Diagnosis Prediction via Medical Context Attention Networks Using Deep Generative Modeling

Proceedings of the Web Conference 2020

et al. 2020

Deep learning has demonstrated success in health risk prediction especially for patients with chronic and progressing conditions. Most existing works focus on learning disease patterns from longitudinal patient data, but pay little attention to the disease progression stage itself. To fill the gap, we propose a Stage-aware neural Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction. StageNet is enabled by (1) a stage-aware long short-term memory (LSTM) module that extracts health stage variations unsupervisedly; (2) a stage-adaptive convolutional module that incorporates stage-related progression patterns into risk prediction. We evaluate StageNet on two real-world datasets and show that StageNet outperforms state-of-the-art models in risk prediction task and patient subtyping task. Compared to the best baseline model, StageNet achieves up to 12% higher AUPRC for risk prediction task on two real-world patient datasets. StageNet also achieves over 58% higher Calinski-Harabasz score (a cluster quality metric) for a patient subtyping task.

Section: Baselinesmentioning

confidence: 99%

StageNet: Stage-Aware Neural Networks for Health Risk Prediction

Gao

Xiao

Proceedings of the Web Conference 2020

et al. 2020

“…G2: Demographics-aware model. The model MCA-RNN [2] utilizes patient demographics in diagnosis prediction.…”

Section: A Experimental Settingsmentioning

confidence: 99%

“…Nowadays, Electronic Health Record (EHR) systems are widely adopted to record longitudinal patient health data such as diagnosis, medications, and procedures, which enables the possibility of clinical predictive tasks. Predicting future diagnosis based on patient's historical records of diagnosis, i.e., diagnosis prediction [1], [2], has become a cornerstone of personalized healthcare. This task attracts considerable attention in both industry and the research community because of their importance in need anticipation and precision medicine [2], [3].…”

Section: Introductionmentioning

confidence: 99%

“…Predicting future diagnosis based on patient's historical records of diagnosis, i.e., diagnosis prediction [1], [2], has become a cornerstone of personalized healthcare. This task attracts considerable attention in both industry and the research community because of their importance in need anticipation and precision medicine [2], [3]. Although there is broad consensus on its importance, diagnosis prediction is challenging due to the sequential, high-dimensional, and noisy nature of EHR data.…”

Section: Introductionmentioning

confidence: 99%

“…C2: Existing methods cannot model the mutual effect between important context and historical records. Patient demographics are considered important context in the domain of diagnosis prediction [2], [9]. However, how to model the mutual effect between patient demographics and their diagnosed diseases has not been explored, which limits the accuracy of existing methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CAMP: Co-Attention Memory Networks for Diagnosis Prediction in Healthcare

Gao

2019 IEEE International Conference on Data Mining (ICDM)

et al. 2019

Diagnosis prediction, which aims to predict future health information of patients from historical electronic health records (EHRs), is a core research task in personalized healthcare. Although some RNN-based methods have been proposed to model sequential EHR data, these methods have two major issues. First, they cannot capture fine-grained progression patterns of patient health conditions. Second, they do not consider the mutual effect between important context (e.g., patient demographics) and historical diagnosis. To tackle these challenges, we propose a model called Co-Attention Memory networks for diagnosis Prediction (CAMP), which tightly integrates historical records, fine-grained patient conditions, and demographics with a threeway interaction architecture built on co-attention. Our model augments RNNs with a memory network to enrich the representation capacity. The memory network enables analysis of finegrained patient conditions by explicitly incorporating a taxonomy of diseases into an array of memory slots. We instantiate the READ/WRITE operations of the memory network so that the memory cooperates effectively with the patient demographics through co-attention mechanism. Experiments on real-world datasets demonstrate that CAMP consistently performs better than state-of-the-art methods.

Medical concept integrated residual short‐long temporal convolutional networks for predicting clinical events

Yang

Concurrency and Computation

2022

Large collections of electronic clinical data today provide us with a vast source of information on medical practice. However, the utilization of those data for exploratory analysis to support clinical decisions is still limited. It is particularly challenging for extracting useful disease progression patterns from such data because it is longitudinal, incomplete, irregular, and heterogeneous of the patient conditions. In this article, we propose an integrated clinical event prediction model medical concept integrated residual short-long temporal convolutional networks (SL-TCN) to address these challenges. Compared to existing models, our model has three-fold advantages: (1) it learns a compact set of medical concepts as the bridge between the hidden progression process and the observed medical evidence. ( 2) it learns a continuous-time progression model from discrete-time observations with nonequal intervals and high-dimensional features. (3) We fuse the temporal convolutional network, the long short-term memory network, and the residual connector so as to capture the local and global dependency of the sequence and make the clinical event predictions more robust. Through extensive experiments on the MIMIC III dataset, we demonstrate that our SL-TCN achieves higher precision in clinical event prediction and derives some interesting clinical insights.