Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification
This work addresses mortality prediction in intensive care, offering a robust method for handling sparse longitudinal data, though it is incremental in combining existing generative and ensemble techniques.
The paper tackled classifying scarcely observed longitudinal patient trajectories by developing a generative deep ensemble tensor factorization method, achieving an AUC over 0.85 and outperforming SAPS-II and GRU baselines on an intensive-care mortality prediction task.
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.