Precision Radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework

Deep Learning
1

Did everyone see this?

Oakden-Rayner, Luke, et al. “Precision Radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework.” Scientific Reports 7.1 (2017): 1648.
https://www.nature.com/articles/s41598-017-01931-w

A convolutional neural network (ConvNet) was designed to predict all-cause mortality.

1 Like
2

Thanks for the link ! Unfortunately I missed that paper. This paper totally makes sense and the Nature reviewers can confirm.

Mix imaging data + labs data + clinical data as your initial state with genomic data + environmental data + time data as your direction in a shared multimodal deep learning model (ex. similar to one model to learn them all from google research) and you’ll predict where everyone are going. Getting access to all that data is a different story … in a politically favorable context, money or scientific/academic leadership can probably get access to that data.

1 Like