Deep Computational Phenotyping

Che, Zhengping; Kale, David C.; Li, Wenzhe; Bahadori, Mohammad Taha; Liu, Yanping

doi:10.1145/2783258.2783365

Cited by 218 publications

(159 citation statements)

References 19 publications

Supporting

Mentioning

158

Contrasting

Order By: Relevance

“…LSTM has recently been popularized through success in machine translation [20], image caption generation [25] and clinical diagnosis [2]. An attractive property of the LSTM is that it is capable of learning both long term and short term temporal dependencies.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting

Shahabi

et al. 2017

Proceedings of the 2017 SIAM International Conference on Data Mining

Self Cite

341

169

View full text Add to dashboard Cite

Traffic forecasting is a vital part of intelligent transportation systems. It becomes particularly challenging due to short-term (e.g., accidents, constructions) and long-term (e.g., peak-hour, seasonal, weather) traffic patterns. While most of the previously proposed techniques focus on normal condition forecasting, a single framework for extreme condition traffic forecasting does not exist. To address this need, we propose to take a deep learning approach. We build a deep neural network based on long short term memory (LSTM) units. We apply Deep LSTM to forecast peak-hour traffic and manage to identify unique characteristics of the traffic data. We further improve the model for postaccident forecasting with Mixture Deep LSTM model. It jointly models the normal condition traffic and the pattern of accidents. We evaluate our model on a realworld large-scale traffic dataset in Los Angeles. When trained end-to-end with suitable regularization, our approach achieves 30%-50% improvement over baselines. We also demonstrate a novel technique to interpret the model with signal stimulation. We note interesting observations from the trained neural network.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting

Shahabi

et al. 2017

Proceedings of the 2017 SIAM International Conference on Data Mining

Self Cite

341

169

View full text Add to dashboard Cite

show abstract

“…Deep learning methods have also been employed in a wide range of EMR data analytic tasks [21], including ICU mortality prediction [4,20], diagnosis [19], and interpretable phenotype learning in clinical decision making [5]. These works partition the irregular EMR data into regular time windows (non-overlapping [5,19,20] or overlapping [4]).…”

Section: Transforming Into Regular Time Series Datamentioning

confidence: 99%

“…These works partition the irregular EMR data into regular time windows (non-overlapping [5,19,20] or overlapping [4]). These methods may not be able to capture feature patterns within a short time (i.e., within a window) as they miss the fine-grained visit-level information.…”

Section: Transforming Into Regular Time Series Datamentioning

confidence: 99%

“…Second, we compute the temporary hidden state h (t ) as shown in Equation 4. We can see that the reset gate plays an important role in computing the new hidden h (t ) .…”

Section: Standard Gru For Dpm Problemmentioning

confidence: 99%

“…For a visit at time t, we denote each feature d's time span from its nearest previous occurrence as δ 4 is the time from the second visit to the fourth visit, which is five weeks; δ (6) 5 is the time between the third visit and the fourth visit, which is three weeks. The difference between δ 4 In Figure 4, we choose x D as the label feature for illustration purpose. Each appearance of x D after CutPoint gives one y for prediction.…”

Section: Feature-level Time Decay Modelmentioning

confidence: 99%

See 2 more Smart Citations

Capturing Feature-Level Irregularity in Disease Progression Modeling

Zheng

Wang

Gao

et al. 2017

Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Disease progression modeling (DPM) analyzes patients' electronic medical records (EMR) to predict the health state of patients, which facilitates accurate prognosis, early detection and treatment of chronic diseases. However, EMR are irregular because patients visit hospital irregularly based on the need of treatment. For each visit, they are typically given different diagnoses, prescribed various medications and lab tests. Consequently, EMR exhibit irregularity at the feature level. To handle this issue, we propose a model based on the Gated Recurrent Unit by decaying the effect of previous records using fine-grained feature-level time span information, and learn the decaying parameters for different features to take into account their different behaviours like decaying speeds under irregularity. Extensive experimental results in both an Alzheimer's disease dataset and a chronic kidney disease dataset demonstrate that our proposed model of capturing feature-level irregularity can effectively improve the accuracy of DPM.

show abstract

Deep Learning for Medical Healthcare: Issues, Challenges, and Opportunities

Gupta

Kaur

2021

Computational Analysis and Deep Learning for Medical Care

View full text Add to dashboard Cite

Deep Computational Phenotyping

Cited by 218 publications

References 19 publications

Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting

Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting

Capturing Feature-Level Irregularity in Disease Progression Modeling

Deep Learning for Medical Healthcare: Issues, Challenges, and Opportunities

Contact Info

Product

Resources

About