经济学人双语版-眼科AI An AI for an eye

A pioneering ophthalmologist highlights the potential, and the pitfalls, of medical AI

一位勇于创新的眼科医生指出了医疗AI的潜力和困境【技术季刊《AI及其局限:比预期更陡峭》系列之四】

THE BOOKS strewn around Pearse Keane’s office at Moorfields Eye Hospital in London are an unusual selection for a medic. “The Information”, a 500-page doorstop by James Gleick on the mathematical roots of computer science, sits next to Neal Stephenson’s even heftier “Cryptonomicon”, an alt-history novel full of cryptography and prime numbers. Nearby is “The Player of Games” by the late Iain M. Banks, whose sci-fi novels describe a utopian civilisation in which AI has abolished work.

皮尔斯·基恩(Pearse Keane)位于伦敦摩菲尔茨眼科医院(Moorfields Eye Hospital)的办公室里散落着一些书,看起来不像是一个医生会读的。詹姆斯·格雷克(James Gleick)500页厚的《信息简史》(the Information)追溯计算机科学的数学根基。旁边放着尼尔·斯蒂芬森(Neal Stephenson)的《编码宝典》(Cryptonomicon),一本更大部头的、充斥着密码学和质数的另类历史小说。附近有一本《游戏玩家》(The Player of Games),已故作家伊恩·班克斯(Iain M. Banks)的这部科幻小说描述了一个被AI消灭了工作岗位的乌托邦文明。

Dr Keane is an ophthalmologist by training. But “if I could have taken a year or two from my medical training to do a computer-science degree, I would have,” he says. These days he is closer to the subject than any university student. In 2016 he began a collaboration with DeepMind, an AI firm owned by Google, to apply AI to ophthalmology.

基恩是科班出身的眼科医生。但他说,“如果我当年能从学医的时间里划出一两年来拿个计算机学位,我会的。”如今,他和计算机科学的密切接触超过了任何在校大学生。2016年,他开始和谷歌旗下的AI公司DeepMind合作,把AI应用到眼科。

In Britain the number of ophthalmologists is not keeping up with the falling cost of eye scans (about £20, or $25, from high-street opticians) and growing demand from an ageing population. In theory, computers can help. In 2018 Moorfields and DeepMind published a paper describing an AI that, given a retina scan, could make correct referral decisions 94% of the time, matching human experts. A more recent paper described a system that can predict the onset of age-related macular degeneration, a progressive disease that causes blindness, up to six months in advance.

在英国,眼球扫描的价格不断下跌(商业大街上的眼镜店标价在20英镑或25美元左右),同时人口老龄化导致了需求不断增长,但眼科医生的数量跟不上这些变化。从理论上讲,计算机可以提供帮助。2018年,摩菲尔茨眼科医院和DeepMind发表了一篇论文,描述一种AI在收到视网膜扫描后做出正确转诊决定的几率达94%,和人类专家相当。更新近的一篇论文介绍的一个系统可以提前最多半年预测出老年性黄斑变性,一种会导致失明的进行性疾病。

But Dr Keane cautions that in practice, moving from a lab demonstration to a real system takes time: the technology is not yet being used on real patients. His work highlights three thorny problems that must be overcome if AI is to be rolled out more quickly, in medicine and elsewhere.

但基恩提醒道,在实践中,从实验室演示发展成真正可用的系统需要时间,因而这项技术尚未在真实的患者身上使用。他的研究强调,要想在医学和其他领域加速推广AI,必须克服三个棘手问题。

The first is about getting data into a coherent, usable format. “We often hear from medics saying they have a big dataset on one disease or another,” says Dr Keane. “But when you ask basic questions about what format the data is in, we never hear from them again.”

首先是把数据变成统一的、可用的格式。“我们常听医生说,他们手头有这种或那种病的大数据集,”基恩说,“但当你问起这些数据是什么格式之类的基本问题,就再没有下文了。”

Then there are the challenges of privacy and regulation. Laws guarding medical records tend to be fierce, and regulators are still wrestling with the question of how exactly to subject AI systems to clinical trials.

其次是隐私和监管方面的挑战。保护病历的法规往往都很严苛,而监管机构还在为到底该如何制定AI系统的临床试验要求的问题斗争。

Finally there is the question of “explainability”. Because AI systems learn from examples rather than following explicit rules, working out why they reach particular conclusions can be tricky. Researchers call this the “black box” problem. As AI spreads into areas such as medicine and law, solving it is becoming increasingly important.

最后是“可解释性”的问题。因为AI系统是从样本中学习,而不是遵循明确的规则,所以要搞明白它们何以得出特定的结论可能很难。研究人员把这称为“黑匣子”问题。随着AI扩展到医学和法律等领域,解决这个问题变得越来越重要。

One approach is to highlight which features in the model’s input most strongly affect its output. Another is to boil models down into simplified flow-charts, or let users question them (“would moving this blob change the diagnosis?”). To further complicate matters, notes Dr Keane, techies building a system may prefer one kind of explainability for testing purposes, while medics using it might want something closer to clinical reasoning. Solving this problem, he says, will be important both to mollify regulators and to give doctors confidence in the machines’ opinions.

一种解决方法是突出显示模型输入中哪些特征对输出的影响最大。另一个是将模型浓缩为简易的流程图,或让用户对它们提出质疑(“移动这个斑点是否会改变诊断?”)基恩指出,让事情变得更复杂的是,构建AI系统的技术人员可能在测试中倾向于某种可解释性,而使用系统的医务人员可能想要某种更接近于临床推理的东西。他说,解决这个问题对于让监管机构放心和让医生对机器的意见有信心都很重要。

But even when it is widely deployed, AI will remain a backroom tool, not a drop-in replacement for human medics, he predicts: “I can’t foresee a scenario in which a pop-up on your iPhone tells you you’ve got cancer.” There is more to being a doctor than accurate diagnosis.

但是他预测,即使被广泛部署,AI仍将只是一种后台工具,而不是医务人员的直接替代品。“我无法想象你的iPhone上弹出一个窗口,告诉你你得了癌症。”当医生不仅仅是要做出准确的诊断。

 

上百种外刊不间断更新,可以加微信(185855023)或扫下方二维码咨询。

 

外刊VIP介绍:点击查看

猜你 喜欢

发表评论

电子邮件地址不会被公开。