GRAM
Edward Choi, Mohammad Taha Bahadori, Le Song et al. · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · 2017
accuracy, data needs, interpretability) of GRAM to various methods including the recurrent neural network (RNN) in two sequential diagnoses prediction tasks and one heart failure prediction task. Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data. Additionally, unlike other methods, the medical concept representations learned by GRAM are well aligned with the medical ontology. Finally, GRAM exhibits intuitive attention behaviors by adaptively generalizing to higher level concepts when facing data insufficiency at the lower level concepts.
Cited by 635 works. doi:10.1145/3097983.3098126
Authors
References
- Long Short-Term Memory
- WordNet
- Glove: Global Vectors for Word Representation
- Visualizing Data using t-SNE
- Learning long-term dependencies with gradient descent is difficult
- Distributed Representations of Words and Phrases and their Compositionality
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- Neural Machine Translation by Jointly Learning to Align and Translate
- ADADELTA: An Adaptive Learning Rate Method
- PhysioBank, PhysioToolkit, and PhysioNet