Early diagnosis of treatable diseases is essential for improving healthcare, and many diseases' onsets are predictable from annual lab tests and their temporal trends. We introduce a multi-resolution convolutional neural network for early detection of multiple diseases from irregularly measured sparse lab values. Our novel architecture takes as input both an imputed version of the data and a binary observation matrix. For imputing the temporal sparse observations, we develop a flexible, fast to train method for differentiable multivariate kernel regression. Our experiments on data from 298K individuals over 8 years, 18 common lab measurements, and 171 diseases show that the temporal signatures learned via convolution are significantly more predictive than baselines commonly used for early disease diagnosis.
@article{arxiv.1511.07938,
title = {Temporal Convolutional Neural Networks for Diagnosis from Lab Tests},
author = {Narges Razavian and David Sontag},
journal= {arXiv preprint arXiv:1511.07938},
year = {2016}
}