Dr. Brandi Sinkfield:
Intro: Welcome to the Women's Digital Health Podcast, a podcast dedicated to learning more about new digital technologies in women's health. We discuss convenient and accessible solutions that support women with common health conditions. Join us as we explore innovations like mobile health applications, sensors, telehealth, and artificial intelligence, plus more. Learn from a board-certified anesthesiologist the best tips to fill in some of your health experience gaps throughout life's journey.
Welcome back to episode 21. This episode is focused on how artificial intelligence is enhancing anesthesia and postoperative care. And I'm gonna call this a bonus episode specifically for my women's digital health listeners because this talk is done after a talk I did at the American Society of Anesthesiology back in October in 2024. And if you are an anesthesiologist or you have access to the virtual education, check out that talk in the ASA virtual experience. It's called AI Applications in Postoperative Anesthesia. But I wanted to make sure that my listeners also had some access to that talk and had some understanding of how artificial intelligence is being used in anesthesia. And so this episode is all about that. All right so before I begin this talk I wanted to make sure you all understand that there have been a lot of things happening in the background for women's digital health hence why I've been so quiet on the podcast side but 2024 was really busy towards the end of the year.
On top of the talk that I did in October, I was also working on my first ebook and I'm proud to announce that it is out. So definitely go check that out. It's all about perimenopause. It's called Hormone Harmony. It's really focused on giving women an opportunity to advocate for themselves. You know, whether you're in a clinical visit or you just want to understand what perimenopause is, you know, you just want to navigate that health care system with some confidence. Check out my first e-book. Trust me, guys, I did my homework. The references are all there. and you know the goal is really to get you on board with understanding your body if you are in this time period or you know someone who's going through the perimenopausal journey or you're not even sure if you are.
Now how does one get access to this ebook? Well first of all it's on my website. The link will definitely be in the show notes to this episode. There will be a link in my newsletter and I will definitely be promoting this ebook throughout on my social media platforms so check out the various ways in which you can get access to this book. I do think this is going to be a part of a series because I've gotten so many questions about perimenopause and am I on perimenopause and what is perimenopause and What does that mean? Because it's just very different from menopause, which I know has been getting a lot of media attention. So I just thought that it would be appropriate for us to talk about what happens before menopause as a way to understand how women are navigating the health care system as well as using technology. That ebook also comes with a guide, a digital health technology guide, how do you use technology to really improve the quality of life, particularly in this time of life of perimenopause. So check out the book called Hormone Harmony and then check out the digital health technology guide that comes with that. Again, you can check it out on my website, my newsletter, and it'll be in the show notes.
On top of that, I got invited to speak on a panel discussion. This was early this year. It's called The Female Quotient, and it's this huge forum dedicated to women all over the world who are focused on women in business. And I got a chance to participate at the Consumer Electronics Showcase early in January this year. I met so many really incredible people at that event. Thank you to Shelly Zelis, who, as the founder of that organization, The Female Quotient is phenomenal. You know, her team is fantastic. They host these forums, not only just Consumer Electronics Showcase, but the World Economic Forum at Sundance. They are everywhere. And her team is so organized and they are so on top of it. It is just a phenomenal organization. And I'm truly honored to be a part of this. And so thank you so much to Female Quotient for giving me the opportunity. Thank you to Jenna Green, who is the founder of Forward Collective, who was the person that actually connected me with the chief advancement officer, Nancy Weintraub, and the chief clinical officer, Paula Pumphin Craven of Easterseals, where we had a wonderful panel discussion about the future of healthcare technology with women in leadership. And I was so honored to be on that panel discussion.
So these are all the things that I've been doing behind the scenes for Women's Digital Health in preparation for season three. So thank you for your patience. And without further ado, let's get into episode 21 that's focused on AI applications in postoperative anesthesia.
So I've broken this episode into four parts. The first is really understanding what anesthesiologists do. The second part is reviewing some vocabulary terms. You know, I call those vocab-vittles if you've listened to my previous episodes. The third part is really helping you understand how artificial intelligence is helping anesthesiologists in real time and like what's happening in the operating room if you saw an anesthesiologist using artificial intelligence. And finally, we're going to bust some myths about what AI is doing in healthcare, specifically for anesthesiologists, and what it's not doing.
All right, so the first part, understanding what anesthesiologists do. I think it's important to give you context before I start throwing around terms and throwing around scenarios. I know a lot of people watch medical dramas like Grey's Anatomy. So I think most people understand that anesthesiologists are the ones to put you to sleep and wake you up. And while that's true, The reality is that I have a quiet ninja part of my job. And that actually begins before you even come into the operating room. Anesthesiologists have the responsibility of assessing risks. Anesthesiologists have to decide, okay, what is the likelihood that you're gonna have a good outcome versus a not so good outcome? The biggest fear I hear before surgery is doctor, Am I going to wake up during the surgery? And honestly, the probability of that happening is low. I am actually more concerned about whether or not your wound's going to heal or whether or not you're going to have, you know, a heart attack or a stroke. And part of this is because I'm worried about things like your blood sugar being way too high before surgery.
So the last thing an anesthesiologist wants is for you to have a bad outcome when we could have delayed your surgery so that we could make things better. So let's go back to the blood sugar. If I've got some time to actually improve your blood sugar, I'm going to push for that. I'm going to talk to your primary care doctor and your surgeon and say, hey, Let's see what we can do to make this person better. Let's make them the best it can possibly be before they go to surgery. Now, once you get that green light, yes, we are definitely monitoring your vital signs like your heart rate, your blood pressure, and your oxygen, and we are definitely giving you medications during surgery to keep you asleep, I guarantee. The probability of you waking up during the surgery is pretty low, but these other things that are important for decision-making, I have to stay on top of constantly.
So that leads me to the second role that anesthesiologists play in the operating room. That is making sure you are safe. And part of that is being able to anticipate when something's gonna happen and preventing it from happening at all. And so we'll discuss later how AI shows up in that, but I just wanted to make sure that you understand we are your safety check. We are the person that's thinking three and four steps ahead about what could go wrong and what could go right. Lastly, we are managing your pain and we're there when you're recovering. Part of our job is coming up with a plan for your pain prior to surgery, during surgery, and after surgery.
Okay, so those are the roles of anesthesiology for the most part. You may be wondering, OK, this is about AI. How does artificial intelligence really step in with anesthesiologists to help us do some of these jobs? How do they help us do our job even better? And so we're going to get to that. But before I discuss that, we've got to understand terms.
So I'm going to call this part vocab-vittles. you can definitely check out Episode 7, Episode 10, and Episode 13 where I go a lot deeper into some of these terminologies.
So the first term is predictive analytics. Predictive analytics is basically just saying I'm going to use past data to make a prediction about the future. So let's use blood sugar as an example. It'd be great to know what your blood sugar was before you go to the operating room to help us predict the future of your blood sugars during and after surgery and how to manage it. it can help us choose the best medications before you even come to the hospital. And so that when you get to the hospital and you're going for surgery, we already have a plan in place to help you maintain your blood sugar if it's too low or get it down if it's too high. And certainly to help you get it stabilized so that you can recover, you can have the best wound healing and reduce your risk for other complications secondary to poor blood sugar control. Think of that like Google Maps. You know, when you put in your current location and you're putting in the address of where you want to go, the Google Maps can actually predict the traffic even before you actually start on your journey. So knowing that traffic's going to be ahead might help you pick out which snacks you want to bring on your trip, and you might want to plan how Soon you want to leave from your current location and get to your destination.
So using predictive analytics can help you predict what things you might need in the future to have the best outcome. The second term is machine learning. This is a type of artificial intelligence that allows the computer to learn from data without being reprogrammed or recoded over and over again. Let's use blood pressure as an example. Machine learning could be used to help a doctor adjust or recommend new medications to raise or lower someone's blood pressure before surgery. Once the machine learns what the patient's data, vital signs, all the important labs and diagnostic material is before, machine learning can actually help support the doctor in suggesting managing their blood pressure medications by starting medications or giving them fluids depending on the circumstances. So I think the best example here would be, think about Spotify or Apple Podcasts, where you put in a song that you like, and based upon the songs that you like, they create an algorithm. And that algorithm learns what kind of songs you like, and it creates a playlist on its own. It no longer needs you to put in what you like. Over time, it improves your playlist, and it adds other songs that maybe you hadn't even heard of, all based upon, you know, certain information that you put in originally.
So think of machine learning as once I get the information, you don't have to tell me again, I know what you like. The last term would be natural language processing. And simply put, natural language processing describes how computers can read or speak to humans and how humans can speak to the computer and the computer now understands what you're saying. The example here is the ability of a computer to take large amounts of spoken or written data that patients say about their healthcare experience, the machine then takes that information and organizes it much quicker than a human could do. So think like Siri or Alexa and their ability to understand voice commands and actually perform a task that you request. Let's say, you know, you ask it to tell you what the weather is, it'll tell you what the weather is.
Okay, so natural language processing is the bridge of communication between the computer and the human. Okay, so now that you have the terms, we can start to get into scenarios that would actually play out in the operating room using artificial intelligence.
Call to action: Hey listeners, it's Dr. Brandi. Thanks for listening to this episode of Women's Digital Health. Subscribe to Women's Digital Health on your favorite podcast platform. If you want to know even more about how to use technology to improve your health, subscribe to our newsletter on womensdigitalhealth.com. Follow us on Instagram, Facebook, YouTube, and LinkedIn. Enjoy the rest of this episode.
So there's a lot of things that anesthesiologists do. Yes, we are giving medications. Yes, we're monitoring the patient. But there's other things that we are responsible for. Think of us as the chief safety officer in the operating room. We are protecting the patient. I know you think we're over there just doing Sudoku and playing Candy Crush on our phones, but do not be fooled. We are watching everything. Who's coming in the room? Is there any way that we can best support the surgeon in performing this procedure? You know, making sure that the patient's in the ideal position and just anticipating certain things that could happen and change in the operating room. And there's a lot that goes into that.
It would be great to have an assistant since most of the time anesthesiologists are doing a lot of these jobs. It would be great if we could have, you know, sort of this smart anesthesiology assistant that could help us. And that's what we would call artificial intelligence. That's how artificial intelligence is showing up in the anesthesia world.
How would that work? So artificial intelligence can continuously track your vital signs and it can give some warnings. Let me give you an example. So let's go back to that blood pressure example. Artificial intelligence can now predict that the blood pressure is dropping even before we see it on the screen. How does it do this? Well, remember, we're using predictive analytics to learn from our past what could likely happen in the future. And then we're using machine learning to say, hey, listen, I've seen this play out before. You don't have to tell me. I know what's going to happen next. Let me take this opportunity to warn you, doctor, that the blood pressure is going to drop based upon previous scenarios that I've been trained on.
Now our smart anesthesiology assistants can help us by time to draw up drugs and inform the surgeon and circulating nurse and other important people in the room about how we're going to handle this anticipated change in blood pressure. This is really important because if you can anticipate a drop in blood pressure sooner, this means fewer complications and better patient outcomes. So think about like a smart thermostat. You know, let's say if you have a smart thermostat in your room, the thermostat always knows you come home at five o'clock and it can start adjusting the temperature before you come home to make sure that the temperature is not too hot or not too cold. So that's kind of how artificial intelligence can assist and warn an anesthesiologist in the operating room.
Another scenario that artificial intelligence can assist anesthesiologists with would be improving your experience with pain management in the hospital. Let's say you took the time to give feedback to the hospital about your experience. You know, you really want people to read this and you really want to improve the experience that you've had in this hospital.
Now imagine you are a hospital administration and you are getting feedback from your patients, but you have 15,000 of those surveys. You really want to improve the experience of all your patients, but you have 15,000 surveys to read through.
That is the scenario that happened in Cleveland Clinic and they used natural language process to categorize and organize the feedback from these patients so that they could make those changes as quickly as you can so that patients can actually see that you respond to these surveys. So think of Yelp reviews. You know, as soon as a restaurant owner reads a Yelp review, good or bad, they are making changes because they want to improve their services so that they can keep their customers.
Having a quicker way to get through reviews by organizing them using the advantages of natural language processing can help you focus on the bad ones so that you can make those improvements more quickly rather than reading through all of the reviews and then trying to figure out which one is the one I need to focus on to improve our customer service.
Okay, so those are two examples of how artificial intelligence can assist anesthesiologists. But I'm definitely curious to know if you think AI could help you get better care or not. So join my WhatsApp chat.
This episode is all about understanding what AI could do. But, you know, raise your concerns about AI. What are your questions? You know, what do you think? How do you think you would feel knowing that artificial intelligence is monitoring you, monitoring your vital signs? Do you trust AI? So check out the show notes. We will put the link to the WhatsApp chat. And I would love to just, you know, get your feedback.
So the last part of this episode is all about myths. Now I get a lot of questions from my patients about anesthesia and when I think people hear about artificial intelligence in healthcare, they think robots are going to replace the doctors. And that's not what's happening. Smart anesthesia assisted is really something called decision support. And decision support is a method in which machine learning helps and supports a doctor in making a decision at a critical point. And so that already exists. It's not necessarily that it's replacing the knowledge and expertise of an anesthesiologist because even if that decision support offers a suggestion, it doesn't mean that the anesthesiologist is going to take that suggestion because the human can really appreciate the context of what's actually happening. You know, maybe that blood pressure drop is not real. Maybe the blood sugar is abnormal because it was collected in a wrong way.
There are all sorts of other scenarios that a human can provide context to what's actually happening rather than just relying on raw data that the machine is getting. So the next myth I often hear is that artificial intelligence can make ethical decisions or they can replace the human's ability to make the right or wrong decision and that's not true.
Artificial intelligence is there to assist humans in making those decisions but I don't personally see artificial intelligence being able to make ethical decisions. If anything, we actually need more humans in this ethical decision-making aspect of artificial intelligence in healthcare, and that's a whole separate topic. But we definitely need more people to help technical and financial experts of artificial intelligence to understand the right thing to do for patients, the right thing to do for people, and remind them that when you're dealing with healthcare, it could be their child or their parent or their sibling or their loved one that we need to consider when we are building these systems for healthcare using artificial intelligence.
All right, the final myth is that if you are able to predict accurately using predictive analytics, that's definitely going to improve outcomes. Now, I've talked a lot about predictive analytics in this episode, and that's definitely one of the strengths of AI, you know, its ability to capture a large amount of data and then come up with this very accurate, precise prediction. And that's great. That's if all the information is there and it's where it should be.
And this is where the human mind becomes better than artificial intelligence because it knows when a data point like blood sugar is wrong and is just not even compatible with life. If the blood sugar is 3,000, No, that's wrong. And so artificial intelligence is still early in its ability to judge and adapt and know what's right. It's just an assistant. It can't replace the experience and expertise of an anesthesiologist.
If you can't tell, I love what I do. I love anesthesia. I love practicing. And I know that artificial intelligence and anesthesiology together can really make anesthesia safer and give patients better, more personalized care. It can help doctors predict risk. It can find to medications. It can improve pain management. You can improve service and overall patient experience. But at the end of the day, the human doctor is still in control. They're just using artificial intelligence as a tool and it's not a replacement.
And with that, that concludes episode 21. In this episode, we discussed what anesthesiologists do. We talked about important terms that are used when we're talking about artificial intelligence in anesthesia. We covered examples of how AI is used in anesthesia, and we busted some myths about what AI can and cannot do in anesthesia. So if you want to know any more about AI, definitely check out my new digital ebook, Hormone Harmony. a must read for anybody who's trying to figure out MIM perimenopause. What is it? It's a must read. So until next time, stay empowered, stay informed, take charge of your health. And remember, you are more than enough, even more than that. Bye for now.
Outro: Although I'm a board-certified physician, I am not your physician. All content and information on this podcast is for informational and educational purposes only. It does not constitute medical advice and it does not establish a doctor-patient relationship by listening to this podcast. Never disregard professional medical advice or delay in seeking it because of something you heard on this podcast. The personal views of our podcast guests on women's digital health are their own and do not replace medical professional advice.
