Disentangled representation for sequential treatment effect estimation.

BACKGROUND AND OBJECTIVE: Treatment effect estimation, as a fundamental problem in causal inference, focuses on estimating the outcome difference between different treatments. However, in clinical observational data, some patient covariates (such as gender, age) not only affect the outcomes but also affect the treatment assignment. Such covariates, named as confounders, produce distribution discrepancies between different treatment groups, thereby introducing the selection bias for the estimation of treatment effects. The situation is even more complicated in longitudinal data, because the confounders are time-varying that are subject to patient history and meanwhile affect the future outcomes and treatment assignments. Existing methods mainly work on cross-sectional data obtained at a specific time point, but cannot process the time-varying confounders hidden in the longitudinal data. METHODS: In this study, we address this problem for the first time by disentangled representation learning, which considers the observational data as consisting of three components, including outcome-specific factors, treatment-specific factors, and time-varying confounders. Based on this, the proposed approach adopts a recurrent neural network-based framework to process sequential information and learn the disentangled representations of the components from longitudinal observational sequences, captures the posterior distributions of latent factors by multi-task learning strategy. Moreover, mutual information-based regularization is adopted to eliminate the time-varying confounders. In this way, the association between patient history and treatment assignment is removed and the estimation can be effectively conducted. RESULTS: We evaluate our model in a realistic set-up using a model of tumor growth. The proposed model achieves the best performance over benchmark models for both one-step ahead prediction (0.70% vs 0.74% for the-state-of-the-art model, when γ = 3. Measured by normalized root mean square error, the lower the better) and five-step ahead prediction (1.47% vs 1.83%) in most cases. By increasing the effect of confounders, our proposed model always shows superiority against the state-of-the-art model. In addition, we adopted T-SNE to visualize the disentangled representations and present the effectiveness of disentanglement explicitly and intuitively. CONCLUSIONS: The experimental results indicate the powerful capacity of our model in learning disentangled representations from longitudinal observational data and dealing with the time-varying confounders, and demonstrate the surpassing performance achieved by our proposed model on dynamic treatment effect estimation.

On learning disentangled representations for individual treatment effect estimation.

OBJECTIVE: Estimating the individualized treatment effect (ITE) from observational data is a challenging task due to selection bias, which results from the distributional discrepancy between different treatment groups caused by the dependence between features and assigned treatments. This dependence is induced by the factors related to the treatment assignment. We hypothesize that features consist of three types of latent factors: outcome-specific factors, treatment-specific factors and confounders. Then, we aim to reduce the influence of treatment-related factors, i.e., treatment-specific factors and confounders, on outcome prediction to mitigate the effects of selection bias. METHOD: We present a novel representation learning model in which both the main task of outcome prediction and the auxiliary task of classifying the treatment assignment are used to learn the outcome-oriented and treatment-oriented latent representations, respectively. However, since the confounders are related to both treatment assignment and outcome, it is still contained in the representations. To further reduce influence of the confounders contained in both representations, individualized orthogonal regularization is incorporated into the proposed model. The orthogonal regularization forces the outcome-oriented and treatment-oriented latent representations of an individual to be vertical in the inner product space, meaning they are orthogonal with each other, and the common information of confounder is reduced. Such that the ITE can be estimated more precisely without the effects of selection bias. RESULT: We evaluate our proposed model on a semi-simulated dataset and a real-world dataset. The experimental results demonstrate that the proposed model achieves competitive or better performance compared with the performances of the state-of-the-art models. CONCLUSION: The proposed method is well performed on ITE estimation with the ability to reduce selection bias thoroughly by incorporating an auxiliary task and adopting orthogonal regularization to disentangle the latent factors. SIGNIFICANCE: This paper offers a novel method of reducing selection bias in estimating the ITE from observational data by disentangled representation learning.

Knowledge-aware multi-center clinical dataset adaptation: Problem, method, and application.

Adaptable utilization of clinical data collected from multiple centers, prompted by the need to overcome the shifts between the dataset distributions, and exploit these different datasets for potential clinical applications, has received significant attention in recent years. In this study, we propose a novel approach to this task by infusing an external knowledge graph (KG) into multi-center clinical data mining. Specifically, we propose an adversarial learning model to capture shared patient feature representations from multi-center heterogeneous clinical datasets, and employ an external KG to enrich the semantics of the patient sample by providing both clinical center-specific and center-general knowledge features, which are trained with a graph convolutional autoencoder. We evaluate the proposed model on a real clinical dataset extracted from the general cardiology wards of a Chinese hospital and a well-known public clinical dataset (MIMIC III, pertaining to ICU clinical settings) for the task of predicting acute kidney injury in patients with heart failure. The achieved experimental results demonstrate the efficacy of our proposed model.

Treatment effect prediction with adversarial deep learning using electronic health records.

BACKGROUND: Treatment effect prediction (TEP) plays an important role in disease management by ensuring that the expected clinical outcomes are obtained after performing specialized and sophisticated treatments on patients given their personalized clinical status. In recent years, the wide adoption of electronic health records (EHRs) has provided a comprehensive data source for intelligent clinical applications including the TEP investigated in this study. METHOD: We examined the problem of using a large volume of heterogeneous EHR data to predict treatment effects and developed an adversarial deep treatment effect prediction model to address the problem. Our model employed two auto-encoders for learning the representative and discriminative features of both patient characteristics and treatments from EHR data. The discriminative power of the learned features was further enhanced by decoding the correlational information between the patient characteristics and subsequent treatments by means of a generated adversarial learning strategy. Thereafter, a logistic regression layer was appended on the top of the resulting feature representation layer for TEP. RESULT: The proposed model was evaluated on two real clinical datasets collected from the cardiology department of a Chinese hospital. In particular, on acute coronary syndrome (ACS) dataset, the proposed adversarial deep treatment effect prediction (ADTEP) (0.662) exhibited 1.4, 2.2, and 6.3% performance gains in terms of the area under the ROC curve (AUC) over deep treatment effect prediction (DTEP) (0.653), logistic regression (LR) (0.648), and support vector machine (SVM) (0.621), respectively. As for heart failure (HF) case study, the proposed ADTEP also outperformed all benchmarks. The experimental results demonstrated that our proposed model achieved competitive performance compared to state-of-the-art models in tackling the TEP problem. CONCLUSION: In this work, we propose a novel model to address the TEP problem by utilizing a large volume of observational data from EHR. With adversarial learning strategy, our proposed model can further explore the correlational information between patient statuses and treatments to extract more robust and discriminative representation of patient samples from their EHR data. Such representation finally benefits the model on TEP. The experimental results of two case studies demonstrate the superiority of our proposed method compared to state-of-the-art methods.

Endpoint prediction of heart failure using electronic health records.

BACKGROUND: Heart failure (HF) is a serious condition associated with high morbidity and mortality rates. Effective endpoint prediction in patient treatment trajectories provides preventative information about HF prognosis, guides decision making about the type and intensity of care, and enables better understanding of provider performance. OBJECTIVE: We explored the potential of a large volume of electronic health records (EHRs) for endpoint prediction of HF. Specifically, a suite of patient features observed at the prediction time point were utilized as the auxiliary information during the training of the prediction model. MATERIAL AND METHOD: We extract the latent representation of patient treatment trajectory by equipping a recurrent neural network (RNN) with two learning strategies, namely adversarial learning and multi-task learning. As for the adversarial learning strategy, an adversarial learning scheme is used to differentiate the generated feature vector from the real one, while in the multi-task learning strategy, we consider the prediction of patient feature vector as an auxiliary task other than endpoint prediction. With such learning strategies, the extracted representation of patient treatment trajectory is particularly optimized for predicting HF endpoint, including HF-readmission, all-cause mortality and their combination (i.e., composite endpoint). RESULTS AND DISCUSSION: We evaluate the proposed approach on a real clinical dataset collected from a Chinese hospital. The experimental dataset contains 2102 HF patient treatment trajectories with 13,545 visits on the hospital. The area under the ROC curve (AUC) achieved by our best model in predicting composite endpoint is 0.744, which is better than that of state-of-the-art models, including the standard Long Short Term Memory (0.727), Gated Recurrent Unit (0.732), RETAIN(0.730). With respect to the prediction of HF-readmission and all-cause mortality, our method also shows better performance than benchmark models. CONCLUSION: The experimental results show that the proposed model can achieve competitive performance over state-of-the-art models in terms of endpoint prediction for HF, and reveal some suggestive hypotheses that could be validated by further investigations in the medical domain.

Using neural attention networks to detect adverse medical events from electronic health records.

The detection of Adverse Medical Events (AMEs) plays an important role in disease management in ensuring efficient treatment delivery and quality improvement of health services. Recently, with the rapid development of hospital information systems, a large volume of Electronic Health Records (EHRs) have been produced, in which AMEs are regularly documented in a free-text manner. In this study, we are concerned with the problem of AME detection by utilizing a large volume of unstructured EHR data. To address this challenge, we propose a neural attention network-based model to incorporate the contextual information of words into AME detection. Specifically, we develop a context-aware attention mechanism to locate salient words with respect to the target AMEs in patient medical records. And then we combine the proposed context attention mechanism with the deep learning tactic to boost the performance of AME detection. We validate our proposed model on a real clinical dataset that consists of 8845 medical records of patients with cardiovascular diseases. The experimental results show that our proposed model advances state-of-the-art models and achieves competitive performance in terms of AME detection.