Doctor AI: Predicting Clinical Events via Recurrent Neural Networks

By Edward Choi, Mohammad Taha Bahadori, Andy Schuetz, Walter F. Stewart, Jimeng Sun. 2015

Subfields: Model Architectures, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

In Medical & Health AI

Citations in the corpus

Neural Ordinary Differential Equations (2018, neutral): “We trained a second version of this RNN whose inputs were concatenated with the time difference to the next observation to aid RNN with irregular observations.”
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability (2017, background): “(Miotto et al. 2016; Choi et al. 2016; Che et al. 2015)), the clinical community remains skeptical of machine learning systems”
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (2016, methodology): “For example, in disease progression modeling (DPM) [11], each visit of a patient visit sequence is represented by a set of varying number of medical codes {c1, c2, .”
Interpretable and Steerable Sequence Learning via Prototypes (2019, methodology): “en to be very effective in modeling sequence data. They have been successfully applied to sentiment analysis [34], ECG signal classification [16], mortality and disease risk prediction using EHR data [8, 10, 13], and etc.. Despite their impressive performance, these deep learning models consist of c”
Interval Coded Scoring: a toolbox for interpretable scoring systems (2018, neutral): “A ﬁnal example is the so-called ‘doctor AI’ system (Choi et al., 2016).”
Interpretable Representation Learning for Healthcare via Capturing Disease Progression through Time (2018, background): “Several recent studies showed that predictive modeling of EHR data using RNNs can significantly outperform traditional models such as logistic regression, multilayer perceptron (MLP), and support vector machine (SVM), which all depend on feature engineering [6, 18, 23].”
Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation (2018, methodology): “s best performance on the validation dataset. - Basic-LSTM (BL): BL uses LSTM to recommend the sequential medications based on the longitudinal and temporal records of patients. Inspired by Doctor-AI [9], BL fuses multi-sources of patient-specific information and considers each admission of a patien”
Recurrent Neural Networks for Multivariate Time Series with Missing Values (2016, critical): “Recently RNN models have been explored for modeling diseases and patient diagnosis in health care domain [14, 5, 19] using doctor notes but are not readily applicable for comparison in our time series classiﬁcation tasks since they don’t handle missing data.”
Explainable Prediction of Medical Codes from Clinical Text (2018, methodology): “From the application perspective, we plan to build models that leverage hierarchy of ICD codes (Choi et al., 2016), and to attempt the more diﬃcult task of predicting diagnosis and treatment codes for future visits from discharge summaries.”
GRAM: Graph-based Attention Model for Healthcare Representation Learning (2016, methodology): “To address these challenges, we propose GRaph-based Attention Model (GRAM) that supplements electronic health records (EHR) with hierarchical information inherent to medical ontologies.”
Scalable and accurate deep learning with electronic health records (2018, background): “eling the temporal sequence of events that occurred in a patient’s record, which may enhance accuracy in scenarios that depend on the order of events, with convolutional and recurrent neural networks [61, 2, 17, 81, 16, 92]. In general, prior work has focused on a subset of features available in the”
Information Leakage in Embedding Models (2020, background): “Machine learning (ML) has seen an explosive growth over the past decade and is now widely used across industry from image analysis [24, 34], speech recognition [22], and even in applications in the medical sciences for diagnosis [8, 54].”
Meaningful Explanations of Black Box AI Decision Systems (2019, methodology): “The platform should enable validating our approach in realistic cases in challenging domains, such as health-care, e.g., explaining systems such as DoctorAI, based on a multi-label Recurrent Neural Network trained on patients’ Electronic Health Records (Choi et al. 2016).”
Multitask learning and benchmarking with clinical time series data (2017, unknown): “Rather than attempt to assign timestamps using a heuristic, we decided instead to embrace this limitation.”
Attentive State-Space Modeling of Disease Progression (2019, unknown): “, “Doctor AI” [11], “L2D” [12], and “Disease-Atlas” [13].”