人工智能在急诊医学中的应用：炒作与现实

大家好，欢迎回到斯坦福急诊医学播客。我是主持人马修·斯特雷洛医生，斯坦福大学急诊医学系执行副主席。人工智能发展迅猛，有人认为过于迅速。它已经开始重塑我们的医疗实践方式。

Hello, everyone, and welcome back to the Stanford Emergency Medicine Podcast. I'm your host, doctor Matthew Strelow, executive vice chair of the Department of Emergency Medicine at Stanford. Artificial intelligence is moving fast. Some say too fast. And it's already starting to reshape the way we practice medicine.

为了帮助我们理解这一切，我们邀请到了克里斯蒂安·罗斯医生。他是急诊医师、助理教授，也是斯坦福的临床信息学家。他的工作重点是开发真正能帮助医生且不干扰其工作流程的人工智能工具，并深度参与实时诊疗中AI应用的伦理探讨。

To help us make sense of all, I'm joined by Doctor. Christian Rose. He's an emergency physician, an assistant professor, and a clinical informaticist at Stanford. His work focuses on building AI tools that can actually help doctors without disrupting how they work. And he's deeply engaged in the ethical side of using AI in real time care.

罗斯医生，欢迎您的到来，感谢您参加我们的节目。

Doctor. Rose, welcome, and thank you for joining us.

谢谢邀请，非常高兴来到这里。

Thanks for having me. So glad to be here.

让我们先从宏观视角开始。所有这些创新都伴随着重大问题：我们将走向何方？现实世界中哪些真正有效？哪些问题需要我们停下来思考？

Let's start big picture. All this innovation comes with some big questions. Where are we headed? What's actually working in the real world? And what should make us stop and think?

当我思考人工智能时，主要将其视为利用数据与信息技术来模拟人类行为或我们认为人类运用智能的方式。人工智能可以呈现多种形态——可能是筛选数据寻找模式，也可能是撰写《大西洋月刊》文章、《纽约时报》报道或科研论文。因此人工智能本质上都是对人类智能的模仿，这种定义也有局限，因为我们甚至没考虑人类不擅长的领域，以及机器可能比我们做得更好/以不同方式自主完成的事情。

When I think about artificial intelligence, I mostly think of it just as a way that we can use data and information technologies to mimic parts of what humans do or what we think humans use intelligence for. There's many different ways that artificial intelligence can look like that. It can be, you know, sorting through data and looking for patterns, but it can also be writing and, you know, writing an Atlantic article or a New York article or a scientific research paper. So artificial intelligence is all a forms of mimicking human intelligence, which is also a little limiting because we don't even think about the sort of ways in which humans don't work well and the things that machines could do, you know, better than us slash different than us on their own anyway.

我常听到生成式AI和预测式AI这些术语，您能帮我们理解这些概念吗？

I hear the terms generative AI and predictive AI. Can you help us understand these terms?

当我们谈论这个话题时，指的是它能生成内容。人们见过Dolly，那是我早期广泛接触的版本，当时朋友们都在说：看这个生成式AI，只要描述需求就能生成图片，它能创造东西。

When we talk about that, what we mean is it's generating something. People saw Dolly. I think that was the earliest sort of version, that I had seen broadly that friends were like, look at this generative AI. It'll make a picture when I describe what I want. It will generate something.

后来出现了GPT和ChatGPT，我们意识到它现在可以生成文本、生成摘要，再次为我创造内容。这要与预测功能区分开——预测模型是获取数据后做出预测，而生成式模型的预测在于判断马特希望这句话表达什么，他想传达什么观点？

Then we got GPT and ChatGPT, and we were like, oh, maybe now it can it will generate text for me, generate a summary. It will make again something for me. That is just to be distinguished from the predictive part, which is they take data. They make a prediction. And then the prediction that a generative model is using is what does Matt want this sentence to reflect, and what is the idea he's trying to get at?

它通过多维向量空间分析后表示：我已锁定目标方向，最终通过这个多维空间为你生成字符串。我认为厘清术语很重要，因为我见过论文将预测型AI称为生成式AI，或把单纯的数据观察归类为预测AI。这些都涉及机器学习的子集（人工智能的分支），以及更深层的深度学习和神经网络等。这些对急诊医学而言是新术语，虽然这已是医学界第三次人工智能浪潮——六十年代、八九十年代各有过一次，当前是第三次。

And it looks through multidimensional vector space and says, I think I've got a target on where I'm trying to get to and gives you essentially the string through that, you know, multidimensional space. The reason I think it's just important to think about how we use these terms is I've seen papers that refer to generative AI when they're talking about predictive AI. They mention predictive AI when they're actually just talking about, observations or not, you know, making predictions, but sorting, different data points that gets to the subset of machine learning, which is a subset of artificial intelligence, and then deep learning and neural networks, which are a subset of that and other things. So a lot of these are sort of new terms in emergency medicine, newish terms in in medicine, though this is the third wave of artificial intelligence in, the medical sphere. There were waves in the sixties, in the eighties and nineties, and then we have this most recent sort of third wave of AI in medicine.

我们长期使用这类工具，约六十年来它一直处于医学发展前沿，只是称呼不同。数据科学与预测分析存在已久，我们都从中受益。医学界用它进行资源分配（如肝移植），本质上仍是回归分析与预测。

We've been using tools like this for a long time, and it's been at the forefront of where people thought medicine was going again for about like sixty years. We just didn't call it that. Data science and predictive analytics has been around for a long time. All of us have benefited from it in some way. And medicine has been using that and trying to allocate resources like liver transplants, which is, you know, again, regression analyses and predictions.

如果预测某个结果，通常视为预测模型；若生成新内容，则视为生成模型。但这些术语的使用存在大量交叉和复杂性，不同模型的功能边界也很模糊。

Predicting you know, if it's predicting something, some outcome, you generally are thinking of it as a predictive model. If it's generating new content or things, you're thinking of it as a generated model. But there is a lot of overlap and complexity in how these terms are used and and and which models are doing what.

正是如此。

Exactly.

但我最大的收获是：突然意识到自己可能已使用预测型AI二十年。比如在谷歌拼写时，它总问'你是想输入...？'，按你的说法这就是AI——原来我早就是AI老手了。没错。

But the other thing that I really took home from that is that I'm now realized that I've been using predictive AI maybe for twenty years because like I'm always spelling things in Google and it was always saying, did you mean? And that you're telling me that's so I'm I'm like really facile with AI. I've been doing that. Yeah.

确实如此。而且我想说，我们很多急诊科同事都参与了预测性AI的工作，比如回归分析。当我们使用TI-83计算器输入数据点生成曲线和最佳拟合线时，很明显这些技术已经变得非常强大。它们能处理的数据量惊人，呈现方式也变得更加直观易用。

You have been. And also I would say a lot of our emergency physician colleagues have all been parts of predictive AI is, you know, regression analyses. And when we use our TI 83 plus to put in data points and get a curve and a best fit line, I think, obviously, these technologies have become extremely robust. The amount of data that they can process is wild. The way that they present it back to us has gotten much easier to navigate.

那么我们现在进展到什么程度了？目前急诊科正在使用哪些AI工具？

So where are we at now? Like, what AI tools are being used in the ED today?

我从大学时期就开始从事信息学工作，我的毕业论文涉及太空医学，这让我对信息学领域产生了兴趣，开始研究人们如何设置警报或医嘱，以及如何被提醒可能犯的错误。说实话，尽管我已经关注这个领域大约十七年（从2008年到2025年），但感觉变化甚微。急诊医学中反复出现的问题依然存在。我看到人们开发的工具包括Qventus（我在住院医师时期接触过），用于预测患者到急诊科的时间和资源调配。排队论也是一种人工智能方法，用于预测患者流量。

I have been doing informatics work since my my college, like, senior thesis was a little bit around space medicine, and that got me interested in the informatics space, which got to how do people place alerts or orders and how do they get alerted to mistakes they might be making. And and I'm gonna be honest, very little has changed, I feel, even though I've been paying attention now for, you know, I guess, what is that, like, seventeen years, 2008 till 2025. And then it's still addressing the same sort of problems we see over and over again in emergency medicine. The tools that I've seen people working on are, things like Qventus, when I was in residency, trying to understand how people arrive in the ED and predict and have resources available. Queuing theory, is an artificial intelligence, you know, methodology to try to predict who's who's gonna come in.

这自然引出了下一个逻辑空间——我见过无数公司尝试改进分诊系统，基于患者到院时间优化ESI评分，避免前台人员因主观偏见导致误判（比如X类患者和Y类患者的临床表现差异）。目前急诊医学最关注的核心问题还包括：如何从车祸、机动车事故或穿透伤等创伤中识别高危患者。本质上，很多工具还是在解决我们过去就一直关注的问题——精准识别并治疗那些易被漏诊的高风险患者。

That gets you to the next logical space that everyone I've seen many, many, many companies try to work on, which is triage and improving, you know, ESI scores based on when someone comes and not leaving that up to a human who might be biased at the front desk and not really know that, you know, the patient population X presents slightly different than patient population Y. And that still tends to be one of the biggest problems that people focus on right now in emergency medicine, as well as who is the most likely sick or ill from the types of injuries, car accidents, motor vehicle accidents, or penetrating trauma. So a lot of the same tools are a lot, to me, a lot of the same things we thought about before to ultimately target and treat at risk patients who we might otherwise fail.

我想我们都深刻体会过患者分流的痛点。当患者被分诊到管理困难的区域时——无论是分诊不足还是过度分诊——都会给我们带来巨大压力。

I think that we've all felt the pain of patient flow. We've all felt the pain of patients being triaged into difficult areas for us to manage them because they're either under or over triage and things like that.

还有关键问题是谁该去哪里？比如空中转运资源分配。我们优秀的同事Rice医生就在研究：当面临关键资源时，如何决策转运对象。我们既不想压垮医疗系统，又必须承担这种决策压力。因此有时我们会尝试开发机器学习或人工智能模型来简化这个过程。

And a lot of And who who needs to go where? Flight I think flight things. You know, one of our colleagues, our awesome colleagues, doctor Rice, works on you have a critical resource and you worry about who needs to get sent. We don't wanna overwhelm systems and that, you know, there's a burden there on us that we worry about. So sometimes we like to come up with a machine learning, or artificial intelligence model to make that easier for us.

当你看到这些模型真正在急诊科 frontline 部署时，你观察到临床医生或急诊科工作人员对它们的反应如何？

When you see these models being rolled out on the front lines, actually in the emergency department, how do you see clinicians or or emergency medicine staff responding to them?

我要把问题抛回给你。你观察到人们是如何回应这些的？我常常试着闭上眼睛不去看。

I'm gonna flip it back to you. How have you how have you seen people, responding to them? I try to shut my eyes. I try to shut my eyes a lot

并向像你这样的专家请教。是的。我认为反应大致可以分为两类：一类是我称之为过度采纳者，另一类是采纳不足者，或者说过于兴奋和不够兴奋的人。作为急诊医学从业者，我们对这些持合理的怀疑态度。

and ask the experts like yourself. Yeah. You know, I I think it comes up that the response is a little bit into two camps. I think there are people that are what I would call over adopters and people that are under adopters or at least overexcited and underexcited. And I think we as emergency medicine providers have a reasonable dose of skepticism around them.

我认为我们的医疗系统可能缺乏足够的怀疑精神。我不确定他们是否完全理解在临床层面运营急诊科所需的复杂性和专业知识。所以我确实看到了这种差异。可以说大多数临床医生目前对它们持某种怀疑态度，但我不确定整个医疗系统是否也如此。

I think our health systems may not have enough skepticism around them. I don't know if they necessarily fully understand the complexity and the expertise that go into running the emergency department at the clinical level. So I do see that kind of difference. So I would say most clinicians are responding to them right now with what I would say is some skepticism, but I'm not sure that the health systems at large are doing that.

让我们思考一下关注点。急诊医学有群体健康需求——我知道你在工作中也经常思考这个问题。社区需求、医院需求（如果我们细分的话），更大的社区和资源分配，医院在任何时间点的处理能力，这些都最终落实到医护人员身上。

Let's just think of our attention points. There's the population health needs for emergency medicine. I know you think a lot about this in your work too. There's what a community needs, what a hospital needs if we subdivide down to that. So larger community and distribution of resources, the hospital at any point in time, what it can handle and not, that then funnels down to the provider.

而医护人员的需求往往与患者需求不同。每一个层面都是我们试图达成一致的节点——虽然'一致'这个词被过度使用了——但本质上是在问：如何同时满足所有这些目标？我理解同事们面临的困境，在决策时需要同时权衡这么多因素实在太难了。很少有工具能一次性解决所有问题。

And then the provider needs are often different than what the patient needs. And each one of those represents a point at which we're trying to find alignment. An overused word in many ways, but also you're trying to say, how do we meet all of these goals at once? I feel for our colleagues that the amount of things we try to hold at once, while trying to make a decision is really tough. And rarely does any one tool capture all of those at once.

因此我认为部分怀疑情绪源于你感受到的竞争性需求：既要对眼前患者负责，又要考虑五分钟后的下一位患者，还要顾及整个医疗系统的资源分配。模型引发怀疑的原因在于——正如你所说——有人可能喜欢它，因为这帮助他们停止过度思考或减轻同时权衡多因素的疲劳感。对公共卫生科学家和初级保健医生来说，它能限定选择范围（比如患者可以去A、B或C目的地），从而卸下部分认知负担——这正是你们在斯坦福研究的课题。但根据文献记载，目前部署的大多数技术产生的效果都很有限。

And so I think some of the skepticism can be that you feel like a competing demands, which is the patient in front of you, and always your responsibility to them while also recognizing it as the next patient to come in, what the situation will look like in five minutes, and then the larger health system, you know, and how resources get distributed. The reason the skepticism in models can come up is it might to your point, some people might like it because they say, oh, this helped me sort of turn off. I was overthinking or I'm so fatigued trying to hold all of these elements at once, a population health scientist and a primary care physician, this helps me just sort of limit and say this patient could go to A, B, or C destination, or those are all reasonable outcomes. And it helps you offload some of that cognitive burden, which is some of the things that we're, you researching at Stanford. I think that when I see people and I look at the literature from how they've used most of the, like, to date deployed technologies, they just had very small effects.

在医学领域，要对我们已经做得不错的事情实现大规模改进本就很难。这不是说现行医疗体系完美无缺或无需改变，而是指前期投入资源构建模型、收集数据、清洗数据、以真实反映医患体验的方式部署，再验证是否真正改变了患者结局——整个过程极其困难。每个过渡环节都是需要专人负责的研究领域。有人会觉得'天啊，它帮我解决了真正沉重的负担'，也有人会说'我从不这样行医'。

It's often hard for anything in medicine to show a large scale, improvement, in something that we already do kind of well. And that's not to say medicine is perfect right now or doesn't need to change. It's just quite hard to put in the resources upfront to build a model, to find the data points, to do all of the cleaning, to deploy it in a way that's authentic to the patient and physician experience, then to see the results and see if that's actually changed in a formative way the outcome of that that individual patient, that's really hard. Again, each of those transitional points is an area of research and is an area of need for someone to take ownership of how well the tool functions. Some people either find, oh my god, it's helped me in something that is truly burdensome, and others say, oh, I never I didn't practice this way.

我最初从事的是基础医疗决策工作，现在却凭空增加了14项额外考量。电子健康记录系统本应让我们下达医嘱更便捷、减少医疗差错、减轻医生完成工作的行政负担。但事实证明，这套系统反而让这些负担翻倍恶化，导致我们50%的时间都耗在点击操作、下达医嘱和在正确情境中寻找正确医嘱上。所以人们期待这些工具能有所改善。但人性就是如此，我们处理问题的方式往往因人而异，而这些问题本身也常常变化无常。

I practice bread and butter, decision rule based medicine to begin with, and now this has just added 14 additional considerations. The EHR was supposed to make it easier for us to place orders, prevent medical errors, and make it so the physicians have less administrative burden of trying to get the work done. And it turns out the EHR has just, like, doubled that and made it way worse such that 50% of our time is spent trying to click through and place an order and find the right order in the right context. So there's hope that some of these tools will make that better. It's just that humans are human and the way we engage is often unique to each, each person's current problem, and those are often a moving target too.

钟形曲线一端的人会说'我爱死它了，天天都用'，另一端的人则说'被它搞砸过两次，再也不信了'。中间的大多数人态度是'它有时能帮我解决部分问题'，表现得模棱两可。

So some people on the one end of the bell curve are like, I love it. I'd use it every day. Some people are like, I had it messed up twice, so I don't trust it anymore. I'll never use it again. Then you have everyone in the middle who's like, it helps some of the time with some of the questions I had, and I'm sort of ambivalent.

应该说大多数人都属于中间派。从CPOE（计算机化医嘱录入）时代开始，多数专业系统的实施结果都大同小异。真正能明确说'就该这么做'的情况少之又少，而我们却要全盘改变。

Would say most people fall into that. And most of the pro most of the implementations all the way back to, you know, CPOE have been sort of the same result. There's very few things that it's just like, this is the way to do it. And then we've changed wholesale.

确实。我同意你的观点，现在炒作的热度有些超前了。不过你知道我是篮球运动员出身，我教孩子们传球要预判队友走位，而不是盯着他们当前的位置。

Yeah. I mean, I agree with you. I think the hype train's a little out front of where we're actually at, but I know you're a basketball player. I'm a basketball player. I teach my kids not to throw the ball where the player the other player not where they're going to be.

当我展望未来几年，电子健康记录系统与人工智能的结合，加上跨多系统的集成电子健康记录，确实能帮助我们突破某些瓶颈，可能对医疗护理产生深远影响。但我也担忧其负面影响和风险——多到我们无法穷尽。说说哪些风险最让你夜不能寐？

And I do see when I look where we're going to be a few years down the road, the combination of the EHR with AI and integrated electronic health records across multiple systems and situations is gonna allow us to unlock some things that are going to make, that have the potential to be really impactful in our care. I do worry though about the downsides, right? And the risks of this. And I think there are so many that it's like, we can't cover them all. But tell me, what are some of the ones that really would keep you up at night?

在急诊护理中采用人工智能的最大风险是什么？或者说早期采用阶段的风险。

What are the biggest risks of us adopting AI in emergency care? Or at least, let's say, early adoption.

没错。我们还得考虑风险对象。至少可以分两方面讨论：患者及其接受的护理面临的风险，以及我们医生群体面临的风险。实际上电子健康记录系统严重伤害了我们，导致大量职业倦怠，让患者感觉得不到足够的医患沟通时间，这种技术正在损害医患关系。

Yeah. Well, let's also think the risks to whom. Let's break down or just talk about at least two. Risk to the patients themselves and the care we provide and the risk to us as physicians. The HR hurt us a lot actually and caused a lot of burnout and has made it so that patients don't feel like they get time with their doctors, so there's a harm to the patient physician relationship because of technology.

我们很少会遇到需要AI模型处理普通情况的问题，你知道的，就像听到蹄声就想到马。我们通常需要它来处理那些‘我听到蹄声但担心可能是斑马’的情况——我不想错过斑马。要获得能真正全面考虑患者需求（不仅是临床情况，还包括他们的家庭环境、主治医生、如何获取并实施护理）的决策支持数据一直非常困难。所以虽然你可能诊断出问题，但诊断只是我们工作的一小部分。

It's rare that we have a problem or need an AI model for the average, you know, the you hear hoofbeats and think horses. We usually need it for the I hear hoofbeats and I'm worried it might be a zebra. Let me not miss the zebra. It has been really difficult to have data that supports decision making for patients that truly takes into account all of their needs, and not just their clinical scenario, but like where what they go home to, who their doctor is, how to get them and deliver that care. So while you might diagnose stuff, diagnosis is only a part of what we do, in fact, a small part of what we do.

风险在于你自动化了部分流程。许多人得到的护理服务变得模板化，缺乏需要人类参与才能提供的深度认知——真正能掌舵的人。这可能导致边缘群体更加边缘化，使本就不常在医疗体系中的人承受双重负面影响。原本无法获得服务的人或许能获得服务，但可能是差异化的版本。这就像那些唾手可得的风险之一：因为人力不足而自动化掉某些人性化环节，导致人们得到的服务与预期不符，让他们再次感到被边缘化。

So the risk is that you automate some of that. A lot of people get a version of care that's cookie cutter in ways and lacks the deep knowledge you need, by having a human in the loop that can actually still steer the ship for them. That can leave people marginalized, at the edge, leaves the edge people more at the edge, you know, so you have a doubling down of the negative effects for people that aren't, usually part of the health system. People who don't have access might get access, but might have a differential, version of it. That's like one of the big, again, low hanging fruit versions of the risk is you automate away some of the human elements because we just don't have the humans, and people get a version that's not quite, you know, it's not quite the, version they expected, and it leaves them feeling, you know, again, sort of left at the margins.

对。请继续。嗯。

For the yeah. Go ahead. Mhmm.

我正想说，我读过你关于偏见的文章和演讲。嗯。对吧？正如你谈到的边缘群体，这是你真正深入探讨并拓宽我认知的议题。你能向大家概述一下为什么AI实际上会加剧偏见吗？

I was gonna say I've heard you write and speak on bias. Mhmm. Right? And I think, you know, as you talk about people that are on the margins, that's one of the things that you've really talked about and opened up my thinking around. Can you explain to people just an overview of why AI can actually exacerbate bias?

因为我认为我们通常会想到人类存在偏见，但我知道像您这样在这个领域的人经常谈论机器也存在偏见。那么您能否解释一下，这种情况是如何发生的？我们有什么可以做的，以及目前正在采取哪些措施？

Because I think we think about humans being biased, but I know that people that are in this space like yourself talk a lot about machines being biased. So can you explain, like, how does that happen? Is there things we can do and what's being done?

好的。我们都知道有些医院很早就采用了电子健康记录系统，属于早期采纳者。退伍军人事务部医院就是其中之一，还有许多学术医疗中心。当我们考虑这些学术中心的地理分布时，它们通常并不能代表全国大部分地区的情况。

Okay. So there are certain hospitals that we all know that have had EHRs for a long time and early adopters. The VA is one of those. And then a lot of academic centers. When we think of academic centers and where they're located, they're not generally representative of a lot of the country.

居民分布情况如何？如果你身处自由派沿海城市，与中西部小型乡村分布城市相比，医疗资源可及性就不同。我们就从这里说起。不同人群会去不同类型的医院就诊，而不同医院对患者信息的数字化获取程度也不同。我们用于建模的数据收集自那些平均能获得最高质量学术医疗服务的地区，旧金山患者的特征或反应与休斯顿患者略有不同，而后者又与印第安纳波利斯或纽约市有所差异。

Who lives where? And if you're in a liberal coastal city versus a middle of the country, smaller rural distribution city and different access to healthcare. We'll just start there. So different people we know present to different types of hospitals and different hospitals have different access to digital versions of patient information. The data that's been collected that we use, that we throw into the models then is from places where people have access to the highest quality of academic care on average, and San Francisco patients look a little bit different or respond a little different to people in Houston, which is a little bit different than Indianapolis, or New York City.

如果你知道并意识到这一点那很好，但这同时也意味着规模化运作存在困难——比如那些前往仍在使用纸质病历或刚开始使用电子病历的乡村医院就诊的患者群体。这些电子病历数据实际上并未传输给开发模型的大公司，因此这类患者始终处于边缘地带。当他们前往大型医疗中心就诊时，模型根本不知道该如何处理他们。在我看来，这本质上是某些地区拥有更多数据点，却无法准确反映全貌的问题。

That's fine if you know and are aware of that, but it also means that anything like being operated at scale just doesn't have a great way of, okay, here's a patient population who goes to the rural hospital that is still on a paper chart or maybe just started on an EMR. That EMR doesn't actually send data to the big companies that build the model. And so it sort of always lives in the periphery. And if they ever present to one of the major centers, the model doesn't really know how to deal with them. So to me, it's just it's sort of a problem of certain places have more data points, but that doesn't accurately represent the whole picture.

我并不是说每个人和每个模型都必须...我们有朋友讨论过开发超本地化算法并在自家诊所部署。但如果你最初就缺乏数据，且接诊的每个患者都算边缘案例，那么这些未被纳入系统的人就会持续被边缘化，因为我们没有好的应对方案。不过我想简要强调：必须记住人类的行为决策基于自身经验，医生也可能在全国各地流动执业。人工智能确实有机会消除人类固有的无意识偏见——毕竟人类也存在这些偏见，所以不妨换个角度思考。

I'm not saying that every person and every model has to, some friends of ours talk about having hyper local algorithms then and just deploying them at their shop. But if you didn't have any data to begin with and every patient you see is a sort of edge case, you're gonna you're gonna marginal you're gonna keep those people who weren't part of it stuck at the fringe because we don't have a good way of dealing with them. I do wanna just briefly state though that it's important to remember that humans themselves do things and make decisions that are based on our experiences, and physicians may move around the country and go to places. There's a real opportunity for artificial intelligence to take out some unconscious biases that humans do anyway. Humans make these biases too, so you can flip the script and say, hey.

能否开发一种工具，主要功能是提醒使用者可能遗漏了什么，或是过早锁定了鉴别诊断？以前人们会使用鉴别诊断生成器。用同一工具缓解同类问题有很多方法，但提问方式应该更倾向于'我这里可能漏掉了什么？'，而非'如何最快完成诊断或给患者最佳方案？'这些偏见渗透的途径实在太多了。

Can I develop a tool that mostly just alerts someone to the fact that they might be missing something, or they might have prematurely closed on their differential? People were getting differential builders. So there are ways to mitigate that same problem with the same tool, but framing the question more from a, hey, how what might I be missing here? As opposed to how do I get this done as quickly as possible or deliver the best for this person? There's just many ways in which those biases can seep in.

应对方法也有很多。我不想给人留下'最终都会导向这个结果'的印象。我们需要意识到：不是所有人都被看见。就像会哭的孩子有奶吃，轰动的事件才会被关注。

There's also many ways to address them. And I don't wanna leave the impression that it's like, it's it will all ultimately lead to this. Something we need to be aware of, that not everyone is seen. It's like the squeaky wheel gets the grease. If something sweeps, you've heard of it.

这对你某个地方而言是长期问题，但对其他人可能不是。

It's chronically a problem for you in one place. It just might not be for other people.

确实。我最近读到一篇关于黑肺病再次抬头的文章。你能看到这些患者带着这个全国大部分地区已经遗忘的疾病重新出现，他们很可能未被纳入我们构建AI模型的数据库。当他们在其他使用这些模型的地区因咳嗽就诊时，模型可能完全失效。这个风险确实存在，但我很喜欢你提到的积极面——你说'虽然存在偏见风险，但如果我们警惕这点，反而能借助AI缓解自身固有偏见'。

Yeah. I see like, I read an article the other day about the rise of black lung again. You can see how those patients that are now coming back with having a disease that we've kind of forgotten in most of the country and who probably aren't plugged into our databases that are building our AI models may not work well when they come in with a cough somewhere else where they are using those models or starting to implement those models. So there's that risk but I love that you mentioned some of the positives there. You said like, Hey, there is this risk but if we're attentive to that risk of bias that we can actually help it alleviate some of our biases that we have.

没错。能再聊聊你认为AI在医疗领域还有哪些潜在优势让你感到兴奋吗？

Yep. Tell me about some other things that you think that, you know, are potential positives and that you're excited about with AI and healthcare.

我担心没有设定现实的目标。我觉得事情正在失控，而我实际上非常兴奋。只是我们现在可能正处于幻灭的低谷，因为人们最初听说GPT时超级兴奋，但几乎没有企业在他们投入的AI模型上看到大规模的投资回报。总的来说，人们投入了数十亿美元，却不确定何时能收回成本。这也是一个正常的经历。

I worry about not setting realistic goals. I think things are blowing up, and I'm I actually am very excited. It's just that we're we're probably in the trough of disillusionment right now, because people were super hyped from when they first heard of GPT, and almost no business has seen a large scale return on investment for what they put up for, for their AI models. Sort of all over, people put up billions of dollars, and they're they're not sure when they're gonna see their money again. That is a normal experience too.

这是一个众所周知、被充分描述的高德纳技术成熟度曲线，已有四十多年的历史。我在想这个概念最初是什么时候提出的。重要的是不要因为长期的根本性变革而长期陷入幻灭，要记住我们的目标是什么，我们把目光投向哪里。所以我花很多时间思考可能出错的事情，主要是为了避免幻灭的低谷。我认为思考偏见、思考担忧很重要，但我其实相当兴奋。

That is a normal well known, well described Gartner hype cycle, you know, forty plus years. I'm trying to think of when that was originally defined. And so it's important to not become disillusioned for long term formative change to remember, okay, what's our goal and where are we setting our sights? And so a lot of the reasons I spend time thinking about what can go wrong is mostly to try to avoid the trough of disillusionment. I think thinking about bias, thinking about the worries is important, but I'm actually quite excited.

我认为科学史和技术创新史也表明，我们的工作很可能会变得更糟。医生执业的风险现在非常真实。我相信听众中有人担心他们会被AI工具取代，比如把医生排除在外，也许我们会培训高级实践提供者去做那些事情，而AI模型则负责所有的批判性思维。这是一个合理的想法。在自动化历史上从未出现过这种情况，无论是银行柜员、飞机自动驾驶仪还是织布机，它们更多是改变了行业，而不是彻底取代了主要部分。

And I think the history of science, the history of technological innovation also says that like our jobs will probably get, I think there's a lot of reason to be worried that they might get worse. The risk to physician practice is very real right now. I'm sure you have heard in our audience, people worry that they're just gonna get replaced by AI tools, that like, you'll just loop the doctor out, that, maybe we'll up train advanced practice providers to just do the stuff then while the AI model is doing all of the critical thinking. And that's a reasonable thought. That has not ever been the case in automation, you know, whether it's tellers, autopilot in planes, the loom, like, that has just changed industries more than it's ever wholesale, like, not a major part of it out.

所以我认识到人们应该担心，这是这些技术对我们工作的主要风险之一。也许我们会变得更加像数据检查员，而不是像现在这样，我们没有那么多时间进行分析性思考、与朋友交谈，或者研究面前这个非常有趣的病例，因为把它输入到众多可用工具之一，一秒钟就能得到答案。

So I recognize that people should be worried, and that is one of the major risks of these technologies to our work. Maybe we will become even more, you know, data checkers than we currently are, and we don't get to spend as much time doing the analytic thinking, the talking to your friend and trying to, you know, figure out this really interesting case in front of you because it's answered in a second from putting it into one of the many tools that are available.

是的。我认为这是一个挑战，如果我们说可以去掉一些思考、知识和专业知识。我面临的一个挑战是，目前的AI模型在自我事实核查方面并不擅长。最难的是弄清楚你的资深住院医师什么时候错了。弄清楚初级住院医师或医学生什么时候错了并不难。

Yeah. I think it's a challenge where if we say, oh, we can take away some of that thinking, that knowledge, that expertise. One of the challenges I have is AI models currently are not great at fact checking themselves. And the hardest thing to do is to figure out when your senior resident is wrong. It's not hard to figure out when your junior resident or the medical student is wrong.

难的是弄清楚资深住院医师什么时候错了，因为他们90%、95%、99%的时候都是对的。所以实际上需要更多的专业知识来核查模型的准确性。因此，我认为找到平衡会很困难，比如我们要把AI引入这个循环，但必须有一个真正有专业知识的人。但如果你大部分依赖AI，怎么会有这些人呢？因为很多专业知识是通过经验、学习和毅力积累的，而我们的系统可能并不是为这种情况设计的。

It's hard to figure out when the senior resident is wrong because they're right 90% of the time, 95, 99% of the time. And so it actually takes more expertise to fact check the model. So I do think that it's gonna be tough to figure out that balance of, okay, we're gonna put this AI into the loop, but then we're gonna have to have somebody with a real expertise. But how do you have those people if you've relied on AI for most of it? Because so much of it is built over experience and study and perseverance, which may just not kind of, our system may not be designed for that.

但从积极的一面看，世界上大多数地方并不像你我所在的地方这样运作。我从事很多全球卫生工作，世界上大多数地方都面临着日益严重的医疗人力短缺问题。美国是这样，全球更是如此。因此，我们能做些什么来缓解这种人力短缺是当务之急。否则，数百万人将因为缺乏医疗人力而死亡，甚至可能每年都会如此。所以我确实看到有很多机会来增强我们的实践。

But on the positive side, most of the world doesn't operate like where you and I are operating. I do a lot of global health and most of the world operates in a situation where there's a massive healthcare workforce shortage that's getting worse every And that is true in The United States and it's more true globally. And so things we can do to alleviate that workforce shortage is just imperative. Otherwise, millions of people will die and potentially die annually from just a lack of healthcare workforce. So I do see that there's so much opportunity there to augment our practice.

我总是担忧信任问题。我认为信任被频繁讨论。无论是自动驾驶飞机还是汽车等自动化技术，你都能看到这一点。我想请你谈谈，你认为患者和医疗提供者是否会信任AI模型？不是他们是否应该信任，而是他们是否会信任。

I always worry about trust. And I think trust gets talked about a lot. And you see that with it's automating planes or you're automating driving and things like that. I'm wondering if you can talk a little bit about your views on whether our patients and our providers are going to trust AI models. Not whether they should, but whether they will.

我读到的大多数观点认为人们不会信任它们。而我担心的是人们会过早地信任它们。你怎么看？

And I think most of the time I read that people won't trust them. My concern is always that people will trust them and they'll trust them too soon. What do you think?

我认为可以从几个角度来思考。信任是整个医疗领域的重大议题。回到我们关于偏见的讨论，有些人从未就诊就是因为不信任急诊科能提供所需治疗。如今很多人因担心遣返等问题而不信任医疗系统，即使在我们工作的地方也是如此。我们的许多同事都在不懈努力，试图让人们建立对医疗系统的信任。

I think there's a couple of ways to frame it. I think trust is a huge issue in all of healthcare. Back to our bias discussion, the reason some people never showed up was just trust in the ability to go to the ED and get provided with the care that they needed. There's lots of people today who don't trust coming to the healthcare system because of concerns about deportation or what happens even where we work. And lots of our colleagues work endlessly and tirelessly to try to make people feel like there's trust in the health care system.

说到工具层面，我认为就像任何工具一样，信任源于使用过程。我是否信任听诊器或超声设备？超声图像总会出现伪影。我们不会长期讨论窗口设置或伪影意义，只会说'这次效果不太好'。

I think then to the tools, a lot of this comes from the use of it, like any tool. Do I trust my stethoscope, the ultrasound to work? There are artifacts all the time on the ultrasound. We don't have long term discussions about the windowing, you know, and what this artifact meant. We go, oh, that didn't work that well.

当我无法确定所见时，会换设备或寻求支持。回顾自六十年代以来的技术发展史，这些挑战并不像我们感知的那么新。关键在于要有倡导者答疑解惑，并准备好不为技术辩护，而是为医患共同利益发声，让我们能在发现问题或感觉不准确时有所应对。关于医患信任，我听到最多的担忧是：人们可能陷入自动化医疗闭环无法退出，最终极度不信任地说'我得找人类医生朋友'。

I'm not really sure what I'm seeing, so I go to another one or I ask, you know, for support. I think in the history of technology and implementations and things that we've been developing against since the sixties, a thing that actually isn't as new as we may perceive. A part of that is having champions and people to answer the questions and being ready to not go to bat for the technology, but go to bat for us and our patients together such that we can trust that when there's a problem or if we feel like there's an inaccuracy, there's something to do about it. The biggest discussion I hear on this from the trust on the physician and the patient side has been that you'll get an autonomous version of care and people won't be able to get out of the loop once they're in it. And they'll become hugely mistrustful, say, I've got go get my human friend.

我们都经历过这种情况：凌晨三点接到十年未见朋友的紧急电话，说'我爸在急诊科出现某某症状，这种情况合理吗？'

I got to go call my friend, which we've all experienced too. Someone's called you because they said, I'm at an ED. They say my dad's having a blank. Does that make sense based on what's going on? And you go like, oh my God, it's three in the morning for me and I'm getting this frantic call from a friend I haven't seen in ten years.

医疗信任是个重大议题，我们部门的同仁——包括你自己——都在致力解决。我支持这个系统，主张前期严格测试，让所有利益相关者参与工具开发。这正是我们论文的主旨。电子健康记录系统曾像拿着锤子找钉子，当时为快速普及牺牲了很多人的感受，让他们觉得这个系统并非为其最佳利益设计。

Trust in healthcare it's a huge issue that, again, people in in our department work a lot on, you're you know, yourself included. I'm a pro champions of the system. I am pro testing things heavily upfront, having stakeholders involving everyone in these tools. That's sort of what our paper was about. The EHR was sort of hammer looking for nails, and there was a lot of reasons to just get people up to date fast, which left a lot of people feeling like this thing was made not with them and their best interests in mind.

再次强调，人工智能已经存在一段时间了。它只是终于成熟到能够解决我们过去难以规模化处理的难题。我认为建立信任的关键在于，你需要感觉自己有能力质疑、叫停系统，而不是像卡夫卡式困境那样——一旦被AI接管就束手无策。否则人们会永远回避它，这种感受对患者和医护人员同样重要。

Again, AI has been around for a while. It's just finally graduated and come of age enough to answer some of the difficult questions we have had a hard time, you know, doing at scale before. I think that in order to have trust, you need to feel like you are able to push back, stop a system and not feel like a Kafkaesque, like once I'm put into the AI, it's just it, I'm stuck there. Then, because then you'll avoid it forever. And I think that goes to patient and provider side.

医护人员不希望被刻板定型。一个风险是机器为了确诊可能会建议做大量检查：CT扫描、血管造影、全套验血等。当收到无法执行的建议时，医患双方都会感到失望且束手无策，进而对整个系统产生怀疑。根据我的观察，信任源于能感受到自己是参与主体，并且在需要时能找到支持者。

Providers don't want to feel like they're always going be pigeonholed. One of the risks is maybe you're just going to do a ton of testing because in order for a machine to know what's going on, it's going to recommend the CT, the angio, all the blood work, whatever. So you'll be given a recommendation you can't do, you can't really fulfill, then you'll feel let down by it and you won't have any sort of recourse for your patient or if you are a patient to get anything else. So you'll just sort of feel down and distrustful and mistrustful of the system. So think from what I've seen, the trust comes from the ability to feel like you're an engaged member and that there's someone you can call up when you need a hand.

当前技术发展如此迅猛，以至于很多人感觉像是人类与计算机的对决。

And it's all happening so fast right now that I think many people feel like it's computers versus us.

看来我们面临诸多挑战啊。你提到医生们时常感到怀疑和不堪重负，能给他们什么建议吗？对于那些来找你咨询的人，你会怎么说？

So there's a lot coming our way, right? And I think you mentioned that physicians are feeling skeptical and overwhelmed at times. What advice can you give them? What do you say to those folks that come to you and Parts express

创新和信息处理本就是我们急诊科医生的日常。我们分析信息、开发工具——我认识的大多数急诊医生在这些方面都比我出色，尽管他们未必接受过信息学培训。关键是要主动接触技术，尽可能多地实践探索。

of innovation and informatics are all just what every emergency physician friend of ours does anyway. We process information. We try to build tools. Everyone, you know, most of the EM physicians I meet are as good or better than me at all of these things, they didn't necessarily do an informatics fellowship. That means engaging with the technology, experimenting with it wherever you can, trying stuff out to see and find.

就像超声技术刚应用时，最早是用于眼球检查（因为充满液体的结构适合超声成像），后来才逐步拓展到其他领域。从听诊器时代起，医学就是这样进步的。我的理解是：不必直接在临床治疗中尝试，但可以通过实践观察不同模型的效果。

Again, when ultrasound started, ultrasound was first used. I think its first medical use was on an eyeball because it's a fluid filled sac and ultrasound works really well in it. And then people started trying it on other stuff. This is the way that medicine advances and it has been doing that since the stethoscope. So really what that means to me is just, you don't have to do it on clinical care necessarily, but you can, you know, practice and see how different models work.

目前几乎所有AI工具都有免费版本可供体验（趁还没涨价）。多提问、多尝试，结合实际病例思考如何运用这些技术。急诊医学本就是通过试错前进的——只要不危及安全，就该积极探索未来方向。要实现你之前谈到的目标，唯一途径就是迈出第一步。

Free versions of almost all of these things are accessible right now before they eventually get more expensive. Ask questions, try stuff out, think about the cases you encounter, and then look to see if there's a way for these technologies to sort of help. I think that's actually normal academic emergency medicine and just emergency medicine is trial and error and not doing anything inherently dangerous, but trying, you know, trying to see where the future is gonna lie. The only way you get there is by taking your first steps and, you know, your first movements towards the end destination you're talking about earlier.

好的，这是一个很好的结束点，但我们总是喜欢以一个轻松些的问题来收尾。在我看来，你简直就是文艺复兴人的典范。我几乎找不到你不了解或没思考过的事物。那么，如果你不从事医学，你会做什么呢？

Well, that's a great place for us to leave it, but we always like to close with a question that's a little on the lighter side. So you, in my mind, are kind of the epitome of a Renaissance person. It's hard for me to find anything that you don't know about or think about. So if you weren't in medicine, what would you be doing?

天啊。我是说，这简直太

Oh my God. I mean, it's just so

除了所有事情之外。

Besides everything.

我知道。当我们脑海中冒出这些想法时，大多时候我们还是孩子。对我来说，我的心依然向往太空，你知道，我想成为一名宇航员，像卡尔·萨根那样回望地球，欣赏我们生活的这个淡蓝色小点。

I know. Well, when we come up with these in our heads, it's, you know, we're kids for the most part. And I think for me, my head is still in space and, you know, would to be an astronaut and get to look back on the earth like Carl Sagan and enjoy the pale blue dot that is the world that we live in.

我们的同事，尼尔·梅农。

Our colleague, Neil Menon.

我知道。

I know.

他已被选中明年进入太空，作为一名急诊医学医生，斯坦福大学的骄傲毕业生。所以别

Been selected to go to space next year, emergency medicine physician, proud grad of Stanford. So don't

放弃

give up

你的梦想吧，克里斯蒂安。说到这里，今天的节目就到此结束了。非常感谢罗斯医生分享他的见解和经验。显然，我们只是触及了这个快速发展的迷人领域的皮毛。请继续关注未来关于这个话题的更多内容。

on your dreams, Christian. On that note, that's a wrap for today's episode. Huge thanks to doctor Rose for sharing his insight and experience. Clearly, we've only scratched the surface of a fast moving and fascinating field. Keep tuning in for more on this topic in the future.

对于收听的朋友们，请务必查看节目说明，获取罗斯医生最新作品和研究的链接。如果你喜欢今天的节目，别忘了订阅、留下评论并与同事分享。一如既往，我们期待听到你的声音。通过描述中的链接向我们发送你的问题、想法或反馈。

For those listening, be sure to check out the show notes for links to Doctor. Rose's latest work and studies. If you liked today's episode, don't forget to subscribe, leave a review and share it with a colleague. And as always, we want to hear from you. Send us your questions, ideas or feedback at the link in the description.

感谢收听。我们下次再见。在此之前，请继续随时照顾任何人、任何事。我觉得你需要在精算师会议上发言。

Thanks for tuning in. We'll see you next time. Until then, keep taking care of anyone, anything, at any time. I think you need to speak at an actuarial conference.

你可以这样说，嘿，我知道你们面临什么，但伙计，别担心。那始终是现实生活中的目标。2026年欧洲精算师会议，宝贝。

You can just be like, hey, I know what you guys are facing, but man, don't worry about it. It's always Real life goal there. Actuarial Conference Europe twenty twenty six, baby.

没错。安排上吧。

That's right. Line it up.