search

greenelab / deep-review

A collaboratively written review paper on deep learning, genomics, and precision medicine
https://greenelab.github.io/deep-review/
Other
1.25k stars 270 forks source link

Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning #646

Closed agitter closed 1 day ago

agitter commented 7 years ago

https://arxiv.org/abs/1708.09843v1

Traditionally, medical discoveries are made by observing associations and then designing experiments to test these hypotheses. However, observing and quantifying associations in images can be difficult because of the wide variety of features, patterns, colors, values, shapes in real data. In this paper, we use deep learning, a machine learning technique that learns its own features, to discover new knowledge from retinal fundus images. Using models trained on data from 284,335 patients, and validated on two independent datasets of 12,026 and 999 patients, we predict cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as such as age (within 3.26 years), gender (0.97 AUC), smoking status (0.71 AUC), HbA1c (within 1.39%), systolic blood pressure (within 11.23mmHg) as well as major adverse cardiac events (0.70 AUC). We further show that our models used distinct aspects of the anatomy to generate each prediction, such as the optic disc or blood vessels, opening avenues of further research.

Omikar243 commented 1 day ago

Hi sir, Could you please upload the dataset you used in this research?

agitter commented 1 day ago

Hi @Omikar243, you'll have to contact the authors of this study. This issue was to discuss the manuscript as part of a review article about deep learning in biomedicine. Our team was not involved in the research.

Omikar243 commented 1 day ago

I'm sorry but can you give me their contact info or any means through which I can contact them?

agitter commented 1 day ago

I don't know how to contact them. I suggest checking their preprint. If there isn't contact information there, my general advice for finding contact information for a researcher is to search Google Scholar for recent papers they have published in hopes one of them has current contact information. However, that's outside the scope of this issue.