Cardiac Digital Twins:
Inside the Research Lab

Introduction to Cardiac Digital Twins and Dr. Joe Alexander's Background

Michael Krigsman: Today, we go inside a research lab building cardiac digital twins, a computational replica of your heart that could transform personalized medicine and how doctors treat heart failure.

Our guest is Dr. Joe Alexander, director of the Medical and Health Informatics Lab from NTT Research. I'm Michael Krigsman. Welcome to a fascinating episode number 902 of CXOTalk.

Dr. Joe Alexander: The Medical and Health Informatics Lab belongs to NTT Japan, and that company put a Bell Labs-type innovation company in Silicon Valley called NTT Research.

The original 3 labs for NTT Research are a physics lab, a cryptography group, and my group, which is medical and health informatics. We work on moonshot ideas. The physics group is working on quantum computing. Cryptography is working on even post-quantum cryptography, and my group is working on bio-digital twins.

Michael Krigsman: How did you end up where you are now?

Dr. Joe Alexander: Despite growing up poor in Alabama during the Civil Rights Movement, I found myself in a chemical engineering program at Auburn University. Once at a summer job, I was in a hot oil explosion, and as a burn patient, that's what introduced me to medicine.

The physicians who took care of me were from Johns Hopkins, as it turned out. I went back to Auburn, said, "I want to go to medical school. I want to go to Johns Hopkins," and somehow that worked out. Johns Hopkins is where I learned about biomedical engineering and cardiovascular dynamics, and I did a combined MD-PhD program at Johns Hopkins.

Michael Krigsman: You just came out with, "Hey, I want to go to Johns Hopkins," and what was their reaction? It's not a common request.

Dr. Joe Alexander: I had been purely in the chemical engineering program, so I went to the pre-professional advisory committee and gave that very specific request, and they laughed at me and said, "We've never sent anyone to Johns Hopkins." But as it turned out, things worked out for me.

Understanding Biological Digital Twins and Their Applications

Michael Krigsman: Tell us about the work that you're doing. What is a biological digital twin?

Dr. Joe Alexander: We take our examples mostly from the aviation, commercial aviation industry, where they build a mathematical representation of every jet engine. When that engine is flying in the air, there's a replica on the ground that's taking note of all kinds of sensors that are recording information in flight and mathematically incorporating those into the model.

What that does for commercial aviation is that it makes it possible to do predictive maintenance of the engines. You don't have to have a scheduled maintenance. The computer simulation tells you when it's time to maintain what.

Analogously, we thought that if patients are appropriately instrumented, we had enough data from wearable technologies or elsewhere, we could predict when a patient needs some kind of intervention. That set us on the road to predictive health maintenance and the building of a bio-digital twin.

Michael Krigsman: So the inspiration then came from aerospace?

Dr. Joe Alexander: That's correct.

Michael Krigsman: Can you talk about the clinical problems that you're actually trying to solve? Then we'll get into the discussion, the complexities around building a biological digital twin.

Dr. Joe Alexander: The core problem is that we want to improve cardiovascular outcomes because cardiovascular disease is the number one killer globally accounting for about twenty million lives in the year twenty twenty-two.

The way we want to go about it is to make use of mathematical modeling and simulation to tailor a model that's specific to an individual so that patient can have the very best outcomes. currently, we rely on clinical trials that are population-level data and usually there are many populations that don't get included in the clinical trials, and we're not totally sure that the results apply.

Michael Krigsman: When you talk about tailoring specific results to a specific patient, generally, as you indicated, you do large population studies and then take a solution like a medication and apply it to a large group, but you're drilling down. Can you talk about that?

Dr. Joe Alexander: We use models that are causal, that we understand mechanisms for, that are physiological so that we can have insights into how those models behave. We found that for us, rather than go to sophisticated models that have to do with computational fluid dynamics and finite element-type analysis, which are computationally expensive, we develop simple models that allow insights.

Our particular structure of model is called an electrical analog model, meaning that the flow of blood is analogous to the flow of ions, pressures are analogous to voltages, valves are analogous to diodes. We put together a structure representing the entire circulatory system and try to match the parameters in that model to an individual patient.

Michael Krigsman: So it's not just a model of the heart, but it's an entire cardiovascular model. Is that a correct way to put it?

Dr. Joe Alexander: That's correct. It's an entire cardiovascular model where we have more specific models for the heart and the coronary circulation.

That cardiovascular model also has the necessary components to do what we want to do at the moment, which is to manage acute myocardial infarction and acute heart failure. What that means is that that same simple cardiovascular system has to have lungs, it has to have kidneys, it has to have neural regulation.

Michael Krigsman: So it's a very broad-based model that you're creating. So it's far more complex than simply creating a simulation of the heart, for example.

Dr. Joe Alexander: That's correct.

Developing Autonomous Closed-Loop Intervention Systems

Michael Krigsman: Can you drill down into your vision of the digital twin and of the way that you're designing the solution? Give us some insight into what you're doing, how you're doing it, the challenges and so forth.

Dr. Joe Alexander: One of the easiest ways to consider the advantages of this sort of approach is a use case, which is autonomous closed-loop intervention system, which you mentioned in the introduction. This is a situation where we're trying to introduce a system that manages acute myocardial infarction and acute heart failure.

After the patient comes to the emergency room, goes to the cardiac catheterization lab and the culprit lesion is relieved, then they're brought to the CCU or ICU, and they're treated with certain drugs to stabilize the patient and have the heart rest and recover from having had that heart attack.

Those drugs consist usually of something we call catecholamines to help the heart contract, nitrates to reduce blood pressure, diuretics to remove blood volume. These things are given serially by a physician who monitors the patient's response.

What we're doing with the autonomous closed-loop intervention system, or what we aim to do, is to have a system where you just type into the keyboard the desired left atrial pressure, cardiac output, systemic arterial pressure, then a system of syringes filled with each of the necessary agents automatically delivers the amount of drug that's necessary to achieve those desired endpoints.

Then we monitor the patient's response, feed that back to our system, and depending on the error between what we told the machine, the syringes to give and the patient's response, we make an adjustment. This is a feedback control system for delivering care that's specified at the keyboard in terms of desired left atrial pressure, cardiac output, and arterial pressure.

Michael Krigsman: How is this different from existing models? I mean, there are machines that deliver drugs, so what makes this unique?

Dr. Joe Alexander: Anesthesiology is a field where there's some level of automation in the delivery of drugs to maintain blood pressure in patients who are undergoing operations. The thing that we're doing that no one else has done, and it's a very challenging thing, is to control not just blood pressure, but cardiac output and left atrial pressure, and to do these in such a way as to minimize myocardial oxygen consumption.

The whole point is that the heart needs to relax and recover, yet the periphery needs to be perfused. If we can let the heart work the least possible while achieving all these things, then that's the best situation for myocardial recovery. Minimization of myocardial oxygen consumption is the special thing that no one has been able to achieve.

Michael Krigsman: What are you doing that you hope will allow you to achieve this?

Dr. Joe Alexander: We have the benefit of some consultants and some work that gives us a way to monitor and quickly measure myocardial oxygen consumption live. We also have some physiological construct based on cardiac output venous return surface that lets us do a good job of maintaining left atrial pressure at a specific range.

At the same time, we regulate right atrial pressure. The combination of the cardiac venous return surface and technologies to instantaneously track or periodically track myocardial oxygen consumption are some of the benefits, but there's some other techniques that we have as well.

Michael Krigsman: Folks, you can ask questions. If you're watching on LinkedIn, pop your questions into the LinkedIn chat. If you're watching on Twitter, X, use the hashtag CXOTalk and ask Dr. Alexander pretty much whatever you want.

Introduction to Digital Twin and Cardiovascular Focus

Michael Krigsman: Now is a special opportunity to do that. Joe, how does what you were just describing then relate back to the digital twin?

Dr. Joe Alexander: My lab is interested in the human digital twin. We started with cardiovascular system because we have expertise and it's number one killer globally, and we thought it's a good place to start. As well as the fact that the cardiovascular system, even attacking something like acute myocardial infarction, it makes it necessary to consider other organ systems like the lungs and the kidneys and neural regulation.

Development and Functionality of the Autonomous Closed-Loop System

Dr. Joe Alexander: This autonomous closed-loop intervention system, the first guess is given by our electrical analog model of the human cardiovascular system that best fits the particular patient who walks in. Now, how do we determine the best electrical analog model for the patient that we see lying in front of us?

That relies on huge amounts of population-level data to start with, where we build a virtual population of patients that are similar to the patient that walks in in terms of age and conditions, comorbidities, et cetera. We build a virtual population similar to that patient. Based on specific characteristic, we narrow in on the best guess, and that might be several hundred patients that are close to this patient. We use that to get the initial first guess on this closed-loop, autonomous closed-loop intervention system.

Because it's a feedback system, it will automatically adjust those parameters to give the specified left atrial pressure, cardiac output, arterial pressure. Mind you, that information in the error signal, the correction signal that's being fed back, that teaches the model of that patient what those parameters should be.

The model becomes more and more specific for that patient as therapy is administered through this autonomous closed-loop intervention system. It both zeros in on the best parameter choices and at the same time teaches us what the best parameter choices are for that patient. We will create a registry including that patient and those choices.

Michael Krigsman: So you are gathering broad population data and then isolating out of that broad group for each individual patient the right subset of data that most closely corresponds to that particular patient's situation, and then from there, you're building the digital twin of that specific patient. Is that a correct way to say it?

Dr. Joe Alexander: That's very correct. We think of the digital twin as a system of characteristics that represent a patient. Characteristics like resistors, capacitors, diodes, and so forth. We want those parameters, the best choices that most represent that patient and that patient's characteristics.

We begin with population-level data that's in the literature, and from there we build a virtual population that is relevant for this particular patient. From within that virtual population, we find the closest patients for that patient. Then we begin this process of driving the autonomous closed-loop intervention system. In the course of that feedback regulation and adjustment, then we learn to titrate or tune those parameters to match that particular patient.

Michael Krigsman: What kinds of data are you using as inputs into all of this?

Dr. Joe Alexander: In the world of cardiovascular bio digital twins, there are many places we could have started. We started with acute myocardial infarction, acute heart failure, mostly because it's acute and mostly because the patients will be in the ICU or CCU and heavily monitored and heavily instrumented, where we have readings of dynamic signals like dynamic pressure, pressures and volumes, and we have echocardiography. We have a lot of time-dependent signals that we can use to train our models and patient and set those parameters and gather data.

The inputs in the ICU, CCU are measurements of left atrial pressure, right atrial pressure, cardiac output. We can do Swan catheters. We can monitor pressure over periods of time. Usually the admission for that patient is about 4 or 5 days. We can have 4 or 5 days of acute information to tune to that particular patient.

We chose the easiest option, to be honest, as a place to begin. When you go to chronic heart failure, you have to rely on data from patients that are not in the hospital, and they're static measurements, and they're based on wearable technologies, not nearly invasive enough to parameterize such a system. We'll go to chronic heart failure next.

Validation, Challenges, and Ethical Considerations

Michael Krigsman: Where are you in the process of this set of developments?

Dr. Joe Alexander: We have a group of collaborators. The ones most relevant to what we're talking about today are a group at the National Cardiovascular Center in Japan, where they have cardiologists, anesthesiologists, experimentalists, and are able to do animal experiments with animals ranging in size from mice all the way up to cows. We're doing animal experimentation to validate these approaches and test out these technologies.

Last year, for the first time ever, we demonstrated the proper functioning of an autonomous closed-loop intervention system to treat heart failure in an experimental animal, a dog, that had experimentally induced heart failure, and the system compensated and automatically treated that dog while minimizing myocardial oxygen consumption.

We're at a stage now where we're collecting a number of experiments from animals where we'll prove, or we intend to prove that the autonomous closed-loop intervention system outperforms the standard of care by showing that these cardiologists and their treatment compared to the autonomous system cannot yield such a small myocardial infarct size as what we can get from the autonomous closed-loop intervention system. Reduction in infarct size would be physical evidence of how this system could outperform clinicians, and that's what we intend to do.

Michael Krigsman: The autonomous system then is relying on this general population data plus very detailed data coming from the particular patient who is in the ICU or the CCU, because there's lots of data, and your findings so far are a greater degree of accuracy. And accuracy in what specifically that is producing the result?

Dr. Joe Alexander: We are still in the very early stages and developing what we can do in the real-life clinical situation. All of what I'm saying is based on hopes that depend on what we've been able to validate and verify in animal experiments. We're still at the animal experimentation phase. We are not looking at population-level data in animals. We're even beginning without that kind of referenced model of parameters for animals, except what we can get from the literature very simply. Still this autonomous system is able to perform. We demonstrated last year.

But your description of the process is correct. That's what we hope to achieve. There are many challenges, as you can imagine. Again, we're at the early stages achieving this in animals. Before we get anywhere near regulatory approval, we have to go through, and I'm sure you're aware of these types of hurdles, we have to use this kind of system to do clinical decision support before we can go to complete autonomy.

That means the feedback would be going through a physician. The physician would be in this closed loop, and we'd advise the physician, and the physician would make a decision whether to do what the software says or not. We have many things to achieve before I can really answer your question well.

Michael Krigsman: I guess similar to autonomous vehicles, before you let a fleet of autonomous taxis on the road, you have a driver in the car because you really don't know what's gonna happen until you do it, try it because it's new. So it's basically the same concept.

Dr. Joe Alexander: That's exactly right. Some people have suggested that we not call it autonomous intervention, but like a co-pilot system. But we're ambitious in thinking that this kind of a system can replace the need for a specialist to be at the patient's bedside. It could be a system that's monitored by another clinical professional, but probably will not need a specialist, which makes it accessible to kind of remote hospitals with fewer resources. That's part of our vision for this is health equity.

Michael Krigsman: We have an important question from Twitter, from Arsalan Khan, who's a regular listener. He always asks excellent questions, and he says this. This is a very good way into getting to dive into the ethical and equity aspects of this. He says this, "How do you make sure data from these medical instruments is correct and the doctor makes the right decision based on the data versus his or her personal experience?"

Dr. Joe Alexander: My bias, to be honest, and one clinician made this comment, he said that he'd rather have an autonomous system that's focusing beat to beat on adjusting meds for a patient than to have an exhausted resident standing in the hallway checking his phone and doesn't have enough time to lookin on the patient. We had the bias that if the system is built correctly, then it will correct even for errors that the physician might make.

But it's necessary, like you described, for levels of autonomy in vehicles to have that supervision. FDA is not going to approve an autonomous device no matter how well it's tested without that step of clinical decision support.

The Role of Physicians and AI in Healthcare

Dr. Joe Alexander: We can't take the physician out of the loop.

Michael Krigsman: And then we have another related question from Lisbeth Shaw, who says, "How do you know you can trust the model and then the decisions? In healthcare, the standard is let AI guide you, but the doctor should make the decision."

Dr. Joe Alexander: Yes, it's related. Our first pass is to include the doctor in the loop so the doctor can judge what the system is telling him or her. Let me just say that the thing about our system that's different from AI is that it's causally based. Even though cardiologists don't know as much physiology as they once did, the decisions that would be coming out of our system would be based on clinical practice, cardiovascular physiology, cardiovascular dynamics, and it won't be a black box deep learning type output that cannot be reviewed and criticized.

Michael Krigsman: I'm a technologist, and I absolutely support AI and autonomous systems when they're used properly with the right type of governance. But if we look, for example, at the Boeing 737 Max crashes that were caused by faulty sensor algorithms and then incorrectly documented or incompletely documented recovery procedures, it's an example of an autonomous life and death system. The idea of having this kind of autonomous system relating to medicine is kind of scary.

Dr. Joe Alexander: There are certainly lessons to be learned, and some of the lessons are avoiding shortcuts, and some of the lessons have to do with hubris. Certainly fail-safe mechanisms have to be built in, and certainly you don't want to put critical components in the hands, at least I don't, of AI.

The short answer is the work we do is a beautiful dance between creativity and skepticism, and we're skeptical always, and we really don't trust and certainly don't fully rely on systems like AI. Or I would say we depend on AI for particular and certain algorithms for particular applications or particular aspects. That's why our approach is crucially causal and mechanistic and based on physiology so that we can see better than what is being called, I guess, explainable AI.

Explainable AI doesn't give the kinds of explanations that cardiologists understand in terms of physiology and mechanisms, and we do provide those. There will be rationales for what our systems would advise the physician when the physician is in the loop. Now when the physician is not in the loop, then we can't say that the system will be perfect all at once, but we'll certainly be designing with safety in mind and risk.

Clinical Trials and Risk Management in AI-Driven Healthcare

Dr. Joe Alexander: I should also just mention that some of the deeper questions that have to do with testing, implementation, they will involve large-scale clinical trials just like drugs. The same questions that are being raised about algorithms and how do you know if they're safe or not, you know, can be raised about drug development.

We accept the results of clinical trials even when we see these commercials saying that there's a risk of death with some of the medications under certain conditions and that were proven in the trial. There is no perfect solution without some level of risk, and the goal will be to minimize those risks.

As entity research is Bell Labs type moonshot ideas place, we're looking to develop proof of concept to develop a regulatory strategy and to hand off to those companies, to industry that knows how to go into that risk safety environment, like pharmaceutical companies, like medical device companies. We haven't touched on medical devices, but everything I'm describing about drug treatment also applies to the management of devices controlling patients who are more severely ill.

So we'll be looking to partner with pharmaceutical companies, medical device companies that are able to afford, that have expertise in ethical aspect, safety aspects, and conducting those, affording those large-scale clinical trials. Then we'll move on to the next place where we can paint beautiful pictures and brilliant landscapes on our small prison walls.

Causal and Mechanistic Models in Healthcare Systems

Michael Krigsman: You mentioned several times that your work is causal and mechanistic. Can you dive into that and explain what you mean in comparison to things that are not causal or mechanistic?

Dr. Joe Alexander: If we think about a patient who has heart failure, heart failure usually in patients end up with some degree of renal failure. The renal failure causes an increase in volume retention. The volume retention means that you get fluid in the circulatory system that flows back to the lungs, and you get fluid in the lungs.

Fluid in the lungs, elevation of left atrial pressure, means that you have poor oxygen diffusion capacity, so you don't get as much oxygen across the lungs into the circulatory system. Because you don't have as much oxygen, the heart has to pump harder and faster because in order to deliver enough oxygen to perfuse the tissues, in order to do that, the heart has to work harder.

This patient with heart failure, that patient's heart has to work harder and consume more myocardial oxygen. It needs more oxygen, but it can't get more oxygen. So the heart is feeding itself, but it can't get enough oxygen to feed itself, and you quickly deteriorate. That is a sequence of events set in place by various causes that originate with heart failure.

That's different from, for example, having some speckle tracking images that are fed into AI and making some hypothesis from that alone about why a patient is not ventilating well. That for me is pattern recognition with an attempt to extrapolate to causality. But this sequence of events I just described, which also by the way includes anemia and which exacerbates the situation more, these are all things known physiologically and mechanistically to play significant roles in heart failure.

All of the drugs that have been developed are mostly addressing these various aspects, diuretics to relieve, remove volume, catecholamines to improve contractile function. But at some point, the cost in myocardial oxygen consumption is just really the last draw for a patient with chronic heart failure. It's very, very serious.

Michael Krigsman: The intervention that your system is doing, correct me if I'm wrong, is injecting certain types of medications in precisely the right dosages and the right times. Is that correct or is there more to it?

Dr. Joe Alexander: That's correct for our particular use case of acute myocardial infarction, acute heart failure, where we have control over everything and we're measuring everything. It does those injections to manage the acute case. But the best we can expect for that autonomous closed-loop intervention system is the acute case, and so a 4 or 5 day hospital stay. It doesn't give us some knowledge that is helpful in the chronic case when the patient is not in the hospital.

We have some starting places, but we need much more data. We need much more laboratory chemistry. We need to be monitoring patients with wearable technologies and so forth over longer periods of time. However, we expect that the excellent care in the acute situation will have benefits for the patient when they're released from the hospital. They won't be readmitted. For example, the readmission rate we expect will be less or would be over a longer period of time compared to the standard of care.

Michael Krigsman: You described earlier the analogy of an electrical system with diodes and resistors. As I was reading through some of your papers and presentations, I was struck by these electrical diagrams. I mean, literally like schematic diagrams that you'd see for electrical devices. Can you tell us more about that aspect?

Dr. Joe Alexander: When we look at that diagram, we see what looks like electrical circuits. The circulatory system is a circuit, and so that part, it kind of works for us naturally. Actually, elements in that electrical analog diagram represent left ventricular contraction, right ventricular contraction, atrial contractions. The person who is familiar with those symbols can see the entire circulatory system represented there, but they're represented very simply.

For example, just to give you a notion, the left ventricle ejects into the systemic arterial system across the aortic valve. So for us, the left ventricle is a capacitor where for a certain volume, you know, it generates a certain force. We call it a time-varying capacitor because we let the capacitor level change or let the ventricle become stiffer to generate pressure. That pressure in the electrical analog sense is a voltage.

That voltage in the heart, in that left ventricle, gets higher than what's downstream across the valve, then that valve will open or that diode will open, and flow will go out of the diode or across the aortic valve into another set of resistors and capacitors, which we say represent the systemic arterial system.

So resistance in the electrical analog network is the relationship between flow and pressure in the real system. A capacitor in that electrical analog network is representation between volume that goes into an elastic artery. It stretches the wall of the artery, and that generates a certain pressure. So by a series or system of resistors and capacitors and diodes representing different compartments around the arterial, systemic arterial system, the venous systemic venous system, the pulmonary arterial system, the pulmonary venous system, we can represent the entire, simply represent and I know simple is a relative term, but simply represent the entire circulatory loop in the essential measurements or parameters or variables that are important for our application to acute myocardial infarction and acute heart failure.

Michael Krigsman: How does this type of representation interplay with the creation of the digital twin?

Dr. Joe Alexander: This representation is our digital twin is a mathematical representation of that patient in these terms. Now, what I described to you was the simple circulatory loop.

Understanding Coronary Circulation and Cardiac Metabolism

Dr. Joe Alexander: We have other subsystems that are more specialized that are not represented in probably the diagrams you looked at that represent the coronary circulation. Now, if you think about the heart, the heart generates a pressure and it generates a flow. That flow goes into the systemic arteries across the aorta. But that same aorta has a coronary circulation that supplies blood to the heart itself. That's why I say the heart feeds itself in supplying its own blood supply. That coronary circulation has a little more sophistication that we need to account for.

If there's autoregulation of coronary flow, we need to account for that. When the heart beats, it squeezes the vessels surrounding it, so it squeezes its own coronary vessels. We need to account for that in describing what flow gets to an ischemic heart. We have to do a more sophisticated model drilling in on the heart and its metabolism.

Now it turns out that myocardial oxygen consumption, cardiac metabolism has been thoroughly described in simple terms that relate to pressure and volume mechanics. Again, those signals that we're measuring all the time, we're interested in pressures and volumes. You can measure, you can use a pressure volume loop to represent the mechanics of a chamber of the heart, where the slope of the pressure volume relationship is an index of the ability of the heart to contract.

So a simple index of the ability of the heart to contract can be derived by pressure volume measurements as well, those same simple signals. The areas in various aspects for the pressure volume can show potential energy of the heart, the work that the heart does, and they correlate with myocardial oxygen consumption. So there's a tremendous amount of data about the heart that's implicit in the way that we study it using pressures, flows, and volumes.

Electrical Analog Models in Cardiology

Michael Krigsman: Arslan Khan on Twitter comes back again and he asks, with your research, what did you find, or did you find that the systems and processes, traditional ways of describing the body were either not useful or overly complicated? How did you end up with this electrical analog?

Dr. Joe Alexander: In the world of cardiology, although the electrical analog model is not so thoroughly represented as what we're using, it has become a traditional approach to characterizing hemodynamics. Pressure volume area, end systolic pressure volume relationship, the representation of the dynamics of the circulatory system, a neural control of the circulation using baroreceptors and so forth. This electrical analog way is traditional. It's just that many practitioners don't understand it on this level.

They're using volume conductance catheters in the cath lab to measure volume and pressure and generating pressure volume loops and generating indices of contractility. So it's not non-traditional, it's just that we're taking it on a whole nother level and extending it and using some non-traditional or some elements that we discovered and that have been published but have not been traditionally used because of, I'll just say complexity of biomedical engineering compared to clinical medicine. A lot of clinical cardiologists are using the principles but don't understand it so thoroughly.

Now, I mentioned a consultant that we have on the project. His name is Kenji Sunagawa. He discovered and proved many of the principles that are being used in clinical cardiology today that are based on pressure volume characteristics and electrical analog models. There's an electrical analog model of the systemic arterial system called impedance that is not only representing the resistances, but the frequency-dependent nature of pressure and flow in the dynamics of the arterial system. People are using results from impedance characteristics without being able to measure impedance, which is another electrical term because it's just a little bit more complicated than what people are ready for.

All of these insights—For example, another example is ventriculovascular coupling. Cardiologists talk about ventriculovascular coupling, and one concept is to think of the heart as a battery with a charge, and the arterial system represented by a pressure end systolic pressure and stroke volume relationship where you have two capacitors and opening the aortic valve is the closing of a switch between the capacitors and volume will move from one capacitor to the other.

That notion of ventriculovascular coupling is something also derived by Dr. Kenji Sunagawa, who's a consultant. I'll just add that a lot of the work I did together with Kenji Sunagawa when I was a graduate student at Johns Hopkins. We have a long history of work using electrical analog models dating back to the 70s.

Michael Krigsman: How much of the math did you need to develop versus relying on traditional or existing understanding of these various relationships?

Dr. Joe Alexander: As a biomedical engineer, we've used whatever popular mathematics was available at the time that might render some new piece of information about biology to be understandable or to make sense. I started way back in the 70s doing neural networks when it was a fashionable thing. We did wavelet analysis of waveforms and reflection coefficients, reflected waves. We, as biomedical engineers, we love complexity and we'll use homeomorphic deconvolution, mathematics of measuring earthquakes. Anything that's available, we'll learn and use.

How much? As much as necessary and practical. Back in the day, we had RadioShack computers controlling analog computers that we patched in in order to have real-time control of an isolated perfused dog heart preparation. That was just the way we do things. So I don't know how much mathematics, but as much as necessary to be practical.

There's an engineer Ian Hunter at MIT who once said to me, he said, "Scientists like taking things apart and engineers like putting things together." In retrospect, everything I've done, I'm more an engineer than a scientist, has been integrative. How to explain the system when it's already put together. Sometimes that takes a lot of mathematics, and we'll do what's necessary about that.

Michael Krigsman: Sounds like you're building the bionic system. Remember there used to be a TV show called The 6 Million Dollar Man? Sounds like you're building the bionic approach. What about the team required to build this? There are so many different skills that are involved.

Interdisciplinary Collaboration and Innovations in Cardiology

Dr. Joe Alexander: One comment to your comment about the bionic man, bionic woman, is that Kenji and I once wrote a paper around the bionic baroreceptor reflex with exactly that notion in mind, where you have a device that automatically can regulate arterial pressure, reproducing a failed autonomic system. There's a syndrome called Shy-Drager syndrome where baroreceptor doesn't work, and that kind of system has been proven to work. Back in the 70s or eighties, we were developing a bionic baroreceptor reflex.

Yes, on our team in the MEI Lab, immediately we have a number of PhDs and biomedical engineers in biomedical engineering. We have MDs, we have master's people, and everybody can do programming. Everybody knows physiology either from the beginning or they've learned from our consultants. We have routine conferences with cardiologists and anesthesiologists doing experiments together with them. We have that level of expertise.

At the National Cardiovascular Center I mentioned earlier, those guys are seeing patients on the one hand, then doing experiments in animals, then writing programs, and then building electrical analog circuits. The same person is doing all of those things. We have access to all of their training and their expertise.

This is an occasion where I should also mention that I've talked about our main collaborator and our main projects on the larger scale. We also have collaborations looking at other aspects of digital twins with a Harvard disease biophysics group where we're working on developing a biohybrid digital twin strategy using stem cells to manufacture, tissue engineer hearts from patients' own stem cells and then study those chambers beating in isolation.

We have a goal, or they have a goal, and we're trying to facilitate them to build a heart based on patient's own stem cells and tissues generated in a bioreactor from those stem cells. There we're tapping into tissue engineering and lots of machine learning.

We published a paper with them in Science Robotics on machine learning-inspired design of array where they posited that it may be possible with AI and machine learning to have biological design evolve at a more rapid rate than evolution on the basis of what would be predicted from some first principles that we know about how tissues function. Not necessarily a trial and error approach to evolution, but a specific design inspired by machine learning.

Then we have a collaboration with Technical University of Munich, where they're developing different types of biosensors and different types of technologies for in vivo measurements of electrical signals. We have a lot of expertise available in our collaborations and a lot of expertise local to our small team, which is only about 9 people at the moment.

Michael Krigsman: So you really are fusing the physiology with medical practice and research with robotics and the math abstracted to create your models. I mean, it's so interdisciplinary.

Innovative Research and Strategy in Healthcare

Dr. Joe Alexander: It is. While we have a strategy, we're also, again, we're that Bell Labs type group where you get a bunch of creative people who have lots of new ideas. Some of the work that we're doing is born out of many great ideas that need to be pursued, at the same time that we try to keep a larger strategy in mind so that everyone is working around a kind of organizing principle for what we want to achieve.

One of the main goals is improved patient outcomes. Some of those goals we expect to achieve in the longer term, but some we want to demonstrate in the shorter term. This autonomous closed-loop intervention system is turning out to be, at least in terms of first in human studies, we expect to see some first in human studies within 5 years.

Health Equity and the Quintuple Aims of Healthcare

Michael Krigsman: You brought up earlier the health equity vision that you have, and how does this research relate to that? And very quickly, 'cause again, we're gonna runout of time.

Dr. Joe Alexander: If you think of the quintuple aims of healthcare, and that's improved experience of the patient, improved experience for the clinician, improved population health, decreased cost, improved health equity, then I think, for example, the autonomous closed-loop intervention system does all of that.

So improves health equity by not requiring so many specialists in order to treat a very deadly cardiovascular disease. The cost we hope should be less, although the history of medicine would suggest that no matter how dramatic an improvement we make in scientific advancement, the entrepreneurs find a way to make it more costly.

But we think that this technology will be less costly and should improve the physician experience. They won't be so exhausted having to give so much care to managing particular patients. The benefits just strike directly, I think, with the quintuple aims of improved healthcare.

Future Directions and Closing Remarks

Michael Krigsman: Where is all this going? Where is your research headed right now?

Dr. Joe Alexander: In the immediate term, we're headed toward those first in human studies that have to do with clinical decision support. We're looking to develop a regulatory strategy with a partner and hand off the expertise, hand off to them and their expertise and investments in large-scale clinical trials and developing technology devices or pharmaceuticals.

Then we would move to focusing on chronic heart failure. That's where we would expect to make use more of the collaborations we have with Harvard Disease Biophysics Group and with our folks at TUM wearable devices and such. Again, this is all starting from the notion of a human biodigital twin, or human biodigital twins, not just cardiovascular. It was a starting place. I am personally interested in neurodegenerative diseases, and so if I'm around long enough, I hope we can get to that branch of work as well.

Michael Krigsman: All right. With that, I'm afraid we're out of time. A huge thank you to Dr. Joe Alexander. He is director of the Medical and Health Informatics Lab at NTT Research. Joe, thank you so much for taking time to be with us. It's been a very fascinating glimpse into your work.

Dr. Joe Alexander: Thank you so much, Michael, for having me.

Michael Krigsman: Everybody, thank you for watching. Before you go, subscribe to the CXOTalk newsletter so we can notify you about upcoming shows. We have great shows that are coming up. 

Thanks so much everybody for watching, and we'll see you again next time. Have a great day.