 Speaker 4: those quantum properties. So we found ourselves in situations where 427 00:27:15,880 --> 00:27:22,399 Speaker 4: we were able to predict the fits between certain targets, 428 00:27:22,440 --> 00:27:27,199 Speaker 4: and where in conditions like Alzheimer's disease, for example, we 429 00:27:27,600 --> 00:27:34,399 Speaker 4: published where the quantum based modeling of the compound was 430 00:27:35,200 --> 00:27:39,760 Speaker 4: much better than what we would have gotten with what 431 00:27:39,800 --> 00:27:41,800 Speaker 4: we got right, Like, we did it both ways, and 432 00:27:41,840 --> 00:27:44,960 Speaker 4: the quantum one was the better fit than the AI 433 00:27:45,200 --> 00:27:46,120 Speaker 4: generated one. 434 00:27:46,440 --> 00:27:49,520 Speaker 3: This is fair. Quantum is a little more of an 435 00:27:49,640 --> 00:27:52,760 Speaker 3: artist and a little less of a of a kind 436 00:27:52,760 --> 00:27:57,800 Speaker 3: of nerd AI sounds nerdy to me. What seems like 437 00:27:57,920 --> 00:28:01,639 Speaker 3: creative and artistic, creative, creative. 438 00:28:02,040 --> 00:28:07,160 Speaker 4: It's like people, Yeah, it's it opens up path that 439 00:28:07,320 --> 00:28:11,720 Speaker 4: you never knew existed. That's why when I get asked 440 00:28:11,720 --> 00:28:14,119 Speaker 4: about what do I see is the best, you know, 441 00:28:14,200 --> 00:28:18,080 Speaker 4: the the most important breakthrough that quantum is going to 442 00:28:18,160 --> 00:28:21,199 Speaker 4: allow us to do, my answer is I really don't know, 443 00:28:21,840 --> 00:28:26,840 Speaker 4: because we I You know, when other people invented these 444 00:28:26,960 --> 00:28:31,760 Speaker 4: new technologies, I don't think they really knew that they're 445 00:28:31,800 --> 00:28:34,040 Speaker 4: you know, like think of laser. I don't think the 446 00:28:34,080 --> 00:28:37,520 Speaker 4: person who invented laser thought that they will be used 447 00:28:37,560 --> 00:28:39,800 Speaker 4: to scan groceries at the grocery store. 448 00:28:39,880 --> 00:28:40,080 Speaker 5: You know. 449 00:28:40,520 --> 00:28:45,520 Speaker 4: But so technology developing technology, the way I think of 450 00:28:45,560 --> 00:28:47,600 Speaker 4: it is like having a baby. You know, you raise 451 00:28:47,680 --> 00:28:50,120 Speaker 4: it as best you can, but then they're going to 452 00:28:50,200 --> 00:28:53,800 Speaker 4: go off and do their thing, and you will be 453 00:28:54,400 --> 00:28:57,360 Speaker 4: tying them down if you restrict them to just what 454 00:28:57,440 --> 00:29:01,440 Speaker 4: you thought they should do, you know, So it. 455 00:29:02,000 --> 00:29:03,320 Speaker 5: Opens up that. 456 00:29:04,920 --> 00:29:09,880 Speaker 4: Space, that creative space for us to ask questions. 457 00:29:09,640 --> 00:29:11,520 Speaker 5: Differently than we used to. 458 00:29:11,880 --> 00:29:16,880 Speaker 4: We should train our mind to stop starting from classical 459 00:29:17,520 --> 00:29:20,200 Speaker 4: and then trying to squeeze it into quantum. We have 460 00:29:20,320 --> 00:29:24,040 Speaker 4: to learn how to think quantum up front, right from 461 00:29:24,080 --> 00:29:29,280 Speaker 4: the beginning, which we haven't really been doing as a 462 00:29:29,320 --> 00:29:33,920 Speaker 4: scientific community since our inception. We were trained, and how 463 00:29:33,960 --> 00:29:38,440 Speaker 4: do you convert what you're thinking into a formula that 464 00:29:38,920 --> 00:29:42,760 Speaker 4: you can ask from a computer which is a classical 465 00:29:42,880 --> 00:29:48,280 Speaker 4: right computer with quantum because of how it works, it 466 00:29:48,360 --> 00:29:50,920 Speaker 4: can answer questions, It can look at problems in a 467 00:29:51,000 --> 00:29:55,480 Speaker 4: very different way. So we have to think differently about 468 00:29:55,520 --> 00:29:57,440 Speaker 4: the questions and how we ask them. 469 00:29:57,760 --> 00:30:02,160 Speaker 3: With IBM, you recently modeled protein with over twelve thousand atoms. 470 00:30:02,640 --> 00:30:05,640 Speaker 3: Talk to me about that and why it's so meaningful 471 00:30:05,680 --> 00:30:07,680 Speaker 3: for drug discovery. 472 00:30:07,760 --> 00:30:12,760 Speaker 4: So in October of twenty twenty four, so just eighteen 473 00:30:12,800 --> 00:30:18,280 Speaker 4: months ago, the largest compound biological compound that could be 474 00:30:18,360 --> 00:30:25,040 Speaker 4: simulated with quantum was ten atoms big, and it was 475 00:30:25,360 --> 00:30:30,200 Speaker 4: unfathomable back then that we will get past the thousand 476 00:30:30,480 --> 00:30:36,840 Speaker 4: or few thousand atom simulation in the foreseeable future. And 477 00:30:37,240 --> 00:30:41,280 Speaker 4: what our team with IBM and with Rieken in Japan, 478 00:30:41,440 --> 00:30:48,480 Speaker 4: published last month April twenty twenty six, is a simulation 479 00:30:49,320 --> 00:30:55,200 Speaker 4: of the electrical properties of an enzyme trips in in 480 00:30:55,280 --> 00:30:59,680 Speaker 4: the body That is twelve thousand, six hundred atoms big 481 00:31:00,440 --> 00:31:04,360 Speaker 4: for you know, orders of magnitude beyond what anybody thought 482 00:31:04,640 --> 00:31:09,719 Speaker 4: was possible in that span of time. And the reason 483 00:31:09,800 --> 00:31:15,480 Speaker 4: why that happened was because of a you know, innovations 484 00:31:16,080 --> 00:31:22,400 Speaker 4: in the technology itself where the teams stopped thinking of 485 00:31:22,560 --> 00:31:27,800 Speaker 4: quantum and AI as competitors and instead thought of them 486 00:31:28,120 --> 00:31:33,280 Speaker 4: as different members of the same team. Right you're you're 487 00:31:34,080 --> 00:31:37,280 Speaker 4: We're now in basketball season in the US, the n 488 00:31:37,360 --> 00:31:39,960 Speaker 4: b A, and you need the you need defense, but 489 00:31:40,080 --> 00:31:42,840 Speaker 4: you also need your center, somebody to shoot. 490 00:31:44,000 --> 00:31:48,160 Speaker 5: You need all of the pieces to work together. 491 00:31:48,680 --> 00:31:52,760 Speaker 4: So with this, it was figuring out where do I 492 00:31:52,880 --> 00:31:55,720 Speaker 4: put you know, when do I put AI on the field, 493 00:31:55,840 --> 00:31:58,600 Speaker 4: When do I put Quantum on the field, and how 494 00:31:58,640 --> 00:31:59,880 Speaker 4: do I tell them. 495 00:32:00,200 --> 00:32:01,160 Speaker 5: To work together. 496 00:32:01,640 --> 00:32:06,800 Speaker 4: It's the scientific terms the quantum centric super computing. So 497 00:32:06,960 --> 00:32:10,720 Speaker 4: quantum is at the center, but we're using our supercomputing 498 00:32:11,080 --> 00:32:17,320 Speaker 4: tools AI classical to interact with it and split that 499 00:32:17,440 --> 00:32:22,080 Speaker 4: big problem of the twelve thousand, six hundred atoms into pieces, 500 00:32:22,480 --> 00:32:26,240 Speaker 4: where some pieces are best served with quantum and others 501 00:32:26,280 --> 00:32:27,959 Speaker 4: are best served with classically. 502 00:32:28,680 --> 00:32:33,600 Speaker 3: This distinction that we now cling to AI and quantum 503 00:32:33,640 --> 00:32:36,520 Speaker 3: are these very different things develop by different people for 504 00:32:36,560 --> 00:32:40,640 Speaker 3: different purposes. What you're suggesting is that's probably going to 505 00:32:40,680 --> 00:32:43,920 Speaker 3: go away. Yeah, in the future, these things will work together. 506 00:32:44,680 --> 00:32:47,680 Speaker 3: It's going to become teamwork and not one on one 507 00:32:47,680 --> 00:32:49,240 Speaker 3: competition exactly. 508 00:32:49,480 --> 00:32:51,760 Speaker 5: And it is that now in Keeveland, Clank. 509 00:32:51,800 --> 00:32:56,840 Speaker 4: I mean, the way we've evolved our priorities with IBM, 510 00:32:57,640 --> 00:33:01,600 Speaker 4: it's a realization that both organizations have come to where 511 00:33:02,120 --> 00:33:06,080 Speaker 4: really to for progress to happen, we should stop seeing 512 00:33:06,080 --> 00:33:11,760 Speaker 4: them as separate. We should put them together and work 513 00:33:12,440 --> 00:33:16,000 Speaker 4: to the best of what each piece of technology can provide. 514 00:33:16,320 --> 00:33:21,040 Speaker 3: One theme running through a lot of your your what 515 00:33:21,080 --> 00:33:24,840 Speaker 3: you've been talking about is that the arrival of this 516 00:33:25,080 --> 00:33:34,320 Speaker 3: new technology requires the researcher to behave differently and that's 517 00:33:34,360 --> 00:33:37,320 Speaker 3: one of the reasons why you want the quantum machine 518 00:33:37,360 --> 00:33:40,240 Speaker 3: and the on full display. And then you were talking 519 00:33:40,240 --> 00:33:42,280 Speaker 3: about how you have to ask different kinds of questions. 520 00:33:42,480 --> 00:33:46,160 Speaker 3: I'm curious, can you can you can you elaborate on 521 00:33:46,200 --> 00:33:49,640 Speaker 3: that a little bit. So take me back, for example, 522 00:33:49,680 --> 00:33:52,320 Speaker 3: to your earliest days. If I had given you all 523 00:33:52,360 --> 00:33:57,360 Speaker 3: these tools that people have now, how would your research 524 00:33:57,440 --> 00:34:00,440 Speaker 3: have proceeded differently? What would you have done differently? 525 00:34:02,280 --> 00:34:03,520 Speaker 5: You know, I would have. 526 00:34:06,080 --> 00:34:15,879 Speaker 4: Looked at the molecular components of the human brain as 527 00:34:15,920 --> 00:34:19,560 Speaker 4: they relate to outcomes of brain surgery way earlier than 528 00:34:19,600 --> 00:34:22,280 Speaker 4: I did. The first ten years of my career doing 529 00:34:22,320 --> 00:34:28,240 Speaker 4: research was all spent building models that were purely based 530 00:34:28,360 --> 00:34:30,600 Speaker 4: on brain waves. 531 00:34:31,040 --> 00:34:34,360 Speaker 5: And pictures of the brain. 532 00:34:35,600 --> 00:34:40,160 Speaker 4: It wasn't until after I hit a wall with my 533 00:34:40,360 --> 00:34:45,480 Speaker 4: models aren't getting past that eighty percent accuracy threshold that 534 00:34:45,920 --> 00:34:49,880 Speaker 4: I started thinking, oh, you know, there must be something 535 00:34:50,000 --> 00:34:54,000 Speaker 4: genetic or you know, more biological that is influencing this. 536 00:34:54,760 --> 00:34:59,840 Speaker 4: Had I been exposed to quantum at least as a 537 00:35:00,040 --> 00:35:04,120 Speaker 4: onsept right, to quantum computing and what quantum science is 538 00:35:04,840 --> 00:35:08,880 Speaker 4: back then, I think it would have opened up my 539 00:35:09,040 --> 00:35:14,000 Speaker 4: mind to realize that it's not just about what I see. 540 00:35:14,200 --> 00:35:19,759 Speaker 4: You know, there is hidden relationships that exist within the 541 00:35:20,239 --> 00:35:25,640 Speaker 4: human body, and that's our genetic makeup and our chemical 542 00:35:25,840 --> 00:35:31,719 Speaker 4: makeup that influence what comes to the surface that urge 543 00:35:31,840 --> 00:35:32,680 Speaker 4: to dig deeper. 544 00:35:33,320 --> 00:35:34,880 Speaker 5: The other thing, it would have changed. 545 00:35:35,000 --> 00:35:37,839 Speaker 4: Is it would have made me reach out to engineers 546 00:35:37,880 --> 00:35:43,760 Speaker 4: and physicists and mathematicians much earlier in my career. 547 00:35:44,000 --> 00:35:48,640 Speaker 3: Yeah, yeah, yeah. And how would it have changed is 548 00:35:48,680 --> 00:35:52,040 Speaker 3: a very kind of prosaic question, but just kind of 549 00:35:53,000 --> 00:35:55,800 Speaker 3: the day to day life of someone doing medical research. 550 00:35:55,920 --> 00:35:59,120 Speaker 3: I mean, the oh wow, you walk into the office 551 00:35:59,120 --> 00:36:02,160 Speaker 3: in the morning. How does your day proceed differently when 552 00:36:02,160 --> 00:36:06,200 Speaker 3: you're when you have these kinds of tools at your fingertips. 553 00:36:07,960 --> 00:36:13,319 Speaker 4: That's the fundamental question in biomedical research right now, and 554 00:36:13,400 --> 00:36:16,279 Speaker 4: it's it's less to do with quantum, more to do 555 00:36:16,440 --> 00:36:21,720 Speaker 4: with agentic AI, right, these agents that we can work 556 00:36:21,760 --> 00:36:26,160 Speaker 4: with now to help us how to think more creatively 557 00:36:26,640 --> 00:36:32,080 Speaker 4: and how to do work that up until now was 558 00:36:32,200 --> 00:36:36,319 Speaker 4: more like Scott work that the researchers had to do, 559 00:36:36,480 --> 00:36:40,799 Speaker 4: whether it was you know, so the hypothesis generation has 560 00:36:40,840 --> 00:36:45,719 Speaker 4: always been the most creative part of aspect of scientific research. 561 00:36:46,480 --> 00:36:50,360 Speaker 4: But what comes after it with the data collection, for example, 562 00:36:50,520 --> 00:36:57,120 Speaker 4: that was always such a repetitive, you know, exercise, and 563 00:36:57,160 --> 00:37:02,040 Speaker 4: then the analysis after that was something that was very 564 00:37:02,160 --> 00:37:06,000 Speaker 4: resource intensive and you had to try so many different 565 00:37:06,040 --> 00:37:10,000 Speaker 4: approaches before you get to an answer, and that was 566 00:37:10,239 --> 00:37:18,000 Speaker 4: fairly complex. Now with access to urgantic AI and you know, 567 00:37:18,120 --> 00:37:23,359 Speaker 4: some quantum. Of course, we can spend more of our 568 00:37:23,640 --> 00:37:28,640 Speaker 4: energy on the creative thinking part of the aspect of 569 00:37:28,719 --> 00:37:34,640 Speaker 4: the work and less on the you know, just that repetitive. 570 00:37:34,360 --> 00:37:38,120 Speaker 3: When you look around, I'm assuming you walk around Cleveland 571 00:37:38,160 --> 00:37:41,160 Speaker 3: Clinic and you have lots of conversations with some of 572 00:37:41,160 --> 00:37:45,120 Speaker 3: the most brilliant medical researchers in the world. Are you 573 00:37:45,280 --> 00:37:50,440 Speaker 3: satisfied with how quickly and aggressively they are adopting these 574 00:37:50,440 --> 00:37:54,080 Speaker 3: new technologies or do they still need encouragement from you 575 00:37:54,160 --> 00:37:57,520 Speaker 3: to do you have to say that? People? Wait, I've 576 00:37:57,520 --> 00:38:00,279 Speaker 3: got this machine in the cafeteria. You should be using 577 00:38:00,320 --> 00:38:01,200 Speaker 3: it for this problem. 578 00:38:01,920 --> 00:38:03,000 Speaker 5: How much are you doing. 579 00:38:02,840 --> 00:38:06,000 Speaker 3: That kind of encouraging in cheerleading or is it unnecessary? 580 00:38:07,120 --> 00:38:12,160 Speaker 4: No, there's plenty of cheerleading that's necessary people. You know, 581 00:38:13,200 --> 00:38:18,120 Speaker 4: humans don't like to change. It's hardwired in us. So 582 00:38:18,560 --> 00:38:23,120 Speaker 4: there is plenty of cheerleading. But what happens is, i 583 00:38:23,120 --> 00:38:27,000 Speaker 4: mean the way we built our program to where we 584 00:38:27,040 --> 00:38:30,920 Speaker 4: are now, So Cleveland Clinic now is pretty much winning 585 00:38:31,040 --> 00:38:35,720 Speaker 4: every global competition. And Quantum for life sciences, whether that's 586 00:38:35,760 --> 00:38:41,359 Speaker 4: the welcome trust, you know, Quantum for biological applications. We 587 00:38:41,880 --> 00:38:45,400 Speaker 4: our partner, there was a startup in Finland, Algorithmic. 588 00:38:45,480 --> 00:38:46,200 Speaker 5: They're brilliant. 589 00:38:46,320 --> 00:38:49,920 Speaker 4: We worked with them to develop a photodynamic drug therapy 590 00:38:50,040 --> 00:38:54,520 Speaker 4: for cancer or whether it is the NIH with they 591 00:38:54,520 --> 00:38:59,719 Speaker 4: had an X price challenge for quantum or university is 592 00:38:59,760 --> 00:39:03,800 Speaker 4: that we're collaborating with. We have a program that's bringing 593 00:39:03,880 --> 00:39:07,040 Speaker 4: startups to our ecosystem. We give them access to the 594 00:39:07,080 --> 00:39:11,200 Speaker 4: machine if they have a question that is significant enough 595 00:39:11,239 --> 00:39:17,960 Speaker 4: for life sciences universities that we're building a bachelor's, master's, 596 00:39:18,000 --> 00:39:23,120 Speaker 4: PhD programs with on quantum computing. We developed that whole 597 00:39:23,960 --> 00:39:28,279 Speaker 4: ecosystem around it. If that's not cheerleading, I don't know 598 00:39:28,320 --> 00:39:33,040 Speaker 4: what else would qualify for cheerleading. But then what happens 599 00:39:33,280 --> 00:39:38,319 Speaker 4: is these early adopters, the risk takers, become the cheerleaders themselves, right, 600 00:39:38,440 --> 00:39:42,080 Speaker 4: and then they work with it, they achieve success, and 601 00:39:42,239 --> 00:39:47,839 Speaker 4: we're nothing but competitive in medicine and science. Right, So 602 00:39:47,880 --> 00:39:49,839 Speaker 4: then it becomes okay, so and so I did this 603 00:39:49,880 --> 00:39:52,440 Speaker 4: with this machine, Let me learn it so I can 604 00:39:52,520 --> 00:39:56,880 Speaker 4: do the same. And it becomes this virtuous cycle of 605 00:39:57,120 --> 00:40:03,280 Speaker 4: then innovation and growth and people wanting to work together. 606 00:40:03,480 --> 00:40:05,560 Speaker 5: It's just been fascinating to watch. 607 00:40:06,440 --> 00:40:09,759 Speaker 3: You said that people don't like change, but you clearly do. 608 00:40:10,480 --> 00:40:14,279 Speaker 5: I do. That's the mindset of researchers, right. 609 00:40:14,360 --> 00:40:17,600 Speaker 4: A researcher is someone who is not afraid to fail, 610 00:40:18,080 --> 00:40:21,360 Speaker 4: actually sees failure as a chance to learn something right, 611 00:40:21,680 --> 00:40:26,160 Speaker 4: to do better the next time. So we get rejected 612 00:40:26,200 --> 00:40:28,520 Speaker 4: all the time and we don't care, right, we keep 613 00:40:29,000 --> 00:40:31,319 Speaker 4: moving on with papers. 614 00:40:30,800 --> 00:40:36,879 Speaker 5: Grant applications. So that mindset is what all of. 615 00:40:37,000 --> 00:40:43,680 Speaker 4: Research is built around. So it's a very forward looking mindset. 616 00:40:43,760 --> 00:40:46,400 Speaker 4: And Cleveland Clinic as they health system, we wouldn't have 617 00:40:46,440 --> 00:40:49,799 Speaker 4: survived one hundred years. We wouldn't have done all of 618 00:40:49,840 --> 00:40:54,920 Speaker 4: the firsts that we had. Serotonin the chemical that drives 619 00:40:54,960 --> 00:41:01,000 Speaker 4: the whole science of psychiatry and neuroscience that was discovered 620 00:41:01,239 --> 00:41:06,320 Speaker 4: in Cleveland Clinic. So as an organization, we have enough 621 00:41:07,239 --> 00:41:10,640 Speaker 4: of people who think that way that they will be 622 00:41:10,840 --> 00:41:16,120 Speaker 4: the early adopters who will pull the others with them. 623 00:41:16,440 --> 00:41:23,719 Speaker 3: Yeah, one last question, look ahead ten years, pat me 624 00:41:23,760 --> 00:41:28,040 Speaker 3: a picture of what quantum and related technologies look like 625 00:41:28,120 --> 00:41:30,320 Speaker 3: for a place like Cleveland Clinic and tenures. 626 00:41:31,719 --> 00:41:35,600 Speaker 4: Well, what I hope is that ten years from now, 627 00:41:36,280 --> 00:41:39,200 Speaker 4: if I if I'm seeing a patient in clinic who 628 00:41:39,239 --> 00:41:43,000 Speaker 4: has bad epilepsy, and for the love of you know, 629 00:41:43,080 --> 00:41:46,440 Speaker 4: I can't figure out what medicine do I need to 630 00:41:46,480 --> 00:41:50,359 Speaker 4: prescribe to them to make them seizure free. I will 631 00:41:50,400 --> 00:41:52,840 Speaker 4: be able to send them to get a blood test 632 00:41:54,080 --> 00:42:00,400 Speaker 4: that we can then run through some analytical platform that 633 00:42:00,520 --> 00:42:06,560 Speaker 4: leverages both quantum and AI that can model exactly for 634 00:42:06,640 --> 00:42:11,040 Speaker 4: that patient what compound, either existing. 635 00:42:10,920 --> 00:42:12,400 Speaker 5: Or not to be developed. 636 00:42:12,680 --> 00:42:16,520 Speaker 4: It's some new chemical that we haven't tested for that 637 00:42:16,680 --> 00:42:22,799 Speaker 4: indication yet is going to treat them, you know, make 638 00:42:22,920 --> 00:42:29,160 Speaker 4: them seizure free. It's and I think quantum is ideal 639 00:42:29,760 --> 00:42:33,520 Speaker 4: for a condition like mine epilepsy, because we are a 640 00:42:33,600 --> 00:42:37,279 Speaker 4: rare disease, and I think that benefit that it's going 641 00:42:37,400 --> 00:42:40,000 Speaker 4: to have will start with rare diseases, you know, as 642 00:42:40,040 --> 00:42:43,960 Speaker 4: I explained earlier, So take any other rare disease. We 643 00:42:44,000 --> 00:42:48,080 Speaker 4: should start there and then expand from that to more 644 00:42:48,200 --> 00:42:52,640 Speaker 4: complex things like cancer for example, and others. But those 645 00:42:52,760 --> 00:42:57,440 Speaker 4: rare conditions where we are left now completely scratching our 646 00:42:57,520 --> 00:43:04,560 Speaker 4: heads and going intuition. It will make our care truly precise, 647 00:43:05,239 --> 00:43:10,600 Speaker 4: and it will make drug development a more tailored exercise 648 00:43:12,239 --> 00:43:15,600 Speaker 4: than the way it is now, where it's like a 649 00:43:15,719 --> 00:43:17,839 Speaker 4: hammer that's looking for nails? 650 00:43:18,200 --> 00:43:19,880 Speaker 3: Am I right in thinking that of all of the 651 00:43:20,040 --> 00:43:21,880 Speaker 3: over the one hundred year history or more now of 652 00:43:22,440 --> 00:43:25,319 Speaker 3: Cleveland clinic, this sounds like the absolute best time to 653 00:43:25,320 --> 00:43:26,120 Speaker 3: be a Cleveland clinic. 654 00:43:26,400 --> 00:43:33,399 Speaker 5: Yeah. I love it. No complaints, no complaints, And I 655 00:43:33,440 --> 00:43:34,120 Speaker 5: am hiring. 656 00:43:34,400 --> 00:43:39,799 Speaker 7: I need I need those quantum researchers, those people who 657 00:43:39,800 --> 00:43:43,960 Speaker 7: are wanting, you know, to apply quant to genetic research, 658 00:43:44,080 --> 00:43:48,960 Speaker 7: imaging research, every single aspect of biomedical research. 659 00:43:49,400 --> 00:43:52,839 Speaker 4: We can't afford to just wait on the sideline and 660 00:43:54,400 --> 00:43:57,239 Speaker 4: until the technology is ready and then you know, then 661 00:43:57,320 --> 00:43:59,480 Speaker 4: it will teach us. It is ready now that twelve 662 00:43:59,520 --> 00:44:04,600 Speaker 4: thousand Atham Sam relation wouldn't have happened just a year 663 00:44:04,640 --> 00:44:05,239 Speaker 4: and a half ago. 664 00:44:05,400 --> 00:44:06,560 Speaker 5: It's quidinn. 665 00:44:07,360 --> 00:44:09,680 Speaker 3: So the headline of this conversation is we're hiring. 666 00:44:10,719 --> 00:44:15,160 Speaker 5: Yes, Yeah, that's a good headline. We're growing, how about that. 667 00:44:19,480 --> 00:44:23,280 Speaker 3: Smart Talks with IBM is produced by Matt Ramano, Amy Gains, McQuaid, 668 00:44:23,680 --> 00:44:27,760 Speaker 3: Trina Menino and Jake Harper. Engineering by Nina Bird Lawrence, 669 00:44:27,840 --> 00:44:32,000 Speaker 3: Mastering by Sarah Buguerer, Music by a Gramoscope, Strategy by 670 00:44:32,080 --> 00:44:37,200 Speaker 3: Cassidy Meyer, Sophia Derlon and Tatiana Lieberman. Special thanks to 671 00:44:37,280 --> 00:44:42,880 Speaker 3: doctor Laura Jahi, Alicia Real Cooney, and the Cleveland Clinic team. 672 00:44:43,120 --> 00:44:45,800 Speaker 3: Smart Talks with IBM is a production of Pushkin Industries 673 00:44:46,080 --> 00:44:50,200 Speaker 3: and Ruby Studio at iHeartMedia. To find more Pushkin podcasts, 674 00:44:50,520 --> 00:44:54,719 Speaker 3: listen on the iHeartRadio app, Apple Podcasts, or wherever you 675 00:44:54,840 --> 00:44:58,360 Speaker 3: listen to podcasts. I'm Malcolm Gladwell. This is a paid 676 00:44:58,440 --> 00:45:03,160 Speaker 3: advertisement for IBM. The conversations on this podcast don't necessarily 677 00:45:03,200 --> 00:45:08,680 Speaker 3: represent IBM's positions, strategies, or opinions.