谷歌人工智能可以通过扫描眼睛来预测心脏病

Alphabet’s health science company Verily has announced a wide range of projects, from developing smartwatches made for medical studies to mass-producing infected mosquitoes to curb their population.Scientists from the division now have a new endeavor: Assessing heart disease risk by staring into patients’ eyes.

Alphabet旗下的健康科学公司已经宣布了一系列广泛的项目，从开发用于医学研究的智能手表，到大规模生产受感染的蚊子，以控制人口。来自该部门的科学家现在有了新的尝试：通过扫描病人的眼睛来评估心脏病的风险。

In a paper (PDF) published today in the Nature journal Biomedical Engineering, researchers explained their method: An AI algorithm evaluated eye scans and, after refining its model with machine learning, was able to predict cardiovascular risk factors like age, gender and blood pressure.This could lead to easier and potentially quicker analysis than a blood test with roughly the same accuracy as current methods.

在今天发表在Nature杂志生物医学工程上的一篇PDF格式论文中，研究人员解释了他们的方法：人工智能算法评估了眼睛的扫描结果，在用机器学习的方法改进了模型后，能够预测诸如年龄、性别和血压等心血管疾病的风险因素。这可能会比血液检测更容易，也可能更快地进行分析，其准确度与目前的方法大致相同。

The study isn’t without limitations, given that it only surveyed eye images with a 45-degree field of view.More research would resolve whether the model needs to be adjusted for larger or smaller photos, and a larger data set than what the researchers used is more appropriate for deep learning.In other words, it’s not yet ready for clinical testing, but it’s a promising start for non-invasive evaluation of cardiovascular health.

这项研究并不是没有限制的，因为它只研究了45度视野的眼睛图像。是否需要根据更大的或更小的照片调整该模型还需进一步研究，并且要建立深度学习还需要比已有研究更大的数据库。换句话说，目前还不适合进行临床试验，但是对于非侵入性的心血管健康评估来说，已经有了希望的曙光。