Interpretable Predictions of Clinical Outcomes with An Attention-based Recurrent Neural Network
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
The increasing accumulation of healthcare data provides researchers with ample opportunities to build machine learning approaches for clinical decision support and to improve the quality of health care. Several studies have developed conventional machine learning approaches that rely heavily on manual feature engineering and result in task-specific models for health care. In contrast, healthcare researchers have begun to use deep learning, which has emerged as a revolutionary machine learning technique that obviates manual feature engineering but still achieves impressive results in research fields such as image classification. However, few of them have addressed the lack of the interpretability of deep learning models although interpretability is essential for the successful adoption of machine learning approaches by healthcare communities. In addition, the unique characteristics of healthcare data such as high dimensionality and temporal dependencies pose challenges for building models on healthcare data. To address these challenges, we develop a gated recurrent unit-based recurrent neural network with hierarchical attention for mortality prediction, and then, using the diagnostic codes from the Medical Information Mart for Intensive Care, we evaluate the model. We find that the prediction accuracy of the model outperforms baseline models and demonstrate the interpretability of the model in visualizations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“The purpose of introducing sophisticated activation functions is to overcome the vanishing gradient problem, which causes difficulties of training an RNN to capture long-term dependencies [2; 13].”
BackgroundComparison of the predicted and observed secondary structure of T4 phage lysozyme
Matthews, B. W. (1975) · Biochimica et Biophysica Acta (BBA) - Protein Structure · doi:10.1016/0005-2795(75)90109-9 · Cited by 5,399 · cited 1×
“MCC is an appropriate indicator of the quality of binary classification even when the sizes of both classes in a dataset significantly differ [24].”
BackgroundDeep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
Tests for comparing elements of a correlation matrix
Steiger, J. H. (1980) · Psychological Bulletin · doi:10.1037/0033-2909.87.2.245 · Cited by 4,621 · cited 1×
“Using Steiger’s test [34], which is a statistical test for comparing two dependent correlations, we find the two”
MethodThe Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
Hochreiter, S. (1998) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488598000094 · Cited by 2,939
(1992) · doi:10.5555/176313.176316 · Cited by 2,892
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710 · cited 1×
“utilized denoising autoencoders to produce a compact and general representation of electronic health records that demonstrated better prediction accuracy when used in downstream analysis than the representation produced by conventional dimensional reduction approaches [26].”
MethodMining electronic health records: towards better research applications and clinical care
Jensen, P. B., Jensen, L. J., & Brunak, S. (2012) · Nature Reviews Genetics · doi:10.1038/nrg3208 · Cited by 1,680 · cited 1×
“Conventional predictive models of clinical decision support rely heavily on feature engineering, such as ranking and selecting features based on certain criteria [12; 15; 31], which results in classifier-dependent features and task-specific models.”
MethodFree, C., Phillips, G., Watson, L., Galli, L., Felix, L., Edwards, P., Patel, V., & Haines, A. (2013) · PLoS Medicine · doi:10.1371/journal.pmed.1001363 · Cited by 1,187 · cited 2×
“We choose gamma over the logarithmic range of [10-2, 1] and regularization penalty parameter C over the logarithmic range of [10-2, 10].”
BackgroundMethodDeep Visual-Semantic Alignments for Generating Image Descriptions
Karpathy, A., & Fei-Fei, L. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2598339 · Cited by 1,048
Health Information Technology: An Updated Systematic Review With a Focus on Meaningful Use
Jones, S. S., Rudin, R. S., Perry, T., & Shekelle, P. G. (2014) · Annals of Internal Medicine · doi:10.7326/m13-1531 · Cited by 475
DeepCare: A Deep Dynamic Memory Model for Predictive Medicine
Pham, T., Tran, T., Phung, D., & Venkatesh, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-31750-2_3 · Cited by 269
Cited by
Explainable Deep Learning Models in Medical Image Analysis
Singh, A., Sengupta, S., & Lakshminarayanan, V. (2020) · Journal of Imaging · doi:10.3390/jimaging6060052 · Cited by 718
“cause of the detailed information presented by the images. However, patient records also provide rich information for diagnosis and there were studies discussing their explainability. For example, in [67] a gated recurrent unit (GRU)-based recurrent neural network (RNN) for mortality prediction from diagnostic codes f…”
BackgroundVellido, A. (2020) · Neural Computing and Applications · doi:10.1007/s00521-019-04051-w · Cited by 635
Nasarian, E., Alizadehsani, R., Acharya, U. R., & Tsui, K.-L. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102412 · Cited by 207
Interpretable Representation Learning for Healthcare via Capturing Disease Progression through Time
Bai, T., Zhang, S., Egleston, B. L., & Vucetic, S. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219904 · Cited by 180
RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data
Xu, Y., Biswal, S., Deshpande, S. R., Maher, K. O., & Sun, J. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220051 · Cited by 144
“Later on, graph based attention [6] and hierarchical attention [42] were adapted for incorporating external information like medical ontologies into the deep EHR models; different deep architectures like bidirectional RNN [32], GRU [24] were also applied for improving predictive accuracy.”
Method
Metadata
- Authors
- Sha, Y., & Wang, M. D.
- Venue
- Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics
- Publisher
- ACM
- Published
- 2017-08-20
- Volume
- 2017
- Pages
- 233-240
- OpenAlex
- W2745673637
- Cited by
- 97
- References
- 15
- FWCI
- 4.45
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.