Context-Aware and Time-Aware Attention-Based Model for Disease Risk Prediction With Interpretability
- 23 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (4) , 3551-3562
Abstract
Thanks to the huge accumulation of Electronic Health Records (EHRs)numerous deep learning-based predictive models were proposed for this task. Among them, most of the existing state-of-the-art (SOTA) models were built with recurrent neural networks (RNNs). Regardless of their success, RNN-based models mainly suffer from three limitations. (i) Accuracy: the prediction accuracy of RNN-based models drops quickly as the length of EHR sequences increases. (ii) Efficiency: the recurrence property of RNN-based models makes the computation parallelization impossible, and accordingly hurts the efficiency of such models in practice. (iii) Interpretability: the outputs of RNN-based models are difficult to explain due to the unexplainable nature of deep models. In this paper, we resort to the recently advanced attention mechanism to model the dependencies between inputs and outputs, which overcomes shortages of RNN-based models in accuracy and efficiency. As for interpretability, we model the relationships with two linear mappings from the input to the output, which account for two important factors---one is for context-aware information and the other is for time-aware representation---of capturing discriminative features in learning patient's representations. We empirically demonstrate the effectiveness of the proposed model in both accuracy and computational efficiency, meanwhile, analyze and discuss the reasonability of each explanation approach.Keywords
Funding Information
- National Key Research and Development Program of China (2016YFB1000303, 2018YFC130078)
- National Natural Science Foundation of China (61532015, 61672420)
- China Knowledge Center for Engineering Science and Technology
- Chinese Academy of Engineering
- National Natural Science Foundation of China (61721002)
- Innovation Research Team of Ministry of Education (IRT 17R86)
- Cernet Next Generation Internet Technology Innovation Project
This publication has 28 references indexed in Scilit:
- GRAM2017
- Measuring Patient Similarities via a Deep Architecture with Medical Concept Embedding2016
- Risk Prediction with Electronic Health Records: A Deep Learning Approach2016
- Image Captioning with Semantic Attention2016
- Bringing cohort studies to the bedside: framework for a ‘green button’ to support clinical decision-makingJournal of Comparative Effectiveness Research, 2015
- Effective Approaches to Attention-based Neural Machine Translation2015
- Supervised patient similarity measure of heterogeneous patient recordsACM SIGKDD Explorations Newsletter, 2012
- Use of diverse electronic medical record systems to identify genetic risk for type 2 diabetes within a genome-wide association studyJournal of the American Medical Informatics Association, 2012
- Clinical predictors of progression to Alzheimer disease in amnestic mild cognitive impairmentNeurology, 2007
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997