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