Temporal Convolutional Neural Networks for Diagnosis from Lab Tests
arXiv:1511.07938
Abstract
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.
Cited by in corpus (14)
- GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
- ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
- Deep EHR: Chronic Disease Prediction Using Medical Notes
- Multi-task Prediction of Disease Onsets from Longitudinal Lab Tests
- Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding
- Deepr: A Convolutional Net for Medical Records
- Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
- Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks
- Temporal-Clustering Invariance in Irregular Healthcare Time Series
- Dynamic Weight Alignment for Temporal Convolutional Neural Networks
- ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information
- A latent topic model for mining heterogenous non-randomly missing electronic health records data
- Supervised multi-specialist topic model with applications on large-scale electronic health record data
- Recurrent Neural Networks based Obesity Status Prediction Using Activity Data