Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification

TL;DR

This paper introduces a deep ensemble tensor factorization method for classifying sparse longitudinal patient data, achieving high accuracy in predicting in-hospital mortality from ICU measurements.

Contribution

It proposes a novel combination of generative tensor factorization and ensemble deep learning models for robust classification of longitudinal health data.

Findings

Achieves over 0.85 AUC in mortality prediction

Outperforms SAPS-II and GRU baselines

Effective on sparse, high-dimensional ICU data

Abstract

We present a generative approach to classify scarcely observed longitudinal patient trajectories. The available time series are represented as tensors and factorized using generative deep recurrent neural networks. The learned factors represent the patient data in a compact way and can then be used in a downstream classification task. For more robustness and accuracy in the predictions, we used an ensemble of those deep generative models to mimic Bayesian posterior sampling. We illustrate the performance of our architecture on an intensive-care case study of in-hospital mortality prediction with 96 longitudinal measurement types measured across the first 48-hour from admission. Our combination of generative and ensemble strategies achieves an AUC of over 0.85, and outperforms the SAPS-II mortality score and GRU baselines.