Brain scan 人物
An AI for an eye 眼科AI
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医疗AI的潜力和困境
文章中心是在说明医疗AI的潜力和困境. 第1-2段通过描述眼科医生皮尔斯·基恩的不同寻常的读物, 以及引用他的话突显: 基恩对计算机的热情. 且提出: 基恩拥有不逊于计算机专业大学生的能力, 且他与DeepMind合作开发眼科AI. 第3段提出眼科的现状: 供不应求的眼科医生. 且通过AI的高确诊率和对疾病的强预测能力证明AI在眼科领域的潜力. 第4-7段提出医疗AI的困境: 数据不是统一的可用格式; 在隐私和监管领域面临挑战; 不能对特定结论做出解释. 第8段对第3个困境给出建议: 重点关注最影响输出的那些输入; 将模型简化成流程图; 用户通过操作程序自行判断. 且提出: 专业差异导致更不好做出解释, 以及做出解释的重要性. 第9段对医疗AI的未来进行判断: AI不能直接代替医生.
[1] ①THE BOOKS strewn around Pearse Keane's office at Moorfields Eye Hospital in London are an unusual selection for a medic. ②"The Information", a 500-page doorstop by James Gleick on the mathematical roots of computer science, sits next to Neal Stephenson's even heftier "Cryptonom", an alt-history novel full of cryptography and prime numbers. ③Nearby is "The Player of Games" by the late lain M. Banks, whose sci-fi novels describe a utopian civilisation in which AI has abolished work.
①位于伦敦摩菲尔茨眼科医院的皮尔斯·基恩办公室里, 散落着一些书, 这些书看起来不像是一个医生会读的. ②詹姆斯·格雷克的500页厚的《信息简史》, 追溯了计算机科学的数学根基. 旁边放着更大部头的尼尔斯·蒂芬森所著《编码宝典》, 是一本充斥着密码学和质数的另类历史小说. ③附近有一本已故作家伊恩·班克斯所著的《游戏玩家》, 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.
[2] ①Dr Keane is an ophthalmologist by training. ②But "if I could have taken a year or two from my medical training to do a computer-science degree, I would have," he says. ③These days he is closer to the subject than any university student. ④In 2016 he began a collaboration with DeepMind, an AI firm owned by Google, to apply AI to ophthalmology.
①基恩是受正规训练的眼科医生. ②但他说, “如果我能从学医的时间里抽出一两年去获得计算机学位, 我是一定会去的.” ③如今, 他比任何大学生都要密切接触计算机科学. ④2016年, 他开始和谷歌旗下的AI公司DeepMind合作, 把AI应用到眼科.
[3] ①In 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. ②In theory, computers can help. ③In 2018 Moorfields and DeepMind published a paper describing an Al that, given a retina scan, could make correct referral decisions 94% of the time, matching human experts. ④A 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.
①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. ②理论上, 计算机能提供帮助. ③2018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. ④最近更新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.
[4] ①But 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. ②His work highlights three thorny problems that must be overcome if Al is to be rolled out more quickly, in medicine and elsewhere.
①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. ②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.
[5] ①The first is about getting data into coherent, usable format. ②"We often hear from medics saying they have a big dataset on one disease or another," says Dr Keane. ③"But when you ask basic questions about what format the data is in, we never hear from them again."
①首先是把数据变成统一的, 可用的格式. ②基恩说, "我们常听医生说, 他们手头有这种或那种病的大数据集." ③"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."
[6] ①Then there are the challenges of privacy and regulation. ②Laws 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.
①其次是隐私和监管方面的挑战. ②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.
[7] ①Finally there is the question of"explainability". ②Because AI systems learn from examples rather than following explicit rules, working out why they reach particular conclusions can be tricky. ③Researchers call this the "black box" problem. ④As AI spreads into areas such as medicine and law, solving it is becoming increasingly important.
①最后是"可解释性"的问题. ②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. ③研究人员把这称为"黑匣子"问题. ④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.
[8] ①One approach is to highlight which features in the model's input most strongly affect its output. ②Another is to boil models down into simplified flow-charts, or let users question them ("would moving this blob change the diagnosis?"). ③To 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. ④Solving this problem, he says, will be important both to mollify regulators and to give doctors confidence in the machines' opinions.
①一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. ②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?"). ③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. ④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.
[9] ①But 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." ②There is more to being a doctor than accurate diagnosis.
①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.” ②当医生不仅仅是要做出准确的诊断.
pioneering (a.)先驱性的
ophthalmologist (a.)眼科医生
pitfall (n.)困境
strewn (v.)散落
medic (n.)医生
doorstop (n.)笨重的东西
hefty (a.)健壮的 (比较级)heftier
alt-history (a.)另类历史的
late (a.)已故的
cryptography (n.)密码学
prime numbers (n.)素数
civilisation (n.)文明
abolish (v.)废除
by training 受过正规训练的
be (not) keeping up with 跟(不)上
high-street (n.)商业街
optician (n.)眼镜店
referral (n.)转送
the onset of disease/old age/winter 疾病的发作; 老年的开始; 冬天的来临
thorny (a.)棘手的
be to be rolled out 将正式推出(新产品); 将开展(新的政治运动)
coherent (a.)一致的
wrestle with (sth.)全力解决 (sb.)摔跤
tricky (a.)棘手的
boil A down to/into B 将A浓缩为B
blob (n.)斑点
To further complicate matters/To complicate matters further 使事情变得更复杂的是
drop-in (a.)直接使用的
I can't foresee a scenario in which... 我无法想象...
pop-up (n.)弹窗
There is more to being a doctor than accurate diagnosis. 当医生不仅仅是要做出准确的诊断.
Pearse Keane 皮尔斯·基恩
Moorfields Eye Hospital 摩菲尔茨眼科医院
The Information 《信息简史》
James Gleick 詹姆斯·格雷克
Neal Stephenson 尼尔·斯蒂芬森
Cryptonom 《编码宝典》
The Player of Games 《游戏玩家》
lain M. Banks 伊恩·班克斯
age-related macular degeneration 老年性黄斑变性
